Commit
·
e618348
verified
·
0
Parent(s):
Duplicate from openbmb/MiniCPM-Llama3-V-2_5
Browse filesCo-authored-by: Hongji Zhu <[email protected]>
- .gitattributes +37 -0
- README.md +212 -0
- assets/MiniCPM-Llama3-V-2.5-benchmark.png +3 -0
- assets/MiniCPM-Llama3-V-2.5-peformance.png +3 -0
- assets/gif_cases/1-4.gif +3 -0
- assets/gif_cases/meal_plan.gif +3 -0
- assets/gif_cases/ticket.gif +3 -0
- assets/minicpmv-llama3-v2.5/case_OCR_en.png +3 -0
- assets/minicpmv-llama3-v2.5/case_complex_reasoning.png +3 -0
- assets/minicpmv-llama3-v2.5/case_long_img.png +3 -0
- assets/minicpmv-llama3-v2.5/case_markdown.png +3 -0
- assets/minicpmv-llama3-v2.5/cases_all.png +3 -0
- assets/minicpmv-llama3-v2.5/llavabench_compare.png +3 -0
- config.json +54 -0
- configuration_minicpm.py +113 -0
- generation_config.json +6 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +748 -0
- modeling_minicpmv.py +702 -0
- resampler.py +163 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2072 -0
.gitattributes
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
*.gif filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,212 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: visual-question-answering
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
- zh
|
| 6 |
+
datasets:
|
| 7 |
+
- openbmb/RLAIF-V-Dataset
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
<h1>A GPT-4V Level Multimodal LLM on Your Phone</h1>
|
| 12 |
+
|
| 13 |
+
[GitHub](https://github.com/OpenBMB/MiniCPM-V) | [Demo](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5) | <a href="https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/wechat.md" target="_blank"> WeChat</a>
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## News <!-- omit in toc -->
|
| 17 |
+
|
| 18 |
+
#### 📌 Pinned
|
| 19 |
+
|
| 20 |
+
* [2024.05.28] 🚀🚀🚀 MiniCPM-Llama3-V 2.5 now fully supports its feature in llama.cpp and ollama! Please pull the latest code **of our provided forks** ([llama.cpp](https://github.com/OpenBMB/llama.cpp/blob/minicpm-v2.5/examples/minicpmv/README.md), [ollama](https://github.com/OpenBMB/ollama/tree/minicpm-v2.5/examples/minicpm-v2.5)). GGUF models in various sizes are available [here](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf/tree/main). MiniCPM-Llama3-V 2.5 series is **not supported by the official repositories yet**, and we are working hard to merge PRs. Please stay tuned! You can visit our [GitHub](https://github.com/OpenBMB/MiniCPM-V) repository for more information!
|
| 21 |
+
* [2024.05.28] 💫 We now support LoRA fine-tuning for MiniCPM-Llama3-V 2.5, using only 2 V100 GPUs! See more statistics [here](https://github.com/OpenBMB/MiniCPM-V/tree/main/finetune#model-fine-tuning-memory-usage-statistics).
|
| 22 |
+
* [2024.05.23] 🔍 We've released a comprehensive comparison between Phi-3-vision-128k-instruct and MiniCPM-Llama3-V 2.5, including benchmarks evaluations, multilingual capabilities, and inference efficiency 🌟📊🌍🚀. Click [here](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/compare_with_phi-3_vision.md) to view more details.
|
| 23 |
+
* [2024.05.23] 🔥🔥🔥 MiniCPM-V tops GitHub Trending and HuggingFace Trending! Our demo, recommended by Hugging Face Gradio’s official account, is available [here](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5). Come and try it out!
|
| 24 |
+
|
| 25 |
+
<br>
|
| 26 |
+
|
| 27 |
+
* [2024.06.03] Now, you can run MiniCPM-Llama3-V 2.5 on multiple low VRAM GPUs(12 GB or 16 GB) by distributing the model's layers across multiple GPUs. For more details, Check this [link](https://github.com/OpenBMB/MiniCPM-V/blob/main/docs/inference_on_multiple_gpus.md).
|
| 28 |
+
* [2024.05.25] MiniCPM-Llama3-V 2.5 now supports streaming outputs and customized system prompts. Try it at [here](#usage)
|
| 29 |
+
* [2024.05.24] We release the [MiniCPM-Llama3-V 2.5 gguf](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf), which supports [llama.cpp](https://github.com/OpenBMB/MiniCPM-V/tree/main?tab=readme-ov-file#inference-with-llamacpp) inference and provides a 6~8 token/s smooth decoding on mobile phones. Try it now!
|
| 30 |
+
* [2024.05.20] We open-soure MiniCPM-Llama3-V 2.5, it has improved OCR capability and supports 30+ languages, representing the first end-side MLLM achieving GPT-4V level performance! We provide [efficient inference](#deployment-on-mobile-phone) and [simple fine-tuning](https://github.com/OpenBMB/MiniCPM-V/blob/main/finetune/readme.md). Try it now!
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
## Model Summary
|
| 34 |
+
|
| 35 |
+
**MiniCPM-Llama3-V 2.5** is the latest model in the MiniCPM-V series. The model is built on SigLip-400M and Llama3-8B-Instruct with a total of 8B parameters. It exhibits a significant performance improvement over MiniCPM-V 2.0. Notable features of MiniCPM-Llama3-V 2.5 include:
|
| 36 |
+
|
| 37 |
+
- 🔥 **Leading Performance.**
|
| 38 |
+
MiniCPM-Llama3-V 2.5 has achieved an average score of 65.1 on OpenCompass, a comprehensive evaluation over 11 popular benchmarks. **With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max** and greatly outperforms other Llama 3-based MLLMs.
|
| 39 |
+
|
| 40 |
+
- 💪 **Strong OCR Capabilities.**
|
| 41 |
+
MiniCPM-Llama3-V 2.5 can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344), achieving an **700+ score on OCRBench, surpassing proprietary models such as GPT-4o, GPT-4V-0409, Qwen-VL-Max and Gemini Pro**. Based on recent user feedback, MiniCPM-Llama3-V 2.5 has now enhanced full-text OCR extraction, table-to-markdown conversion, and other high-utility capabilities, and has further strengthened its instruction-following and complex reasoning abilities, enhancing multimodal interaction experiences.
|
| 42 |
+
|
| 43 |
+
- 🏆 **Trustworthy Behavior.**
|
| 44 |
+
Leveraging the latest [RLAIF-V](https://github.com/RLHF-V/RLAIF-V/) method (the newest technology in the [RLHF-V](https://github.com/RLHF-V) [CVPR'24] series), MiniCPM-Llama3-V 2.5 exhibits more trustworthy behavior. It achieves **10.3%** hallucination rate on Object HalBench, lower than GPT-4V-1106 (13.6%), achieving the best-level performance within the open-source community. [Data released](https://huggingface.co/datasets/openbmb/RLAIF-V-Dataset).
|
| 45 |
+
|
| 46 |
+
- 🌏 **Multilingual Support.**
|
| 47 |
+
Thanks to the strong multilingual capabilities of Llama 3 and the cross-lingual generalization technique from [VisCPM](https://github.com/OpenBMB/VisCPM), MiniCPM-Llama3-V 2.5 extends its bilingual (Chinese-English) multimodal capabilities to **over 30 languages including German, French, Spanish, Italian, Korean, Japanese etc.** [All Supported Languages](./assets/minicpm-llama-v-2-5_languages.md).
|
| 48 |
+
|
| 49 |
+
- 🚀 **Efficient Deployment.**
|
| 50 |
+
MiniCPM-Llama3-V 2.5 systematically employs **model quantization, CPU optimizations, NPU optimizations and compilation optimizations**, achieving high-efficiency deployment on edge devices. For mobile phones with Qualcomm chips, we have integrated the NPU acceleration framework QNN into llama.cpp for the first time. After systematic optimization, MiniCPM-Llama3-V 2.5 has realized a **150-fold acceleration in multimodal large model end-side image encoding** and a **3-fold increase in language decoding speed**.
|
| 51 |
+
|
| 52 |
+
- 💫 **Easy Usage.**
|
| 53 |
+
MiniCPM-Llama3-V 2.5 can be easily used in various ways: (1) [llama.cpp](https://github.com/OpenBMB/llama.cpp/blob/minicpm-v2.5/examples/minicpmv/README.md) and [ollama](https://github.com/OpenBMB/ollama/tree/minicpm-v2.5/examples/minicpm-v2.5) support for efficient CPU inference on local devices, (2) [GGUF](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-gguf) format quantized models in 16 sizes, (3) efficient [LoRA](https://github.com/OpenBMB/MiniCPM-V/tree/main/finetune#lora-finetuning) fine-tuning with only 2 V100 GPUs, (4) [streaming output](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5#usage), (5) quick local WebUI demo setup with [Gradio](https://github.com/OpenBMB/MiniCPM-V/blob/main/web_demo_2.5.py) and [Streamlit](https://github.com/OpenBMB/MiniCPM-V/blob/main/web_demo_streamlit-2_5.py), and (6) interactive demos on [HuggingFace Spaces](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5).
|
| 54 |
+
|
| 55 |
+
### Evaluation <!-- omit in toc -->
|
| 56 |
+
|
| 57 |
+
Results on TextVQA, DocVQA, OCRBench, OpenCompass MultiModal Avg , MME, MMBench, MMMU, MathVista, LLaVA Bench, RealWorld QA, Object HalBench.
|
| 58 |
+
|
| 59 |
+
<div align="center">
|
| 60 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/64abc4aa6cadc7aca585dddf/v2KE3wqQgM05ZW3dH2wbx.png" width="110%" />
|
| 61 |
+
</div>
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
Evaluation results of multilingual LLaVA Bench
|
| 65 |
+
<div align="center">
|
| 66 |
+
<img src="assets/minicpmv-llama3-v2.5/llavabench_compare.png" width="110%" />
|
| 67 |
+
</div>
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Examples <!-- omit in toc -->
|
| 71 |
+
|
| 72 |
+
<table align="center">
|
| 73 |
+
<p align="center">
|
| 74 |
+
<img src="assets/minicpmv-llama3-v2.5/cases_all.png" width=95%/>
|
| 75 |
+
</p>
|
| 76 |
+
</table>
|
| 77 |
+
|
| 78 |
+
We deploy MiniCPM-Llama3-V 2.5 on end devices. The demo video is the raw screen recording on a Xiaomi 14 Pro without edition.
|
| 79 |
+
|
| 80 |
+
<table align="center">
|
| 81 |
+
<p align="center">
|
| 82 |
+
<img src="assets/gif_cases/ticket.gif" width=40% style="display:inline-block;"/>
|
| 83 |
+
<img src="assets/gif_cases/meal_plan.gif" width=40% style="display:inline-block;"/>
|
| 84 |
+
</p>
|
| 85 |
+
</table>
|
| 86 |
+
|
| 87 |
+
<table align="center">
|
| 88 |
+
<p align="center">
|
| 89 |
+
<img src="assets/gif_cases/1-4.gif" width=80%/>
|
| 90 |
+
</p>
|
| 91 |
+
</table>
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
## Demo
|
| 96 |
+
Click here to try out the Demo of [MiniCPM-Llama3-V 2.5](https://huggingface.co/spaces/openbmb/MiniCPM-Llama3-V-2_5).
|
| 97 |
+
|
| 98 |
+
## Deployment on Mobile Phone
|
| 99 |
+
Coming soon.
|
| 100 |
+
|
| 101 |
+
## Usage
|
| 102 |
+
Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.10：
|
| 103 |
+
```
|
| 104 |
+
Pillow==10.1.0
|
| 105 |
+
torch==2.1.2
|
| 106 |
+
torchvision==0.16.2
|
| 107 |
+
transformers==4.40.0
|
| 108 |
+
sentencepiece==0.1.99
|
| 109 |
+
```
|
| 110 |
+
|
| 111 |
+
```python
|
| 112 |
+
# test.py
|
| 113 |
+
import torch
|
| 114 |
+
from PIL import Image
|
| 115 |
+
from transformers import AutoModel, AutoTokenizer
|
| 116 |
+
|
| 117 |
+
model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_remote_code=True, torch_dtype=torch.float16)
|
| 118 |
+
model = model.to(device='cuda')
|
| 119 |
+
|
| 120 |
+
tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_remote_code=True)
|
| 121 |
+
model.eval()
|
| 122 |
+
|
| 123 |
+
image = Image.open('xx.jpg').convert('RGB')
|
| 124 |
+
question = 'What is in the image?'
|
| 125 |
+
msgs = [{'role': 'user', 'content': question}]
|
| 126 |
+
|
| 127 |
+
res = model.chat(
|
| 128 |
+
image=image,
|
| 129 |
+
msgs=msgs,
|
| 130 |
+
tokenizer=tokenizer,
|
| 131 |
+
sampling=True, # if sampling=False, beam_search will be used by default
|
| 132 |
+
temperature=0.7,
|
| 133 |
+
# system_prompt='' # pass system_prompt if needed
|
| 134 |
+
)
|
| 135 |
+
print(res)
|
| 136 |
+
|
| 137 |
+
## if you want to use streaming, please make sure sampling=True and stream=True
|
| 138 |
+
## the model.chat will return a generator
|
| 139 |
+
res = model.chat(
|
| 140 |
+
image=image,
|
| 141 |
+
msgs=msgs,
|
| 142 |
+
tokenizer=tokenizer,
|
| 143 |
+
sampling=True,
|
| 144 |
+
temperature=0.7,
|
| 145 |
+
stream=True
|
| 146 |
+
)
|
| 147 |
+
|
| 148 |
+
generated_text = ""
|
| 149 |
+
for new_text in res:
|
| 150 |
+
generated_text += new_text
|
| 151 |
+
print(new_text, flush=True, end='')
|
| 152 |
+
```
|
| 153 |
+
|
| 154 |
+
Please look at [GitHub](https://github.com/OpenBMB/MiniCPM-V) for more detail about usage.
|
| 155 |
+
|
| 156 |
+
|
| 157 |
+
## Inference with llama.cpp<a id="llamacpp"></a>
|
| 158 |
+
MiniCPM-Llama3-V 2.5 can run with llama.cpp now! See our fork of [llama.cpp](https://github.com/OpenBMB/llama.cpp/tree/minicpm-v2.5/examples/minicpmv) for more detail.
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
## Int4 quantized version
|
| 162 |
+
Download the int4 quantized version for lower GPU memory (8GB) usage: [MiniCPM-Llama3-V-2_5-int4](https://huggingface.co/openbmb/MiniCPM-Llama3-V-2_5-int4).
|
| 163 |
+
|
| 164 |
+
## MiniCPM-V 2.0 <!-- omit in toc -->
|
| 165 |
+
Please see the info about MiniCPM-V 2.0 [here](https://huggingface.co/openbmb/MiniCPM-V-2).
|
| 166 |
+
|
| 167 |
+
## License
|
| 168 |
+
#### Model License
|
| 169 |
+
* The code in this repo is released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License.
|
| 170 |
+
* The usage of MiniCPM-V series model weights must strictly follow [MiniCPM Model License.md](https://github.com/OpenBMB/MiniCPM/blob/main/MiniCPM%20Model%20License.md).
|
| 171 |
+
* The models and weights of MiniCPM are completely free for academic research. after filling out a ["questionnaire"](https://modelbest.feishu.cn/share/base/form/shrcnpV5ZT9EJ6xYjh3Kx0J6v8g) for registration, are also available for free commercial use.
|
| 172 |
+
|
| 173 |
+
|
| 174 |
+
|
| 175 |
+
#### Statement
|
| 176 |
+
* As an LLM, MiniCPM-Llama3-V 2.5 generates contents by learning a large mount of texts, but it cannot comprehend, express personal opinions or make value judgement. Anything generated by MiniCPM-Llama3-V 2.5 does not represent the views and positions of the model developers
|
| 177 |
+
* We will not be liable for any problems arising from the use of the MinCPM-V open Source model, including but not limited to data security issues, risk of public opinion, or any risks and problems arising from the misdirection, misuse, dissemination or misuse of the model.
|
| 178 |
+
|
| 179 |
+
## Other Multimodal Projects from Our Team
|
| 180 |
+
|
| 181 |
+
[VisCPM](https://github.com/OpenBMB/VisCPM/tree/main) | [RLHF-V](https://github.com/RLHF-V/RLHF-V) | [LLaVA-UHD](https://github.com/thunlp/LLaVA-UHD) | [RLAIF-V](https://github.com/RLHF-V/RLAIF-V)
|
| 182 |
+
|
| 183 |
+
## Citation
|
| 184 |
+
|
| 185 |
+
If you find our work helpful, please consider citing the following papers
|
| 186 |
+
|
| 187 |
+
```bib
|
| 188 |
+
@article{yu2023rlhf,
|
| 189 |
+
title={Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback},
|
| 190 |
+
author={Yu, Tianyu and Yao, Yuan and Zhang, Haoye and He, Taiwen and Han, Yifeng and Cui, Ganqu and Hu, Jinyi and Liu, Zhiyuan and Zheng, Hai-Tao and Sun, Maosong and others},
|
| 191 |
+
journal={arXiv preprint arXiv:2312.00849},
|
| 192 |
+
year={2023}
|
| 193 |
+
}
|
| 194 |
+
@article{viscpm,
|
| 195 |
+
title={Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages},
|
| 196 |
+
author={Jinyi Hu and Yuan Yao and Chongyi Wang and Shan Wang and Yinxu Pan and Qianyu Chen and Tianyu Yu and Hanghao Wu and Yue Zhao and Haoye Zhang and Xu Han and Yankai Lin and Jiao Xue and Dahai Li and Zhiyuan Liu and Maosong Sun},
|
| 197 |
+
journal={arXiv preprint arXiv:2308.12038},
|
| 198 |
+
year={2023}
|
| 199 |
+
}
|
| 200 |
+
@article{xu2024llava-uhd,
|
| 201 |
+
title={{LLaVA-UHD}: an LMM Perceiving Any Aspect Ratio and High-Resolution Images},
|
| 202 |
+
author={Xu, Ruyi and Yao, Yuan and Guo, Zonghao and Cui, Junbo and Ni, Zanlin and Ge, Chunjiang and Chua, Tat-Seng and Liu, Zhiyuan and Huang, Gao},
|
| 203 |
+
journal={arXiv preprint arXiv:2403.11703},
|
| 204 |
+
year={2024}
|
| 205 |
+
}
|
| 206 |
+
@article{yu2024rlaifv,
|
| 207 |
+
title={RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness},
|
| 208 |
+
author={Yu, Tianyu and Zhang, Haoye and Yao, Yuan and Dang, Yunkai and Chen, Da and Lu, Xiaoman and Cui, Ganqu and He, Taiwen and Liu, Zhiyuan and Chua, Tat-Seng and Sun, Maosong},
|
| 209 |
+
journal={arXiv preprint arXiv:2405.17220},
|
| 210 |
+
year={2024},
|
| 211 |
+
}
|
| 212 |
+
```
|
assets/MiniCPM-Llama3-V-2.5-benchmark.png
ADDED
|
Git LFS Details
|
assets/MiniCPM-Llama3-V-2.5-peformance.png
ADDED
|
Git LFS Details
|
assets/gif_cases/1-4.gif
ADDED
|
Git LFS Details
|
assets/gif_cases/meal_plan.gif
ADDED
|
Git LFS Details
|
assets/gif_cases/ticket.gif
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/case_OCR_en.png
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/case_complex_reasoning.png
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/case_long_img.png
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/case_markdown.png
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/cases_all.png
ADDED
|
Git LFS Details
|
assets/minicpmv-llama3-v2.5/llavabench_compare.png
ADDED
|
Git LFS Details
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "openbmb/MiniCPM-Llama3-V-2_5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MiniCPMV"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"auto_map": {
|
| 9 |
+
"AutoConfig": "configuration_minicpm.MiniCPMVConfig",
|
| 10 |
+
"AutoModel": "modeling_minicpmv.MiniCPMV",
|
| 11 |
+
"AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
|
| 12 |
+
},
|
| 13 |
+
"batch_vision_input": true,
|
| 14 |
+
"bos_token_id": 128000,
|
| 15 |
+
"drop_vision_last_layer": false,
|
| 16 |
+
"eos_token_id": 128001,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 4096,
|
| 19 |
+
"image_size": 448,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 14336,
|
| 22 |
+
"max_position_embeddings": 8192,
|
| 23 |
+
"mm_use_im_start_end": true,
|
| 24 |
+
"model_type": "minicpmv",
|
| 25 |
+
"num_attention_heads": 32,
|
| 26 |
+
"num_hidden_layers": 32,
|
| 27 |
+
"num_key_value_heads": 8,
|
| 28 |
+
"patch_size": 14,
|
| 29 |
+
"pretraining_tp": 1,
|
| 30 |
+
"query_num": 96,
|
| 31 |
+
"rms_norm_eps": 1e-05,
|
| 32 |
+
"rope_scaling": null,
|
| 33 |
+
"rope_theta": 500000.0,
|
| 34 |
+
"slice_config": {
|
| 35 |
+
"max_slice_nums": 9,
|
| 36 |
+
"patch_size": 14,
|
| 37 |
+
"model_type": "minicpmv"
|
| 38 |
+
},
|
| 39 |
+
"slice_mode": true,
|
| 40 |
+
"tie_word_embeddings": false,
|
| 41 |
+
"torch_dtype": "float16",
|
| 42 |
+
"transformers_version": "4.40.0",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"vision_config": {
|
| 45 |
+
"hidden_size": 1152,
|
| 46 |
+
"image_size": 980,
|
| 47 |
+
"intermediate_size": 4304,
|
| 48 |
+
"model_type": "idefics2",
|
| 49 |
+
"num_attention_heads": 16,
|
| 50 |
+
"num_hidden_layers": 27,
|
| 51 |
+
"patch_size": 14
|
| 52 |
+
},
|
| 53 |
+
"vocab_size": 128256
|
| 54 |
+
}
|
configuration_minicpm.py
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# coding=utf-8
|
| 2 |
+
# Copyright 2022 EleutherAI and the HuggingFace Inc. team. All rights reserved.
|
| 3 |
+
#
|
| 4 |
+
# This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX
|
| 5 |
+
# and OPT implementations in this library. It has been modified from its
|
| 6 |
+
# original forms to accommodate minor architectural differences compared
|
| 7 |
+
# to GPT-NeoX and OPT used by the Meta AI team that trained the model.
|
| 8 |
+
#
|
| 9 |
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
| 10 |
+
# you may not use this file except in compliance with the License.
|
| 11 |
+
# You may obtain a copy of the License at
|
| 12 |
+
#
|
| 13 |
+
# http://www.apache.org/licenses/LICENSE-2.0
|
| 14 |
+
#
|
| 15 |
+
# Unless required by applicable law or agreed to in writing, software
|
| 16 |
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
| 17 |
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
| 18 |
+
# See the License for the specific language governing permissions and
|
| 19 |
+
# limitations under the License.
|
| 20 |
+
""" MiniCPM model configuration"""
|
| 21 |
+
import os
|
| 22 |
+
from typing import Union
|
| 23 |
+
|
| 24 |
+
from transformers.utils import logging
|
| 25 |
+
from transformers import LlamaConfig, PretrainedConfig
|
| 26 |
+
from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionConfig
|
| 27 |
+
|
| 28 |
+
logger = logging.get_logger(__name__)
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
class MiniCPMVSliceConfig(PretrainedConfig):
|
| 32 |
+
model_type = "minicpmv"
|
| 33 |
+
|
| 34 |
+
def __init__(
|
| 35 |
+
self,
|
| 36 |
+
patch_size=14,
|
| 37 |
+
max_slice_nums=9,
|
| 38 |
+
scale_resolution=448,
|
| 39 |
+
**kwargs,
|
| 40 |
+
):
|
| 41 |
+
super().__init__(**kwargs)
|
| 42 |
+
self.patch_size = patch_size
|
| 43 |
+
self.max_slice_nums = max_slice_nums
|
| 44 |
+
self.scale_resolution = scale_resolution
|
| 45 |
+
|
| 46 |
+
@classmethod
|
| 47 |
+
def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
|
| 48 |
+
cls._set_token_in_kwargs(kwargs)
|
| 49 |
+
|
| 50 |
+
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
|
| 51 |
+
|
| 52 |
+
if config_dict.get("model_type") == "minicpmv":
|
| 53 |
+
config_dict = config_dict["slice_config"]
|
| 54 |
+
|
| 55 |
+
if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
|
| 56 |
+
logger.warning(
|
| 57 |
+
f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
|
| 58 |
+
f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
|
| 59 |
+
)
|
| 60 |
+
|
| 61 |
+
return cls.from_dict(config_dict, **kwargs)
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
class MiniCPMVConfig(LlamaConfig):
|
| 66 |
+
model_type = "minicpmv"
|
| 67 |
+
keys_to_ignore_at_inference = ["past_key_values"]
|
| 68 |
+
|
| 69 |
+
default_vision_config = {
|
| 70 |
+
"hidden_size": 1152,
|
| 71 |
+
"image_size": 980,
|
| 72 |
+
"intermediate_size": 4304,
|
| 73 |
+
"model_type": "idefics2",
|
| 74 |
+
"num_attention_heads": 16,
|
| 75 |
+
"num_hidden_layers": 27,
|
| 76 |
+
"patch_size": 14,
|
| 77 |
+
}
|
| 78 |
+
|
| 79 |
+
def __init__(
|
| 80 |
+
self,
|
| 81 |
+
use_cache=True,
|
| 82 |
+
query_num=64,
|
| 83 |
+
image_size=448,
|
| 84 |
+
drop_vision_last_layer=True,
|
| 85 |
+
batch_vision_input=True,
|
| 86 |
+
slice_config=None,
|
| 87 |
+
vision_config=None,
|
| 88 |
+
**kwargs,
|
| 89 |
+
):
|
| 90 |
+
self.use_cache = use_cache
|
| 91 |
+
self.query_num = query_num
|
| 92 |
+
self.image_size = image_size
|
| 93 |
+
self.drop_vision_last_layer = drop_vision_last_layer
|
| 94 |
+
self.batch_vision_input = batch_vision_input
|
| 95 |
+
|
| 96 |
+
if slice_config is None:
|
| 97 |
+
self.slice_config = MiniCPMVSliceConfig(max_slice_nums=1)
|
| 98 |
+
else:
|
| 99 |
+
self.slice_config = MiniCPMVSliceConfig(**slice_config)
|
| 100 |
+
self.slice_mode = True
|
| 101 |
+
|
| 102 |
+
# same as HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit
|
| 103 |
+
if vision_config is None:
|
| 104 |
+
self.vision_config = Idefics2VisionConfig(**self.default_vision_config)
|
| 105 |
+
logger.info("vision_config is None, using default vision config")
|
| 106 |
+
elif isinstance(vision_config, dict):
|
| 107 |
+
self.vision_config = Idefics2VisionConfig(**vision_config)
|
| 108 |
+
elif isinstance(vision_config, Idefics2VisionConfig):
|
| 109 |
+
self.vision_config = vision_config
|
| 110 |
+
|
| 111 |
+
self.patch_size = self.vision_config.patch_size
|
| 112 |
+
|
| 113 |
+
super().__init__(**kwargs)
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"eos_token_id": 128001,
|
| 5 |
+
"transformers_version": "4.40.0"
|
| 6 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45cb989d608666713ecd5a1fbd9d9728d560b6f67846aefa29fb980d5b723a80
|
| 3 |
+
size 2443235064
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06ea145d0841c392c2d2a261e83c9523ac7f2f30d2292f7ddbb00f7a28e5dc47
|
| 3 |
+
size 2416006592
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13aa3033a8c96e1a09326c68f755655d2c98383fef0277c57e851776cb41ace7
|
| 3 |
+
size 2499909808
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a41e014eeaf91645e468279cb092ed3f189b3a8679b4950bd9fcd34ac45a350
|
| 3 |
+
size 2499909832
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec7c6f6f1c80cd8f7d8fde4cc50726e077801cd360ae48ca5506146b6b19a6e5
|
| 3 |
+
size 2416006640
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11b58e0535e426d5c35239e67caedcf3178254031435d28b86e6e2f2dd89229e
|
| 3 |
+
size 2499909816
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:773eae47408e0a463826016c6cd58441dbd9f06c9e5f1998aa77ba60729a7dce
|
| 3 |
+
size 2299293224
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,748 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 34148369344
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"llm.lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"llm.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"llm.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"llm.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"llm.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"llm.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"llm.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"llm.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"llm.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"llm.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"llm.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 17 |
+
"llm.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"llm.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"llm.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"llm.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"llm.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"llm.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"llm.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"llm.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"llm.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 26 |
+
"llm.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 27 |
+
"llm.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 28 |
+
"llm.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 29 |
+
"llm.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 30 |
+
"llm.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 31 |
+
"llm.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 32 |
+
"llm.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"llm.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"llm.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"llm.model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"llm.model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 37 |
+
"llm.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 38 |
+
"llm.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"llm.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"llm.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 41 |
+
"llm.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"llm.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 43 |
+
"llm.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"llm.model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"llm.model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"llm.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 47 |
+
"llm.model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"llm.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"llm.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 50 |
+
"llm.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"llm.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"llm.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 53 |
+
"llm.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"llm.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 55 |
+
"llm.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"llm.model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 57 |
+
"llm.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"llm.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"llm.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"llm.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"llm.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 62 |
+
"llm.model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 63 |
+
"llm.model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 64 |
+
"llm.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 65 |
+
"llm.model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 66 |
+
"llm.model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 67 |
+
"llm.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"llm.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 69 |
+
"llm.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 70 |
+
"llm.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 71 |
+
"llm.model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"llm.model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"llm.model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 74 |
+
"llm.model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 75 |
+
"llm.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 76 |
+
"llm.model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 77 |
+
"llm.model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 78 |
+
"llm.model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 79 |
+
"llm.model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 80 |
+
"llm.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"llm.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"llm.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"llm.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"llm.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"llm.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 86 |
+
"llm.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 87 |
+
"llm.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"llm.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 89 |
+
"llm.model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"llm.model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 91 |
+
"llm.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"llm.model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"llm.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"llm.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"llm.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"llm.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 97 |
+
"llm.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 98 |
+
"llm.model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"llm.model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"llm.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 101 |
+
"llm.model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"llm.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 103 |
+
"llm.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"llm.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"llm.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"llm.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 107 |
+
"llm.model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"llm.model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"llm.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 110 |
+
"llm.model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"llm.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"llm.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 113 |
+
"llm.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"llm.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 115 |
+
"llm.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"llm.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 117 |
+
"llm.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 118 |
+
"llm.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 119 |
+
"llm.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 120 |
+
"llm.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 121 |
+
"llm.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 122 |
+
"llm.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 123 |
+
"llm.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 124 |
+
"llm.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 125 |
+
"llm.model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 126 |
+
"llm.model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 127 |
+
"llm.model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 128 |
+
"llm.model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 129 |
+
"llm.model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 130 |
+
"llm.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 131 |
+
"llm.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 132 |
+
"llm.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 133 |
+
"llm.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 134 |
+
"llm.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 135 |
+
"llm.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 136 |
+
"llm.model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 137 |
+
"llm.model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 138 |
+
"llm.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 139 |
+
"llm.model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 140 |
+
"llm.model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"llm.model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"llm.model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"llm.model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"llm.model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"llm.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 146 |
+
"llm.model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 147 |
+
"llm.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"llm.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 149 |
+
"llm.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"llm.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 151 |
+
"llm.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"llm.model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 153 |
+
"llm.model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 154 |
+
"llm.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 155 |
+
"llm.model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 156 |
+
"llm.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 157 |
+
"llm.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 158 |
+
"llm.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 159 |
+
"llm.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 160 |
+
"llm.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 161 |
+
"llm.model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 162 |
+
"llm.model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 163 |
+
"llm.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 164 |
+
"llm.model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"llm.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"llm.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 167 |
+
"llm.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"llm.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 169 |
+
"llm.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 170 |
+
"llm.model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 171 |
+
"llm.model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 172 |
+
"llm.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 173 |
+
"llm.model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"llm.model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 175 |
+
"llm.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"llm.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 177 |
+
"llm.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"llm.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 179 |
+
"llm.model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 180 |
+
"llm.model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 181 |
+
"llm.model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 182 |
+
"llm.model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 183 |
+
"llm.model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 184 |
+
"llm.model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 185 |
+
"llm.model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 186 |
+
"llm.model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 187 |
+
"llm.model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 188 |
+
"llm.model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 189 |
+
"llm.model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 190 |
+
"llm.model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 191 |
+
"llm.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 192 |
+
"llm.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 193 |
+
"llm.model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 194 |
+
"llm.model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 195 |
+
"llm.model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 196 |
+
"llm.model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 197 |
+
"llm.model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 198 |
+
"llm.model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 199 |
+
"llm.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 200 |
+
"llm.model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 201 |
+
"llm.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 202 |
+
"llm.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 203 |
+
"llm.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 204 |
+
"llm.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 205 |
+
"llm.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 206 |
+
"llm.model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 207 |
+
"llm.model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 208 |
+
"llm.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 209 |
+
"llm.model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 210 |
+
"llm.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 211 |
+
"llm.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 212 |
+
"llm.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"llm.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"llm.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"llm.model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 216 |
+
"llm.model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 217 |
+
"llm.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 218 |
+
"llm.model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 219 |
+
"llm.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 220 |
+
"llm.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 221 |
+
"llm.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 222 |
+
"llm.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 223 |
+
"llm.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 224 |
+
"llm.model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"llm.model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"llm.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 227 |
+
"llm.model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"llm.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 229 |
+
"llm.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 230 |
+
"llm.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 231 |
+
"llm.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 232 |
+
"llm.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 233 |
+
"llm.model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 234 |
+
"llm.model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
| 235 |
+
"llm.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 236 |
+
"llm.model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
| 237 |
+
"llm.model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
| 238 |
+
"llm.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 239 |
+
"llm.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 240 |
+
"llm.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 241 |
+
"llm.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 242 |
+
"llm.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 243 |
+
"llm.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 244 |
+
"llm.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 245 |
+
"llm.model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 246 |
+
"llm.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 247 |
+
"llm.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 248 |
+
"llm.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 249 |
+
"llm.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 250 |
+
"llm.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 251 |
+
"llm.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 252 |
+
"llm.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 253 |
+
"llm.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 254 |
+
"llm.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 255 |
+
"llm.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 256 |
+
"llm.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 257 |
+
"llm.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 258 |
+
"llm.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 259 |
+
"llm.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 260 |
+
"llm.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 261 |
+
"llm.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 262 |
+
"llm.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 263 |
+
"llm.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 264 |
+
"llm.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 265 |
+
"llm.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 266 |
+
"llm.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 267 |
+
"llm.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 268 |
+
"llm.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 269 |
+
"llm.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"llm.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 271 |
+
"llm.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"llm.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"llm.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 274 |
+
"llm.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"llm.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 276 |
+
"llm.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 277 |
+
"llm.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 278 |
+
"llm.model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 279 |
+
"llm.model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 280 |
+
"llm.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 281 |
+
"llm.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"llm.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 283 |
+
"llm.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"llm.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"llm.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"llm.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 287 |
+
"llm.model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 288 |
+
"llm.model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 289 |
+
"llm.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 290 |
+
"llm.model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 291 |
+
"llm.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 292 |
+
"llm.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 293 |
+
"llm.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 294 |
+
"llm.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 295 |
+
"llm.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 296 |
+
"llm.model.norm.weight": "model-00007-of-00007.safetensors",
|
| 297 |
+
"resampler.attn.in_proj_bias": "model-00007-of-00007.safetensors",
|
| 298 |
+
"resampler.attn.in_proj_weight": "model-00007-of-00007.safetensors",
|
| 299 |
+
"resampler.attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 300 |
+
"resampler.attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 301 |
+
"resampler.kv_proj.weight": "model-00007-of-00007.safetensors",
|
| 302 |
+
"resampler.ln_kv.bias": "model-00007-of-00007.safetensors",
|
| 303 |
+
"resampler.ln_kv.weight": "model-00007-of-00007.safetensors",
|
| 304 |
+
"resampler.ln_post.bias": "model-00007-of-00007.safetensors",
|
| 305 |
+
"resampler.ln_post.weight": "model-00007-of-00007.safetensors",
|
| 306 |
+
"resampler.ln_q.bias": "model-00007-of-00007.safetensors",
|
| 307 |
+
"resampler.ln_q.weight": "model-00007-of-00007.safetensors",
|
| 308 |
+
"resampler.proj": "model-00007-of-00007.safetensors",
|
| 309 |
+
"resampler.query": "model-00007-of-00007.safetensors",
|
| 310 |
+
"vpm.embeddings.patch_embedding.bias": "model-00007-of-00007.safetensors",
|
| 311 |
+
"vpm.embeddings.patch_embedding.weight": "model-00007-of-00007.safetensors",
|
| 312 |
+
"vpm.embeddings.position_embedding.weight": "model-00007-of-00007.safetensors",
|
| 313 |
+
"vpm.encoder.layers.0.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 314 |
+
"vpm.encoder.layers.0.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 315 |
+
"vpm.encoder.layers.0.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 316 |
+
"vpm.encoder.layers.0.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 317 |
+
"vpm.encoder.layers.0.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 318 |
+
"vpm.encoder.layers.0.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 319 |
+
"vpm.encoder.layers.0.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 320 |
+
"vpm.encoder.layers.0.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 321 |
+
"vpm.encoder.layers.0.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 322 |
+
"vpm.encoder.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 323 |
+
"vpm.encoder.layers.0.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 324 |
+
"vpm.encoder.layers.0.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 325 |
+
"vpm.encoder.layers.0.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 326 |
+
"vpm.encoder.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 327 |
+
"vpm.encoder.layers.0.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 328 |
+
"vpm.encoder.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 329 |
+
"vpm.encoder.layers.1.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 330 |
+
"vpm.encoder.layers.1.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 331 |
+
"vpm.encoder.layers.1.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 332 |
+
"vpm.encoder.layers.1.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 333 |
+
"vpm.encoder.layers.1.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 334 |
+
"vpm.encoder.layers.1.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 335 |
+
"vpm.encoder.layers.1.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 336 |
+
"vpm.encoder.layers.1.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 337 |
+
"vpm.encoder.layers.1.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 338 |
+
"vpm.encoder.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 339 |
+
"vpm.encoder.layers.1.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 340 |
+
"vpm.encoder.layers.1.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 341 |
+
"vpm.encoder.layers.1.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 342 |
+
"vpm.encoder.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 343 |
+
"vpm.encoder.layers.1.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 344 |
+
"vpm.encoder.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 345 |
+
"vpm.encoder.layers.10.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 346 |
+
"vpm.encoder.layers.10.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 347 |
+
"vpm.encoder.layers.10.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 348 |
+
"vpm.encoder.layers.10.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 349 |
+
"vpm.encoder.layers.10.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 350 |
+
"vpm.encoder.layers.10.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 351 |
+
"vpm.encoder.layers.10.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 352 |
+
"vpm.encoder.layers.10.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 353 |
+
"vpm.encoder.layers.10.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 354 |
+
"vpm.encoder.layers.10.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 355 |
+
"vpm.encoder.layers.10.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 356 |
+
"vpm.encoder.layers.10.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 357 |
+
"vpm.encoder.layers.10.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 358 |
+
"vpm.encoder.layers.10.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 359 |
+
"vpm.encoder.layers.10.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 360 |
+
"vpm.encoder.layers.10.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 361 |
+
"vpm.encoder.layers.11.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 362 |
+
"vpm.encoder.layers.11.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 363 |
+
"vpm.encoder.layers.11.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 364 |
+
"vpm.encoder.layers.11.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 365 |
+
"vpm.encoder.layers.11.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 366 |
+
"vpm.encoder.layers.11.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 367 |
+
"vpm.encoder.layers.11.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 368 |
+
"vpm.encoder.layers.11.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 369 |
+
"vpm.encoder.layers.11.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 370 |
+
"vpm.encoder.layers.11.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 371 |
+
"vpm.encoder.layers.11.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 372 |
+
"vpm.encoder.layers.11.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 373 |
+
"vpm.encoder.layers.11.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 374 |
+
"vpm.encoder.layers.11.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 375 |
+
"vpm.encoder.layers.11.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 376 |
+
"vpm.encoder.layers.11.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 377 |
+
"vpm.encoder.layers.12.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 378 |
+
"vpm.encoder.layers.12.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 379 |
+
"vpm.encoder.layers.12.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 380 |
+
"vpm.encoder.layers.12.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 381 |
+
"vpm.encoder.layers.12.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 382 |
+
"vpm.encoder.layers.12.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 383 |
+
"vpm.encoder.layers.12.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 384 |
+
"vpm.encoder.layers.12.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 385 |
+
"vpm.encoder.layers.12.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 386 |
+
"vpm.encoder.layers.12.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 387 |
+
"vpm.encoder.layers.12.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 388 |
+
"vpm.encoder.layers.12.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 389 |
+
"vpm.encoder.layers.12.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 390 |
+
"vpm.encoder.layers.12.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 391 |
+
"vpm.encoder.layers.12.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 392 |
+
"vpm.encoder.layers.12.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 393 |
+
"vpm.encoder.layers.13.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 394 |
+
"vpm.encoder.layers.13.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 395 |
+
"vpm.encoder.layers.13.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 396 |
+
"vpm.encoder.layers.13.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 397 |
+
"vpm.encoder.layers.13.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 398 |
+
"vpm.encoder.layers.13.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 399 |
+
"vpm.encoder.layers.13.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 400 |
+
"vpm.encoder.layers.13.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 401 |
+
"vpm.encoder.layers.13.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 402 |
+
"vpm.encoder.layers.13.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 403 |
+
"vpm.encoder.layers.13.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 404 |
+
"vpm.encoder.layers.13.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 405 |
+
"vpm.encoder.layers.13.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 406 |
+
"vpm.encoder.layers.13.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 407 |
+
"vpm.encoder.layers.13.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 408 |
+
"vpm.encoder.layers.13.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 409 |
+
"vpm.encoder.layers.14.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 410 |
+
"vpm.encoder.layers.14.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 411 |
+
"vpm.encoder.layers.14.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 412 |
+
"vpm.encoder.layers.14.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 413 |
+
"vpm.encoder.layers.14.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 414 |
+
"vpm.encoder.layers.14.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 415 |
+
"vpm.encoder.layers.14.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 416 |
+
"vpm.encoder.layers.14.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 417 |
+
"vpm.encoder.layers.14.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 418 |
+
"vpm.encoder.layers.14.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 419 |
+
"vpm.encoder.layers.14.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 420 |
+
"vpm.encoder.layers.14.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 421 |
+
"vpm.encoder.layers.14.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 422 |
+
"vpm.encoder.layers.14.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 423 |
+
"vpm.encoder.layers.14.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 424 |
+
"vpm.encoder.layers.14.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 425 |
+
"vpm.encoder.layers.15.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 426 |
+
"vpm.encoder.layers.15.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 427 |
+
"vpm.encoder.layers.15.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 428 |
+
"vpm.encoder.layers.15.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 429 |
+
"vpm.encoder.layers.15.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 430 |
+
"vpm.encoder.layers.15.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 431 |
+
"vpm.encoder.layers.15.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 432 |
+
"vpm.encoder.layers.15.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 433 |
+
"vpm.encoder.layers.15.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 434 |
+
"vpm.encoder.layers.15.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 435 |
+
"vpm.encoder.layers.15.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 436 |
+
"vpm.encoder.layers.15.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 437 |
+
"vpm.encoder.layers.15.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 438 |
+
"vpm.encoder.layers.15.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 439 |
+
"vpm.encoder.layers.15.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 440 |
+
"vpm.encoder.layers.15.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 441 |
+
"vpm.encoder.layers.16.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 442 |
+
"vpm.encoder.layers.16.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 443 |
+
"vpm.encoder.layers.16.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 444 |
+
"vpm.encoder.layers.16.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 445 |
+
"vpm.encoder.layers.16.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 446 |
+
"vpm.encoder.layers.16.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 447 |
+
"vpm.encoder.layers.16.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 448 |
+
"vpm.encoder.layers.16.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 449 |
+
"vpm.encoder.layers.16.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 450 |
+
"vpm.encoder.layers.16.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 451 |
+
"vpm.encoder.layers.16.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 452 |
+
"vpm.encoder.layers.16.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 453 |
+
"vpm.encoder.layers.16.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 454 |
+
"vpm.encoder.layers.16.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 455 |
+
"vpm.encoder.layers.16.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 456 |
+
"vpm.encoder.layers.16.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 457 |
+
"vpm.encoder.layers.17.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 458 |
+
"vpm.encoder.layers.17.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 459 |
+
"vpm.encoder.layers.17.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 460 |
+
"vpm.encoder.layers.17.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 461 |
+
"vpm.encoder.layers.17.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 462 |
+
"vpm.encoder.layers.17.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 463 |
+
"vpm.encoder.layers.17.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 464 |
+
"vpm.encoder.layers.17.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 465 |
+
"vpm.encoder.layers.17.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 466 |
+
"vpm.encoder.layers.17.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 467 |
+
"vpm.encoder.layers.17.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 468 |
+
"vpm.encoder.layers.17.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 469 |
+
"vpm.encoder.layers.17.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 470 |
+
"vpm.encoder.layers.17.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 471 |
+
"vpm.encoder.layers.17.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 472 |
+
"vpm.encoder.layers.17.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 473 |
+
"vpm.encoder.layers.18.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 474 |
+
"vpm.encoder.layers.18.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 475 |
+
"vpm.encoder.layers.18.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 476 |
+
"vpm.encoder.layers.18.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 477 |
+
"vpm.encoder.layers.18.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 478 |
+
"vpm.encoder.layers.18.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 479 |
+
"vpm.encoder.layers.18.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 480 |
+
"vpm.encoder.layers.18.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 481 |
+
"vpm.encoder.layers.18.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 482 |
+
"vpm.encoder.layers.18.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 483 |
+
"vpm.encoder.layers.18.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 484 |
+
"vpm.encoder.layers.18.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 485 |
+
"vpm.encoder.layers.18.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 486 |
+
"vpm.encoder.layers.18.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 487 |
+
"vpm.encoder.layers.18.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 488 |
+
"vpm.encoder.layers.18.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 489 |
+
"vpm.encoder.layers.19.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 490 |
+
"vpm.encoder.layers.19.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 491 |
+
"vpm.encoder.layers.19.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 492 |
+
"vpm.encoder.layers.19.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 493 |
+
"vpm.encoder.layers.19.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 494 |
+
"vpm.encoder.layers.19.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 495 |
+
"vpm.encoder.layers.19.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 496 |
+
"vpm.encoder.layers.19.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 497 |
+
"vpm.encoder.layers.19.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 498 |
+
"vpm.encoder.layers.19.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 499 |
+
"vpm.encoder.layers.19.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 500 |
+
"vpm.encoder.layers.19.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 501 |
+
"vpm.encoder.layers.19.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 502 |
+
"vpm.encoder.layers.19.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 503 |
+
"vpm.encoder.layers.19.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 504 |
+
"vpm.encoder.layers.19.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 505 |
+
"vpm.encoder.layers.2.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 506 |
+
"vpm.encoder.layers.2.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 507 |
+
"vpm.encoder.layers.2.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 508 |
+
"vpm.encoder.layers.2.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 509 |
+
"vpm.encoder.layers.2.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 510 |
+
"vpm.encoder.layers.2.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 511 |
+
"vpm.encoder.layers.2.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 512 |
+
"vpm.encoder.layers.2.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 513 |
+
"vpm.encoder.layers.2.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 514 |
+
"vpm.encoder.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 515 |
+
"vpm.encoder.layers.2.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 516 |
+
"vpm.encoder.layers.2.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 517 |
+
"vpm.encoder.layers.2.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 518 |
+
"vpm.encoder.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 519 |
+
"vpm.encoder.layers.2.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 520 |
+
"vpm.encoder.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 521 |
+
"vpm.encoder.layers.20.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 522 |
+
"vpm.encoder.layers.20.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 523 |
+
"vpm.encoder.layers.20.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 524 |
+
"vpm.encoder.layers.20.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 525 |
+
"vpm.encoder.layers.20.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 526 |
+
"vpm.encoder.layers.20.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 527 |
+
"vpm.encoder.layers.20.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 528 |
+
"vpm.encoder.layers.20.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 529 |
+
"vpm.encoder.layers.20.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 530 |
+
"vpm.encoder.layers.20.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 531 |
+
"vpm.encoder.layers.20.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 532 |
+
"vpm.encoder.layers.20.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 533 |
+
"vpm.encoder.layers.20.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 534 |
+
"vpm.encoder.layers.20.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 535 |
+
"vpm.encoder.layers.20.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 536 |
+
"vpm.encoder.layers.20.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 537 |
+
"vpm.encoder.layers.21.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 538 |
+
"vpm.encoder.layers.21.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 539 |
+
"vpm.encoder.layers.21.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 540 |
+
"vpm.encoder.layers.21.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 541 |
+
"vpm.encoder.layers.21.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 542 |
+
"vpm.encoder.layers.21.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 543 |
+
"vpm.encoder.layers.21.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 544 |
+
"vpm.encoder.layers.21.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 545 |
+
"vpm.encoder.layers.21.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 546 |
+
"vpm.encoder.layers.21.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 547 |
+
"vpm.encoder.layers.21.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 548 |
+
"vpm.encoder.layers.21.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 549 |
+
"vpm.encoder.layers.21.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 550 |
+
"vpm.encoder.layers.21.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 551 |
+
"vpm.encoder.layers.21.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 552 |
+
"vpm.encoder.layers.21.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 553 |
+
"vpm.encoder.layers.22.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 554 |
+
"vpm.encoder.layers.22.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 555 |
+
"vpm.encoder.layers.22.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 556 |
+
"vpm.encoder.layers.22.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 557 |
+
"vpm.encoder.layers.22.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 558 |
+
"vpm.encoder.layers.22.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 559 |
+
"vpm.encoder.layers.22.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 560 |
+
"vpm.encoder.layers.22.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 561 |
+
"vpm.encoder.layers.22.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 562 |
+
"vpm.encoder.layers.22.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 563 |
+
"vpm.encoder.layers.22.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 564 |
+
"vpm.encoder.layers.22.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 565 |
+
"vpm.encoder.layers.22.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 566 |
+
"vpm.encoder.layers.22.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 567 |
+
"vpm.encoder.layers.22.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 568 |
+
"vpm.encoder.layers.22.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 569 |
+
"vpm.encoder.layers.23.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 570 |
+
"vpm.encoder.layers.23.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 571 |
+
"vpm.encoder.layers.23.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 572 |
+
"vpm.encoder.layers.23.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 573 |
+
"vpm.encoder.layers.23.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 574 |
+
"vpm.encoder.layers.23.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 575 |
+
"vpm.encoder.layers.23.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 576 |
+
"vpm.encoder.layers.23.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 577 |
+
"vpm.encoder.layers.23.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 578 |
+
"vpm.encoder.layers.23.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 579 |
+
"vpm.encoder.layers.23.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 580 |
+
"vpm.encoder.layers.23.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 581 |
+
"vpm.encoder.layers.23.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 582 |
+
"vpm.encoder.layers.23.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 583 |
+
"vpm.encoder.layers.23.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 584 |
+
"vpm.encoder.layers.23.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 585 |
+
"vpm.encoder.layers.24.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 586 |
+
"vpm.encoder.layers.24.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 587 |
+
"vpm.encoder.layers.24.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 588 |
+
"vpm.encoder.layers.24.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 589 |
+
"vpm.encoder.layers.24.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 590 |
+
"vpm.encoder.layers.24.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 591 |
+
"vpm.encoder.layers.24.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 592 |
+
"vpm.encoder.layers.24.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 593 |
+
"vpm.encoder.layers.24.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 594 |
+
"vpm.encoder.layers.24.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 595 |
+
"vpm.encoder.layers.24.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 596 |
+
"vpm.encoder.layers.24.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 597 |
+
"vpm.encoder.layers.24.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 598 |
+
"vpm.encoder.layers.24.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 599 |
+
"vpm.encoder.layers.24.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 600 |
+
"vpm.encoder.layers.24.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 601 |
+
"vpm.encoder.layers.25.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 602 |
+
"vpm.encoder.layers.25.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 603 |
+
"vpm.encoder.layers.25.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 604 |
+
"vpm.encoder.layers.25.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 605 |
+
"vpm.encoder.layers.25.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 606 |
+
"vpm.encoder.layers.25.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 607 |
+
"vpm.encoder.layers.25.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 608 |
+
"vpm.encoder.layers.25.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 609 |
+
"vpm.encoder.layers.25.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 610 |
+
"vpm.encoder.layers.25.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 611 |
+
"vpm.encoder.layers.25.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 612 |
+
"vpm.encoder.layers.25.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 613 |
+
"vpm.encoder.layers.25.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 614 |
+
"vpm.encoder.layers.25.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 615 |
+
"vpm.encoder.layers.25.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 616 |
+
"vpm.encoder.layers.25.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 617 |
+
"vpm.encoder.layers.26.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 618 |
+
"vpm.encoder.layers.26.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 619 |
+
"vpm.encoder.layers.26.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 620 |
+
"vpm.encoder.layers.26.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 621 |
+
"vpm.encoder.layers.26.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 622 |
+
"vpm.encoder.layers.26.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 623 |
+
"vpm.encoder.layers.26.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 624 |
+
"vpm.encoder.layers.26.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 625 |
+
"vpm.encoder.layers.26.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 626 |
+
"vpm.encoder.layers.26.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 627 |
+
"vpm.encoder.layers.26.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 628 |
+
"vpm.encoder.layers.26.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 629 |
+
"vpm.encoder.layers.26.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 630 |
+
"vpm.encoder.layers.26.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 631 |
+
"vpm.encoder.layers.26.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 632 |
+
"vpm.encoder.layers.26.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 633 |
+
"vpm.encoder.layers.3.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 634 |
+
"vpm.encoder.layers.3.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 635 |
+
"vpm.encoder.layers.3.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 636 |
+
"vpm.encoder.layers.3.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 637 |
+
"vpm.encoder.layers.3.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 638 |
+
"vpm.encoder.layers.3.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 639 |
+
"vpm.encoder.layers.3.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 640 |
+
"vpm.encoder.layers.3.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 641 |
+
"vpm.encoder.layers.3.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 642 |
+
"vpm.encoder.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 643 |
+
"vpm.encoder.layers.3.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 644 |
+
"vpm.encoder.layers.3.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 645 |
+
"vpm.encoder.layers.3.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 646 |
+
"vpm.encoder.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 647 |
+
"vpm.encoder.layers.3.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 648 |
+
"vpm.encoder.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 649 |
+
"vpm.encoder.layers.4.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 650 |
+
"vpm.encoder.layers.4.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 651 |
+
"vpm.encoder.layers.4.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 652 |
+
"vpm.encoder.layers.4.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 653 |
+
"vpm.encoder.layers.4.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 654 |
+
"vpm.encoder.layers.4.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 655 |
+
"vpm.encoder.layers.4.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 656 |
+
"vpm.encoder.layers.4.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 657 |
+
"vpm.encoder.layers.4.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 658 |
+
"vpm.encoder.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 659 |
+
"vpm.encoder.layers.4.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 660 |
+
"vpm.encoder.layers.4.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 661 |
+
"vpm.encoder.layers.4.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 662 |
+
"vpm.encoder.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 663 |
+
"vpm.encoder.layers.4.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 664 |
+
"vpm.encoder.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 665 |
+
"vpm.encoder.layers.5.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 666 |
+
"vpm.encoder.layers.5.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 667 |
+
"vpm.encoder.layers.5.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 668 |
+
"vpm.encoder.layers.5.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 669 |
+
"vpm.encoder.layers.5.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 670 |
+
"vpm.encoder.layers.5.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 671 |
+
"vpm.encoder.layers.5.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 672 |
+
"vpm.encoder.layers.5.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 673 |
+
"vpm.encoder.layers.5.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 674 |
+
"vpm.encoder.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 675 |
+
"vpm.encoder.layers.5.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 676 |
+
"vpm.encoder.layers.5.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 677 |
+
"vpm.encoder.layers.5.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 678 |
+
"vpm.encoder.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 679 |
+
"vpm.encoder.layers.5.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 680 |
+
"vpm.encoder.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 681 |
+
"vpm.encoder.layers.6.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 682 |
+
"vpm.encoder.layers.6.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 683 |
+
"vpm.encoder.layers.6.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 684 |
+
"vpm.encoder.layers.6.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 685 |
+
"vpm.encoder.layers.6.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 686 |
+
"vpm.encoder.layers.6.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 687 |
+
"vpm.encoder.layers.6.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 688 |
+
"vpm.encoder.layers.6.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 689 |
+
"vpm.encoder.layers.6.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 690 |
+
"vpm.encoder.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 691 |
+
"vpm.encoder.layers.6.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 692 |
+
"vpm.encoder.layers.6.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 693 |
+
"vpm.encoder.layers.6.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 694 |
+
"vpm.encoder.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 695 |
+
"vpm.encoder.layers.6.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 696 |
+
"vpm.encoder.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 697 |
+
"vpm.encoder.layers.7.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 698 |
+
"vpm.encoder.layers.7.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 699 |
+
"vpm.encoder.layers.7.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 700 |
+
"vpm.encoder.layers.7.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 701 |
+
"vpm.encoder.layers.7.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 702 |
+
"vpm.encoder.layers.7.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 703 |
+
"vpm.encoder.layers.7.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 704 |
+
"vpm.encoder.layers.7.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 705 |
+
"vpm.encoder.layers.7.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 706 |
+
"vpm.encoder.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 707 |
+
"vpm.encoder.layers.7.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 708 |
+
"vpm.encoder.layers.7.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 709 |
+
"vpm.encoder.layers.7.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 710 |
+
"vpm.encoder.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 711 |
+
"vpm.encoder.layers.7.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 712 |
+
"vpm.encoder.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 713 |
+
"vpm.encoder.layers.8.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 714 |
+
"vpm.encoder.layers.8.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 715 |
+
"vpm.encoder.layers.8.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 716 |
+
"vpm.encoder.layers.8.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 717 |
+
"vpm.encoder.layers.8.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 718 |
+
"vpm.encoder.layers.8.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 719 |
+
"vpm.encoder.layers.8.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 720 |
+
"vpm.encoder.layers.8.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 721 |
+
"vpm.encoder.layers.8.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 722 |
+
"vpm.encoder.layers.8.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 723 |
+
"vpm.encoder.layers.8.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 724 |
+
"vpm.encoder.layers.8.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 725 |
+
"vpm.encoder.layers.8.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 726 |
+
"vpm.encoder.layers.8.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 727 |
+
"vpm.encoder.layers.8.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 728 |
+
"vpm.encoder.layers.8.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 729 |
+
"vpm.encoder.layers.9.layer_norm1.bias": "model-00007-of-00007.safetensors",
|
| 730 |
+
"vpm.encoder.layers.9.layer_norm1.weight": "model-00007-of-00007.safetensors",
|
| 731 |
+
"vpm.encoder.layers.9.layer_norm2.bias": "model-00007-of-00007.safetensors",
|
| 732 |
+
"vpm.encoder.layers.9.layer_norm2.weight": "model-00007-of-00007.safetensors",
|
| 733 |
+
"vpm.encoder.layers.9.mlp.fc1.bias": "model-00007-of-00007.safetensors",
|
| 734 |
+
"vpm.encoder.layers.9.mlp.fc1.weight": "model-00007-of-00007.safetensors",
|
| 735 |
+
"vpm.encoder.layers.9.mlp.fc2.bias": "model-00007-of-00007.safetensors",
|
| 736 |
+
"vpm.encoder.layers.9.mlp.fc2.weight": "model-00007-of-00007.safetensors",
|
| 737 |
+
"vpm.encoder.layers.9.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
| 738 |
+
"vpm.encoder.layers.9.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
| 739 |
+
"vpm.encoder.layers.9.self_attn.out_proj.bias": "model-00007-of-00007.safetensors",
|
| 740 |
+
"vpm.encoder.layers.9.self_attn.out_proj.weight": "model-00007-of-00007.safetensors",
|
| 741 |
+
"vpm.encoder.layers.9.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
| 742 |
+
"vpm.encoder.layers.9.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
| 743 |
+
"vpm.encoder.layers.9.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
| 744 |
+
"vpm.encoder.layers.9.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
| 745 |
+
"vpm.post_layernorm.bias": "model-00007-of-00007.safetensors",
|
| 746 |
+
"vpm.post_layernorm.weight": "model-00007-of-00007.safetensors"
|
| 747 |
+
}
|
| 748 |
+
}
|
modeling_minicpmv.py
ADDED
|
@@ -0,0 +1,702 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from typing import List, Optional
|
| 3 |
+
import json
|
| 4 |
+
import torch
|
| 5 |
+
import torchvision
|
| 6 |
+
from threading import Thread
|
| 7 |
+
from copy import deepcopy
|
| 8 |
+
from PIL import Image
|
| 9 |
+
from torchvision import transforms
|
| 10 |
+
from transformers import LlamaTokenizer, LlamaPreTrainedModel, LlamaForCausalLM, AutoModel, PreTrainedTokenizerFast, TextIteratorStreamer
|
| 11 |
+
from transformers.models.idefics2.modeling_idefics2 import Idefics2VisionTransformer
|
| 12 |
+
|
| 13 |
+
from .configuration_minicpm import MiniCPMVConfig
|
| 14 |
+
from .resampler import Resampler
|
| 15 |
+
|
| 16 |
+
IMAGENET_INCEPTION_MEAN = (0.5, 0.5, 0.5) # timm.data.IMAGENET_INCEPTION_MEAN
|
| 17 |
+
IMAGENET_INCEPTION_STD = (0.5, 0.5, 0.5) # timm.data.IMAGENET_INCEPTION_STD
|
| 18 |
+
|
| 19 |
+
class MiniCPMVPreTrainedModel(LlamaPreTrainedModel):
|
| 20 |
+
config_class = MiniCPMVConfig
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
class MiniCPMV(MiniCPMVPreTrainedModel):
|
| 24 |
+
def __init__(self, config):
|
| 25 |
+
super().__init__(config)
|
| 26 |
+
|
| 27 |
+
self.llm = LlamaForCausalLM(config)
|
| 28 |
+
self.vpm = self.init_vision_module()
|
| 29 |
+
self.vision_dim = self.vpm.embed_dim
|
| 30 |
+
self.embed_dim = self.llm.config.hidden_size
|
| 31 |
+
self.resampler = self.init_resampler(self.embed_dim, self.vision_dim)
|
| 32 |
+
self.transform = self.init_transform()
|
| 33 |
+
|
| 34 |
+
def init_vision_module(self):
|
| 35 |
+
# same as HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit
|
| 36 |
+
model = Idefics2VisionTransformer(self.config.vision_config)
|
| 37 |
+
if self.config.drop_vision_last_layer:
|
| 38 |
+
model.encoder.layers = model.encoder.layers[:-1]
|
| 39 |
+
|
| 40 |
+
setattr(model, 'embed_dim', model.embeddings.embed_dim)
|
| 41 |
+
setattr(model, 'patch_size', model.embeddings.patch_size)
|
| 42 |
+
|
| 43 |
+
return model
|
| 44 |
+
|
| 45 |
+
def init_resampler(self, embed_dim, vision_dim):
|
| 46 |
+
return Resampler(
|
| 47 |
+
num_queries=self.config.query_num,
|
| 48 |
+
embed_dim=embed_dim,
|
| 49 |
+
num_heads=embed_dim // 128,
|
| 50 |
+
kv_dim=vision_dim,
|
| 51 |
+
adaptive=True
|
| 52 |
+
)
|
| 53 |
+
|
| 54 |
+
def init_transform(self):
|
| 55 |
+
return transforms.Compose(
|
| 56 |
+
[
|
| 57 |
+
transforms.ToTensor(),
|
| 58 |
+
transforms.Normalize(
|
| 59 |
+
mean=IMAGENET_INCEPTION_MEAN, std=IMAGENET_INCEPTION_STD
|
| 60 |
+
),
|
| 61 |
+
]
|
| 62 |
+
)
|
| 63 |
+
|
| 64 |
+
def get_input_embeddings(self):
|
| 65 |
+
return self.llm.get_input_embeddings()
|
| 66 |
+
|
| 67 |
+
def set_input_embeddings(self, value):
|
| 68 |
+
self.llm.embed_tokens = value
|
| 69 |
+
|
| 70 |
+
def get_vllm_embedding(self, data):
|
| 71 |
+
if 'vision_hidden_states' not in data:
|
| 72 |
+
dtype = self.vpm.embeddings.position_embedding.weight.dtype
|
| 73 |
+
device = self.vpm.embeddings.position_embedding.weight.device
|
| 74 |
+
tgt_sizes = data['tgt_sizes']
|
| 75 |
+
pixel_values_list = data['pixel_values']
|
| 76 |
+
vision_hidden_states = []
|
| 77 |
+
all_pixel_values = []
|
| 78 |
+
img_cnt = []
|
| 79 |
+
for pixel_values in pixel_values_list:
|
| 80 |
+
img_cnt.append(len(pixel_values))
|
| 81 |
+
all_pixel_values.extend([i.flatten(end_dim=1).permute(1, 0) for i in pixel_values])
|
| 82 |
+
|
| 83 |
+
# exist image
|
| 84 |
+
if all_pixel_values:
|
| 85 |
+
tgt_sizes = torch.vstack(tgt_sizes).type(torch.int32)
|
| 86 |
+
|
| 87 |
+
if self.config.batch_vision_input:
|
| 88 |
+
max_patches = torch.max(tgt_sizes[:, 0] * tgt_sizes[:, 1])
|
| 89 |
+
|
| 90 |
+
all_pixel_values = torch.nn.utils.rnn.pad_sequence(all_pixel_values, batch_first=True,
|
| 91 |
+
padding_value=0.0)
|
| 92 |
+
B, L, _ = all_pixel_values.shape
|
| 93 |
+
all_pixel_values = all_pixel_values.permute(0, 2, 1).reshape(B, 3, -1, L)
|
| 94 |
+
|
| 95 |
+
patch_attn_mask = torch.zeros((B, 1, max_patches), dtype=torch.bool, device=device)
|
| 96 |
+
for i in range(B):
|
| 97 |
+
patch_attn_mask[i, :tgt_sizes[i][0] * tgt_sizes[i][1]] = True
|
| 98 |
+
|
| 99 |
+
vision_embedding = self.vpm(all_pixel_values.type(dtype), patch_attention_mask=patch_attn_mask).last_hidden_state
|
| 100 |
+
vision_embedding = self.resampler(vision_embedding, tgt_sizes)
|
| 101 |
+
else:
|
| 102 |
+
# get vision_embedding foreach
|
| 103 |
+
vision_embedding = []
|
| 104 |
+
for single_tgt_size, single_pixel_values in zip(tgt_sizes, all_pixel_values):
|
| 105 |
+
single_pixel_values = single_pixel_values.unsqueeze(0)
|
| 106 |
+
B, L, _ = single_pixel_values.shape
|
| 107 |
+
single_pixel_values = single_pixel_values.permute(0, 2, 1).reshape(B, 3, -1, L)
|
| 108 |
+
single_vision_embedding = self.vpm(single_pixel_values.type(dtype)).last_hidden_state
|
| 109 |
+
single_vision_embedding = self.resampler(single_vision_embedding, single_tgt_size.unsqueeze(0))
|
| 110 |
+
vision_embedding.append(single_vision_embedding)
|
| 111 |
+
vision_embedding = torch.vstack(vision_embedding)
|
| 112 |
+
|
| 113 |
+
start = 0
|
| 114 |
+
for pixel_values in pixel_values_list:
|
| 115 |
+
img_cnt = len(pixel_values)
|
| 116 |
+
if img_cnt > 0:
|
| 117 |
+
vision_hidden_states.append(vision_embedding[start: start + img_cnt])
|
| 118 |
+
start += img_cnt
|
| 119 |
+
else:
|
| 120 |
+
vision_hidden_states.append([])
|
| 121 |
+
else: # no image
|
| 122 |
+
if self.training:
|
| 123 |
+
dummy_image = torch.zeros(
|
| 124 |
+
(1, 3, 224, 224),
|
| 125 |
+
device=device, dtype=dtype
|
| 126 |
+
)
|
| 127 |
+
tgt_sizes = torch.Tensor([[(224 // self.config.patch_size), math.ceil(224 / self.config.patch_size)]]).type(torch.int32)
|
| 128 |
+
dummy_feature = self.resampler(self.vpm(dummy_image).last_hidden_state, tgt_sizes)
|
| 129 |
+
else:
|
| 130 |
+
dummy_feature = []
|
| 131 |
+
for _ in range(len(pixel_values_list)):
|
| 132 |
+
vision_hidden_states.append(dummy_feature)
|
| 133 |
+
|
| 134 |
+
else:
|
| 135 |
+
vision_hidden_states = data['vision_hidden_states']
|
| 136 |
+
|
| 137 |
+
if hasattr(self.llm.config, 'scale_emb'):
|
| 138 |
+
vllm_embedding = self.llm.model.embed_tokens(data['input_ids']) * self.llm.config.scale_emb
|
| 139 |
+
else:
|
| 140 |
+
vllm_embedding = self.llm.model.embed_tokens(data['input_ids'])
|
| 141 |
+
|
| 142 |
+
vision_hidden_states = [i.type(vllm_embedding.dtype) if isinstance(
|
| 143 |
+
i, torch.Tensor) else i for i in vision_hidden_states]
|
| 144 |
+
|
| 145 |
+
bs = len(data['input_ids'])
|
| 146 |
+
for i in range(bs):
|
| 147 |
+
cur_vs_hs = vision_hidden_states[i]
|
| 148 |
+
if len(cur_vs_hs) > 0:
|
| 149 |
+
cur_vllm_emb = vllm_embedding[i]
|
| 150 |
+
cur_image_bound = data['image_bound'][i]
|
| 151 |
+
if len(cur_image_bound) > 0:
|
| 152 |
+
image_indices = torch.stack(
|
| 153 |
+
[torch.arange(r[0], r[1], dtype=torch.long) for r in cur_image_bound]
|
| 154 |
+
).to(vllm_embedding.device)
|
| 155 |
+
|
| 156 |
+
cur_vllm_emb.scatter_(0, image_indices.view(-1, 1).repeat(1, cur_vllm_emb.shape[-1]),
|
| 157 |
+
cur_vs_hs.view(-1, cur_vs_hs.shape[-1]))
|
| 158 |
+
elif self.training:
|
| 159 |
+
cur_vllm_emb += cur_vs_hs[0].mean() * 0
|
| 160 |
+
|
| 161 |
+
return vllm_embedding, vision_hidden_states
|
| 162 |
+
|
| 163 |
+
def forward(self, data, **kwargs):
|
| 164 |
+
vllm_embedding, vision_hidden_states = self.get_vllm_embedding(data)
|
| 165 |
+
position_ids = data["position_ids"]
|
| 166 |
+
if position_ids.dtype != torch.int64:
|
| 167 |
+
position_ids = position_ids.long()
|
| 168 |
+
|
| 169 |
+
return self.llm(
|
| 170 |
+
input_ids=None,
|
| 171 |
+
position_ids=position_ids,
|
| 172 |
+
inputs_embeds=vllm_embedding,
|
| 173 |
+
**kwargs
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
def _convert_to_tensors(
|
| 177 |
+
self, tokenizer, input_ids, max_inp_length: Optional[int] = None
|
| 178 |
+
):
|
| 179 |
+
if max_inp_length is not None:
|
| 180 |
+
input_ids = input_ids[:max_inp_length]
|
| 181 |
+
input_ids = torch.tensor(input_ids, dtype=torch.int32)
|
| 182 |
+
|
| 183 |
+
image_start_tokens = torch.where(input_ids == tokenizer.im_start_id)[0]
|
| 184 |
+
# 跳过 im_start
|
| 185 |
+
image_start_tokens += 1
|
| 186 |
+
image_end_tokens = torch.where(input_ids == tokenizer.im_end_id)[0]
|
| 187 |
+
valid_image_nums = max(len(image_start_tokens), len(image_end_tokens))
|
| 188 |
+
image_bound = torch.hstack(
|
| 189 |
+
[
|
| 190 |
+
image_start_tokens[:valid_image_nums].unsqueeze(-1),
|
| 191 |
+
image_end_tokens[:valid_image_nums].unsqueeze(-1),
|
| 192 |
+
]
|
| 193 |
+
)
|
| 194 |
+
|
| 195 |
+
model_input = {}
|
| 196 |
+
model_input["input_ids"] = input_ids.unsqueeze(0).to(self.device)
|
| 197 |
+
model_input["image_bound"] = image_bound
|
| 198 |
+
|
| 199 |
+
return model_input
|
| 200 |
+
|
| 201 |
+
def _process_list(
|
| 202 |
+
self, tokenizer, input_id_list, max_inp_length: Optional[int] = None
|
| 203 |
+
):
|
| 204 |
+
pad_keys = ["input_ids"]
|
| 205 |
+
input_tensors = []
|
| 206 |
+
for input_ids in input_id_list:
|
| 207 |
+
input_tensors.append(
|
| 208 |
+
self._convert_to_tensors(tokenizer, input_ids, max_inp_length)
|
| 209 |
+
)
|
| 210 |
+
padded = {}
|
| 211 |
+
for key in pad_keys:
|
| 212 |
+
padded[key] = pad(input_tensors, key, padding_side="left").to(self.device)
|
| 213 |
+
padded["image_bound"] = [i["image_bound"] for i in input_tensors]
|
| 214 |
+
return padded
|
| 215 |
+
|
| 216 |
+
def _decode(self, inputs_embeds, tokenizer, **kwargs):
|
| 217 |
+
terminators = [
|
| 218 |
+
tokenizer.eos_token_id,
|
| 219 |
+
tokenizer.convert_tokens_to_ids("<|eot_id|>")
|
| 220 |
+
]
|
| 221 |
+
output = self.llm.generate(
|
| 222 |
+
inputs_embeds=inputs_embeds,
|
| 223 |
+
pad_token_id=0,
|
| 224 |
+
eos_token_id=terminators,
|
| 225 |
+
**kwargs
|
| 226 |
+
)
|
| 227 |
+
return self._decode_text(output, tokenizer)
|
| 228 |
+
|
| 229 |
+
def _decode_stream(self, inputs_embeds, tokenizer, **kwargs):
|
| 230 |
+
terminators = [
|
| 231 |
+
tokenizer.eos_token_id,
|
| 232 |
+
tokenizer.convert_tokens_to_ids("<|eot_id|>")
|
| 233 |
+
]
|
| 234 |
+
streamer = TextIteratorStreamer(tokenizer=tokenizer)
|
| 235 |
+
generation_kwargs = {
|
| 236 |
+
'inputs_embeds': inputs_embeds,
|
| 237 |
+
'pad_token_id': 0,
|
| 238 |
+
'eos_token_id': terminators,
|
| 239 |
+
'streamer': streamer
|
| 240 |
+
}
|
| 241 |
+
generation_kwargs.update(kwargs)
|
| 242 |
+
|
| 243 |
+
thread = Thread(target=self.llm.generate, kwargs=generation_kwargs)
|
| 244 |
+
thread.start()
|
| 245 |
+
|
| 246 |
+
return streamer
|
| 247 |
+
|
| 248 |
+
def _decode_text(self, result_ids, tokenizer):
|
| 249 |
+
result_text = []
|
| 250 |
+
for result in result_ids:
|
| 251 |
+
result = result[result != 0]
|
| 252 |
+
if result[0] == tokenizer.bos_id:
|
| 253 |
+
result = result[1:]
|
| 254 |
+
if result[-1] == tokenizer.eos_id or result[-1] == tokenizer.eot_id:
|
| 255 |
+
result = result[:-1]
|
| 256 |
+
result_text.append(tokenizer.decode(result).strip())
|
| 257 |
+
return result_text
|
| 258 |
+
|
| 259 |
+
def slice_image(self, image):
|
| 260 |
+
return slice_image(
|
| 261 |
+
image,
|
| 262 |
+
self.config.slice_config.max_slice_nums,
|
| 263 |
+
self.config.slice_config.scale_resolution,
|
| 264 |
+
self.config.slice_config.patch_size,
|
| 265 |
+
)
|
| 266 |
+
|
| 267 |
+
def get_slice_image_placeholder(self, image, tokenizer):
|
| 268 |
+
image_placeholder = (
|
| 269 |
+
tokenizer.im_start
|
| 270 |
+
+ tokenizer.unk_token * self.config.query_num
|
| 271 |
+
+ tokenizer.im_end
|
| 272 |
+
)
|
| 273 |
+
|
| 274 |
+
slice_images = []
|
| 275 |
+
|
| 276 |
+
source_image, patches, best_grid = slice_image(
|
| 277 |
+
image,
|
| 278 |
+
self.config.slice_config.max_slice_nums,
|
| 279 |
+
self.config.slice_config.scale_resolution,
|
| 280 |
+
self.config.slice_config.patch_size,
|
| 281 |
+
)
|
| 282 |
+
|
| 283 |
+
slice_images.append(source_image)
|
| 284 |
+
final_placeholder = image_placeholder
|
| 285 |
+
|
| 286 |
+
if len(patches) > 0:
|
| 287 |
+
for i in range(len(patches)):
|
| 288 |
+
for j in range(len(patches[0])):
|
| 289 |
+
slice_images.append(patches[i][j])
|
| 290 |
+
|
| 291 |
+
final_placeholder += get_grid_placeholder(
|
| 292 |
+
tokenizer, best_grid, self.config.query_num
|
| 293 |
+
)
|
| 294 |
+
|
| 295 |
+
return slice_images, final_placeholder
|
| 296 |
+
|
| 297 |
+
def reshape_by_patch(self, image_tensor):
|
| 298 |
+
"""
|
| 299 |
+
:param image_tensor: shape [3, H, W]
|
| 300 |
+
:param patch_size:
|
| 301 |
+
:return: [3, patch_size, HW/patch_size]
|
| 302 |
+
"""
|
| 303 |
+
patch_size = self.config.patch_size
|
| 304 |
+
patches = torch.nn.functional.unfold(
|
| 305 |
+
image_tensor,
|
| 306 |
+
(patch_size, patch_size),
|
| 307 |
+
stride=(patch_size, patch_size)
|
| 308 |
+
)
|
| 309 |
+
|
| 310 |
+
patches = patches.reshape(image_tensor.size(0), patch_size, patch_size, -1)
|
| 311 |
+
patches = patches.permute(0, 1, 3, 2).reshape(image_tensor.size(0), patch_size, -1)
|
| 312 |
+
return patches
|
| 313 |
+
|
| 314 |
+
def generate(
|
| 315 |
+
self,
|
| 316 |
+
input_id_list=None,
|
| 317 |
+
img_list=None,
|
| 318 |
+
tgt_sizes=None,
|
| 319 |
+
tokenizer=None,
|
| 320 |
+
max_inp_length: Optional[int] = None,
|
| 321 |
+
vision_hidden_states=None,
|
| 322 |
+
return_vision_hidden_states=False,
|
| 323 |
+
stream=False,
|
| 324 |
+
**kwargs
|
| 325 |
+
):
|
| 326 |
+
|
| 327 |
+
assert input_id_list is not None
|
| 328 |
+
bs = len(input_id_list)
|
| 329 |
+
if img_list == None:
|
| 330 |
+
img_list = [[] for i in range(bs)]
|
| 331 |
+
assert bs == len(img_list)
|
| 332 |
+
|
| 333 |
+
model_inputs = self._process_list(tokenizer, input_id_list, max_inp_length)
|
| 334 |
+
|
| 335 |
+
if vision_hidden_states is None:
|
| 336 |
+
pixel_values = []
|
| 337 |
+
for i in range(bs):
|
| 338 |
+
img_inps = []
|
| 339 |
+
for img in img_list[i]:
|
| 340 |
+
img_inps.append(img.to(self.device))
|
| 341 |
+
if img_inps:
|
| 342 |
+
pixel_values.append(img_inps)
|
| 343 |
+
else:
|
| 344 |
+
pixel_values.append([])
|
| 345 |
+
model_inputs["pixel_values"] = pixel_values
|
| 346 |
+
model_inputs['tgt_sizes'] = tgt_sizes
|
| 347 |
+
else:
|
| 348 |
+
model_inputs["vision_hidden_states"] = vision_hidden_states
|
| 349 |
+
|
| 350 |
+
with torch.inference_mode():
|
| 351 |
+
(
|
| 352 |
+
model_inputs["inputs_embeds"],
|
| 353 |
+
vision_hidden_states,
|
| 354 |
+
) = self.get_vllm_embedding(model_inputs)
|
| 355 |
+
|
| 356 |
+
if stream:
|
| 357 |
+
result = self._decode_stream(model_inputs["inputs_embeds"], tokenizer, **kwargs)
|
| 358 |
+
else:
|
| 359 |
+
result = self._decode(model_inputs["inputs_embeds"], tokenizer, **kwargs)
|
| 360 |
+
|
| 361 |
+
if return_vision_hidden_states:
|
| 362 |
+
return result, vision_hidden_states
|
| 363 |
+
|
| 364 |
+
return result
|
| 365 |
+
|
| 366 |
+
def chat(
|
| 367 |
+
self,
|
| 368 |
+
image,
|
| 369 |
+
msgs,
|
| 370 |
+
tokenizer,
|
| 371 |
+
vision_hidden_states=None,
|
| 372 |
+
max_new_tokens=1024,
|
| 373 |
+
sampling=True,
|
| 374 |
+
max_inp_length=2048,
|
| 375 |
+
system_prompt='',
|
| 376 |
+
stream=False,
|
| 377 |
+
**kwargs
|
| 378 |
+
):
|
| 379 |
+
if isinstance(msgs, str):
|
| 380 |
+
msgs = json.loads(msgs)
|
| 381 |
+
|
| 382 |
+
copy_msgs = deepcopy(msgs)
|
| 383 |
+
assert len(copy_msgs) > 0, 'msgs is empty'
|
| 384 |
+
assert sampling or not stream, 'if use stream mode, make sure sampling=True'
|
| 385 |
+
|
| 386 |
+
if image is not None and isinstance(copy_msgs[0]['content'], str):
|
| 387 |
+
copy_msgs[0]['content'] = [image, copy_msgs[0]['content']]
|
| 388 |
+
|
| 389 |
+
images = []
|
| 390 |
+
tgt_sizes = []
|
| 391 |
+
for i, msg in enumerate(copy_msgs):
|
| 392 |
+
role = msg["role"]
|
| 393 |
+
content = msg["content"]
|
| 394 |
+
assert role in ["user", "assistant"]
|
| 395 |
+
if i == 0:
|
| 396 |
+
assert role == "user", "The role of first msg should be user"
|
| 397 |
+
if isinstance(content, str):
|
| 398 |
+
content = [content]
|
| 399 |
+
|
| 400 |
+
cur_msgs = []
|
| 401 |
+
for c in content:
|
| 402 |
+
if isinstance(c, Image.Image):
|
| 403 |
+
image = c
|
| 404 |
+
if self.config.slice_mode:
|
| 405 |
+
slice_images, image_placeholder = self.get_slice_image_placeholder(
|
| 406 |
+
image, tokenizer
|
| 407 |
+
)
|
| 408 |
+
cur_msgs.append(image_placeholder)
|
| 409 |
+
for slice_image in slice_images:
|
| 410 |
+
slice_image = self.transform(slice_image)
|
| 411 |
+
H, W = slice_image.shape[1:]
|
| 412 |
+
images.append(self.reshape_by_patch(slice_image))
|
| 413 |
+
tgt_sizes.append(torch.Tensor([H // self.config.patch_size, W // self.config.patch_size]).type(torch.int32))
|
| 414 |
+
else:
|
| 415 |
+
images.append(self.transform(image))
|
| 416 |
+
cur_msgs.append(
|
| 417 |
+
tokenizer.im_start
|
| 418 |
+
+ tokenizer.unk_token * self.config.query_num
|
| 419 |
+
+ tokenizer.im_end
|
| 420 |
+
)
|
| 421 |
+
elif isinstance(c, str):
|
| 422 |
+
cur_msgs.append(c)
|
| 423 |
+
|
| 424 |
+
|
| 425 |
+
msg['content'] = '\n'.join(cur_msgs)
|
| 426 |
+
if tgt_sizes:
|
| 427 |
+
tgt_sizes = torch.vstack(tgt_sizes)
|
| 428 |
+
|
| 429 |
+
if system_prompt:
|
| 430 |
+
sys_msg = {'role': 'system', 'content': system_prompt}
|
| 431 |
+
copy_msgs = [sys_msg] + copy_msgs
|
| 432 |
+
|
| 433 |
+
input_ids = tokenizer.apply_chat_template(copy_msgs, tokenize=True, add_generation_prompt=False)
|
| 434 |
+
|
| 435 |
+
if sampling:
|
| 436 |
+
generation_config = {
|
| 437 |
+
"top_p": 0.8,
|
| 438 |
+
"top_k": 100,
|
| 439 |
+
"temperature": 0.7,
|
| 440 |
+
"do_sample": True,
|
| 441 |
+
"repetition_penalty": 1.05
|
| 442 |
+
}
|
| 443 |
+
else:
|
| 444 |
+
generation_config = {
|
| 445 |
+
"num_beams": 3,
|
| 446 |
+
"repetition_penalty": 1.2,
|
| 447 |
+
}
|
| 448 |
+
|
| 449 |
+
generation_config.update(
|
| 450 |
+
(k, kwargs[k]) for k in generation_config.keys() & kwargs.keys()
|
| 451 |
+
)
|
| 452 |
+
|
| 453 |
+
with torch.inference_mode():
|
| 454 |
+
res, vision_hidden_states = self.generate(
|
| 455 |
+
input_id_list=[input_ids],
|
| 456 |
+
max_inp_length=max_inp_length,
|
| 457 |
+
img_list=[images],
|
| 458 |
+
tgt_sizes=[tgt_sizes],
|
| 459 |
+
tokenizer=tokenizer,
|
| 460 |
+
max_new_tokens=max_new_tokens,
|
| 461 |
+
vision_hidden_states=vision_hidden_states,
|
| 462 |
+
return_vision_hidden_states=True,
|
| 463 |
+
stream=stream,
|
| 464 |
+
**generation_config
|
| 465 |
+
)
|
| 466 |
+
|
| 467 |
+
if stream:
|
| 468 |
+
def stream_gen():
|
| 469 |
+
for text in res:
|
| 470 |
+
text = text.replace(tokenizer.eot_token, '').replace(tokenizer.eos_token, '')
|
| 471 |
+
yield text
|
| 472 |
+
return stream_gen()
|
| 473 |
+
|
| 474 |
+
else:
|
| 475 |
+
answer = res[0]
|
| 476 |
+
return answer
|
| 477 |
+
|
| 478 |
+
|
| 479 |
+
class PreTrainedTokenizerFastWrapper(PreTrainedTokenizerFast):
|
| 480 |
+
def __init__(self, **kwargs):
|
| 481 |
+
super().__init__(**kwargs)
|
| 482 |
+
self.eot_token = "<|eot_id|>"
|
| 483 |
+
self.im_start = "<image>"
|
| 484 |
+
self.im_end = "</image>"
|
| 485 |
+
self.ref_start = "<ref>"
|
| 486 |
+
self.ref_end = "</ref>"
|
| 487 |
+
self.box_start = "<box>"
|
| 488 |
+
self.box_end = "</box>"
|
| 489 |
+
self.quad_start = "<quad>"
|
| 490 |
+
self.quad_end = "</quad>"
|
| 491 |
+
self.slice_start = "<slice>"
|
| 492 |
+
self.slice_end = "</slice>"
|
| 493 |
+
|
| 494 |
+
@property
|
| 495 |
+
def eos_id(self):
|
| 496 |
+
return self.eos_token_id
|
| 497 |
+
|
| 498 |
+
@property
|
| 499 |
+
def bos_id(self):
|
| 500 |
+
return self.bos_token_id
|
| 501 |
+
|
| 502 |
+
@property
|
| 503 |
+
def unk_id(self):
|
| 504 |
+
return self.unk_token_id
|
| 505 |
+
|
| 506 |
+
@property
|
| 507 |
+
def eot_id(self):
|
| 508 |
+
return self.convert_tokens_to_ids(self.eot_token)
|
| 509 |
+
|
| 510 |
+
@property
|
| 511 |
+
def im_start_id(self):
|
| 512 |
+
return self.convert_tokens_to_ids(self.im_start)
|
| 513 |
+
|
| 514 |
+
@property
|
| 515 |
+
def im_end_id(self):
|
| 516 |
+
return self.convert_tokens_to_ids(self.im_end)
|
| 517 |
+
|
| 518 |
+
@staticmethod
|
| 519 |
+
def escape(text: str) -> str:
|
| 520 |
+
return text
|
| 521 |
+
|
| 522 |
+
@staticmethod
|
| 523 |
+
def unescape(text: str) -> str:
|
| 524 |
+
return text
|
| 525 |
+
|
| 526 |
+
|
| 527 |
+
def pad(orig_items, key, max_length=None, padding_value=0, padding_side="left"):
|
| 528 |
+
items = []
|
| 529 |
+
if isinstance(orig_items[0][key], list):
|
| 530 |
+
assert isinstance(orig_items[0][key][0], torch.Tensor)
|
| 531 |
+
for it in orig_items:
|
| 532 |
+
for tr in it[key]:
|
| 533 |
+
items.append({key: tr})
|
| 534 |
+
else:
|
| 535 |
+
assert isinstance(orig_items[0][key], torch.Tensor)
|
| 536 |
+
items = orig_items
|
| 537 |
+
|
| 538 |
+
batch_size = len(items)
|
| 539 |
+
shape = items[0][key].shape
|
| 540 |
+
dim = len(shape)
|
| 541 |
+
assert dim <= 3
|
| 542 |
+
if max_length is None:
|
| 543 |
+
max_length = 0
|
| 544 |
+
max_length = max(max_length, max(item[key].shape[-1] for item in items))
|
| 545 |
+
min_length = min(item[key].shape[-1] for item in items)
|
| 546 |
+
dtype = items[0][key].dtype
|
| 547 |
+
|
| 548 |
+
if dim == 1:
|
| 549 |
+
return torch.cat([item[key] for item in items], dim=0)
|
| 550 |
+
elif dim == 2:
|
| 551 |
+
if max_length == min_length:
|
| 552 |
+
return torch.cat([item[key] for item in items], dim=0)
|
| 553 |
+
tensor = torch.zeros((batch_size, max_length), dtype=dtype) + padding_value
|
| 554 |
+
else:
|
| 555 |
+
tensor = (
|
| 556 |
+
torch.zeros((batch_size, max_length, shape[-1]), dtype=dtype)
|
| 557 |
+
+ padding_value
|
| 558 |
+
)
|
| 559 |
+
|
| 560 |
+
for i, item in enumerate(items):
|
| 561 |
+
if dim == 2:
|
| 562 |
+
if padding_side == "left":
|
| 563 |
+
tensor[i, -len(item[key][0]) :] = item[key][0].clone()
|
| 564 |
+
else:
|
| 565 |
+
tensor[i, : len(item[key][0])] = item[key][0].clone()
|
| 566 |
+
elif dim == 3:
|
| 567 |
+
if padding_side == "left":
|
| 568 |
+
tensor[i, -len(item[key][0]) :, :] = item[key][0].clone()
|
| 569 |
+
else:
|
| 570 |
+
tensor[i, : len(item[key][0]), :] = item[key][0].clone()
|
| 571 |
+
|
| 572 |
+
return tensor
|
| 573 |
+
|
| 574 |
+
|
| 575 |
+
def slice_image(
|
| 576 |
+
image, max_slice_nums=9, scale_resolution=448, patch_size=14, never_split=False
|
| 577 |
+
):
|
| 578 |
+
original_size = image.size
|
| 579 |
+
original_width, original_height = original_size
|
| 580 |
+
log_ratio = math.log(original_width / original_height)
|
| 581 |
+
ratio = original_width * original_height / (scale_resolution * scale_resolution)
|
| 582 |
+
multiple = min(math.ceil(ratio), max_slice_nums)
|
| 583 |
+
|
| 584 |
+
source_image = None
|
| 585 |
+
best_grid = None
|
| 586 |
+
patches = []
|
| 587 |
+
|
| 588 |
+
if multiple <= 1 or never_split:
|
| 589 |
+
# dont need to slice, upsample
|
| 590 |
+
best_size = find_best_resize(
|
| 591 |
+
original_size, scale_resolution, patch_size, allow_upscale=True
|
| 592 |
+
)
|
| 593 |
+
source_image = image.resize(best_size, Image.Resampling.BICUBIC)
|
| 594 |
+
else:
|
| 595 |
+
candidate_split_grids_nums = []
|
| 596 |
+
for i in [multiple - 1, multiple, multiple + 1]:
|
| 597 |
+
if i == 1 or i > max_slice_nums:
|
| 598 |
+
continue
|
| 599 |
+
candidate_split_grids_nums.append(i)
|
| 600 |
+
|
| 601 |
+
# source image, down-sampling and ensure divided by patch_size
|
| 602 |
+
best_resize = find_best_resize(original_size, scale_resolution, patch_size)
|
| 603 |
+
source_image = image.copy().resize(best_resize, Image.Resampling.BICUBIC)
|
| 604 |
+
candidate_grids = []
|
| 605 |
+
|
| 606 |
+
# find best grid
|
| 607 |
+
for split_grids_nums in candidate_split_grids_nums:
|
| 608 |
+
m = 1
|
| 609 |
+
while m <= split_grids_nums:
|
| 610 |
+
if split_grids_nums % m == 0:
|
| 611 |
+
candidate_grids.append([m, split_grids_nums // m])
|
| 612 |
+
m += 1
|
| 613 |
+
|
| 614 |
+
best_grid = [1, 1]
|
| 615 |
+
min_error = float("inf")
|
| 616 |
+
for grid in candidate_grids:
|
| 617 |
+
error = abs(log_ratio - math.log(grid[0] / grid[1]))
|
| 618 |
+
if error < min_error:
|
| 619 |
+
best_grid = grid
|
| 620 |
+
min_error = error
|
| 621 |
+
|
| 622 |
+
refine_size = get_refine_size(
|
| 623 |
+
original_size, best_grid, scale_resolution, patch_size, allow_upscale=True
|
| 624 |
+
)
|
| 625 |
+
|
| 626 |
+
refine_image = image.resize(refine_size, Image.Resampling.BICUBIC)
|
| 627 |
+
patches = split_to_patches(refine_image, best_grid)
|
| 628 |
+
|
| 629 |
+
return source_image, patches, best_grid
|
| 630 |
+
|
| 631 |
+
|
| 632 |
+
def ensure_divide(length, patch_size):
|
| 633 |
+
return max(round(length / patch_size) * patch_size, patch_size)
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
def find_best_resize(original_size, scale_resolution, patch_size, allow_upscale=False):
|
| 637 |
+
width, height = original_size
|
| 638 |
+
if (width * height > scale_resolution * scale_resolution) or allow_upscale:
|
| 639 |
+
r = width / height
|
| 640 |
+
height = int(scale_resolution / math.sqrt(r))
|
| 641 |
+
width = int(height * r)
|
| 642 |
+
best_width = ensure_divide(width, patch_size)
|
| 643 |
+
best_height = ensure_divide(height, patch_size)
|
| 644 |
+
return (best_width, best_height)
|
| 645 |
+
|
| 646 |
+
|
| 647 |
+
def get_refine_size(
|
| 648 |
+
original_size, grid, scale_resolution, patch_size, allow_upscale=False
|
| 649 |
+
):
|
| 650 |
+
width, height = original_size
|
| 651 |
+
grid_x, grid_y = grid
|
| 652 |
+
|
| 653 |
+
refine_width = ensure_divide(width, grid_x)
|
| 654 |
+
refine_height = ensure_divide(height, grid_y)
|
| 655 |
+
|
| 656 |
+
grid_width = refine_width / grid_x
|
| 657 |
+
grid_height = refine_height / grid_y
|
| 658 |
+
|
| 659 |
+
best_grid_size = find_best_resize(
|
| 660 |
+
(grid_width, grid_height),
|
| 661 |
+
scale_resolution,
|
| 662 |
+
patch_size,
|
| 663 |
+
allow_upscale=allow_upscale,
|
| 664 |
+
)
|
| 665 |
+
|
| 666 |
+
refine_size = (best_grid_size[0] * grid_x, best_grid_size[1] * grid_y)
|
| 667 |
+
|
| 668 |
+
return refine_size
|
| 669 |
+
|
| 670 |
+
|
| 671 |
+
def split_to_patches(image, grid):
|
| 672 |
+
patches = []
|
| 673 |
+
width, height = image.size
|
| 674 |
+
grid_x = int(width / grid[0])
|
| 675 |
+
grid_y = int(height / grid[1])
|
| 676 |
+
|
| 677 |
+
for i in range(0, height, grid_y):
|
| 678 |
+
images = []
|
| 679 |
+
for j in range(0, width, grid_x):
|
| 680 |
+
box = (j, i, j + grid_x, i + grid_y)
|
| 681 |
+
patch = image.crop(box)
|
| 682 |
+
images.append(patch)
|
| 683 |
+
patches.append(images)
|
| 684 |
+
|
| 685 |
+
return patches
|
| 686 |
+
|
| 687 |
+
|
| 688 |
+
def get_grid_placeholder(tokenizer, grid, query_num):
|
| 689 |
+
image_placeholder = (
|
| 690 |
+
tokenizer.im_start + tokenizer.unk_token * query_num + tokenizer.im_end
|
| 691 |
+
)
|
| 692 |
+
|
| 693 |
+
cols = grid[0]
|
| 694 |
+
rows = grid[1]
|
| 695 |
+
slices = []
|
| 696 |
+
for i in range(rows):
|
| 697 |
+
lines = []
|
| 698 |
+
for j in range(cols):
|
| 699 |
+
lines.append(image_placeholder)
|
| 700 |
+
slices.append("".join(lines))
|
| 701 |
+
slice_placeholder = tokenizer.slice_start + "\n".join(slices) + tokenizer.slice_end
|
| 702 |
+
return slice_placeholder
|
resampler.py
ADDED
|
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from functools import partial
|
| 2 |
+
import numpy as np
|
| 3 |
+
|
| 4 |
+
import torch
|
| 5 |
+
from torch import nn
|
| 6 |
+
from torch.nn.init import trunc_normal_
|
| 7 |
+
|
| 8 |
+
def get_2d_sincos_pos_embed(embed_dim, image_size):
|
| 9 |
+
"""
|
| 10 |
+
image_size: image_size or (image_height, image_width)
|
| 11 |
+
return:
|
| 12 |
+
pos_embed: [image_height, image_width, embed_dim]
|
| 13 |
+
"""
|
| 14 |
+
if isinstance(image_size, int):
|
| 15 |
+
grid_h_size, grid_w_size = image_size, image_size
|
| 16 |
+
else:
|
| 17 |
+
grid_h_size, grid_w_size = image_size[0], image_size[1]
|
| 18 |
+
|
| 19 |
+
grid_h = np.arange(grid_h_size, dtype=np.float32)
|
| 20 |
+
grid_w = np.arange(grid_w_size, dtype=np.float32)
|
| 21 |
+
grid = np.meshgrid(grid_w, grid_h) # here w goes first
|
| 22 |
+
grid = np.stack(grid, axis=0)
|
| 23 |
+
|
| 24 |
+
pos_embed = get_2d_sincos_pos_embed_from_grid(embed_dim, grid)
|
| 25 |
+
return pos_embed
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
def get_2d_sincos_pos_embed_from_grid(embed_dim, grid):
|
| 29 |
+
assert embed_dim % 2 == 0
|
| 30 |
+
|
| 31 |
+
# use half of dimensions to encode grid_h
|
| 32 |
+
emb_h = get_1d_sincos_pos_embed_from_grid_new(embed_dim // 2, grid[0]) # (H, W, D/2)
|
| 33 |
+
emb_w = get_1d_sincos_pos_embed_from_grid_new(embed_dim // 2, grid[1]) # (H, W, D/2)
|
| 34 |
+
|
| 35 |
+
emb = np.concatenate([emb_h, emb_w], axis=-1) # (H, W, D)
|
| 36 |
+
return emb
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
def get_1d_sincos_pos_embed_from_grid_new(embed_dim, pos):
|
| 40 |
+
"""
|
| 41 |
+
embed_dim: output dimension for each position
|
| 42 |
+
pos: a list of positions to be encoded: size (H, W)
|
| 43 |
+
out: (H, W, D)
|
| 44 |
+
"""
|
| 45 |
+
assert embed_dim % 2 == 0
|
| 46 |
+
omega = np.arange(embed_dim // 2, dtype=np.float32)
|
| 47 |
+
omega /= embed_dim / 2.
|
| 48 |
+
omega = 1. / 10000 ** omega # (D/2,)
|
| 49 |
+
|
| 50 |
+
out = np.einsum('hw,d->hwd', pos, omega) # (H, W, D/2), outer product
|
| 51 |
+
|
| 52 |
+
emb_sin = np.sin(out) # (H, W, D/2)
|
| 53 |
+
emb_cos = np.cos(out) # (H, W, D/2)
|
| 54 |
+
|
| 55 |
+
emb = np.concatenate([emb_sin, emb_cos], axis=-1) # (H, W, D)
|
| 56 |
+
return emb
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
class Resampler(nn.Module):
|
| 60 |
+
"""
|
| 61 |
+
A 2D perceiver-resampler network with one cross attention layers by
|
| 62 |
+
given learnable queries and 2d sincos pos_emb
|
| 63 |
+
Outputs:
|
| 64 |
+
A tensor with the shape of (batch_size, num_queries, embed_dim)
|
| 65 |
+
"""
|
| 66 |
+
|
| 67 |
+
def __init__(
|
| 68 |
+
self,
|
| 69 |
+
num_queries,
|
| 70 |
+
embed_dim,
|
| 71 |
+
num_heads,
|
| 72 |
+
kv_dim=None,
|
| 73 |
+
norm_layer=partial(nn.LayerNorm, eps=1e-6),
|
| 74 |
+
adaptive=False,
|
| 75 |
+
max_size=(70, 70),
|
| 76 |
+
):
|
| 77 |
+
super().__init__()
|
| 78 |
+
self.num_queries = num_queries
|
| 79 |
+
self.embed_dim = embed_dim
|
| 80 |
+
self.num_heads = num_heads
|
| 81 |
+
self.adaptive = adaptive
|
| 82 |
+
self.max_size = max_size
|
| 83 |
+
|
| 84 |
+
self.query = nn.Parameter(torch.zeros(self.num_queries, embed_dim))
|
| 85 |
+
trunc_normal_(self.query, std=.02)
|
| 86 |
+
|
| 87 |
+
if kv_dim is not None and kv_dim != embed_dim:
|
| 88 |
+
self.kv_proj = nn.Linear(kv_dim, embed_dim, bias=False)
|
| 89 |
+
else:
|
| 90 |
+
self.kv_proj = nn.Identity()
|
| 91 |
+
|
| 92 |
+
self.attn = nn.MultiheadAttention(embed_dim, num_heads)
|
| 93 |
+
self.ln_q = norm_layer(embed_dim)
|
| 94 |
+
self.ln_kv = norm_layer(embed_dim)
|
| 95 |
+
|
| 96 |
+
self.ln_post = norm_layer(embed_dim)
|
| 97 |
+
self.proj = nn.Parameter((embed_dim ** -0.5) * torch.randn(embed_dim, embed_dim))
|
| 98 |
+
|
| 99 |
+
self._set_2d_pos_cache(self.max_size)
|
| 100 |
+
self.apply(self._init_weights)
|
| 101 |
+
|
| 102 |
+
def _set_2d_pos_cache(self, max_size, device='cpu'):
|
| 103 |
+
pos_embed = torch.from_numpy(get_2d_sincos_pos_embed(self.embed_dim, max_size)).float().to(device)
|
| 104 |
+
self.register_buffer("pos_embed", pos_embed, persistent=False)
|
| 105 |
+
|
| 106 |
+
def _adjust_pos_cache(self, tgt_sizes, device):
|
| 107 |
+
max_h = torch.max(tgt_sizes[:, 0])
|
| 108 |
+
max_w = torch.max(tgt_sizes[:, 1])
|
| 109 |
+
if max_h > self.max_size[0] or max_w > self.max_size[1]:
|
| 110 |
+
self.max_size = [max(max_h, self.max_size[0]), max(max_w, self.max_size[1])]
|
| 111 |
+
self._set_2d_pos_cache(self.max_size, device)
|
| 112 |
+
|
| 113 |
+
def _init_weights(self, m):
|
| 114 |
+
if isinstance(m, nn.Linear):
|
| 115 |
+
trunc_normal_(m.weight, std=.02)
|
| 116 |
+
if isinstance(m, nn.Linear) and m.bias is not None:
|
| 117 |
+
nn.init.constant_(m.bias, 0)
|
| 118 |
+
elif isinstance(m, nn.LayerNorm):
|
| 119 |
+
nn.init.constant_(m.bias, 0)
|
| 120 |
+
nn.init.constant_(m.weight, 1.0)
|
| 121 |
+
|
| 122 |
+
def forward(self, x, tgt_sizes=None):
|
| 123 |
+
assert x.shape[0] == tgt_sizes.shape[0]
|
| 124 |
+
bs = x.shape[0]
|
| 125 |
+
|
| 126 |
+
device = x.device
|
| 127 |
+
dtype = x.dtype
|
| 128 |
+
|
| 129 |
+
patch_len = tgt_sizes[:, 0] * tgt_sizes[:, 1]
|
| 130 |
+
|
| 131 |
+
self._adjust_pos_cache(tgt_sizes, device=device)
|
| 132 |
+
|
| 133 |
+
max_patch_len = torch.max(patch_len)
|
| 134 |
+
key_padding_mask = torch.zeros((bs, max_patch_len), dtype=torch.bool, device=device)
|
| 135 |
+
|
| 136 |
+
pos_embed = []
|
| 137 |
+
for i in range(bs):
|
| 138 |
+
tgt_h, tgt_w = tgt_sizes[i]
|
| 139 |
+
pos_embed.append(self.pos_embed[:tgt_h, :tgt_w, :].reshape((tgt_h * tgt_w, -1)).to(dtype)) # patches * D
|
| 140 |
+
key_padding_mask[i, patch_len[i]:] = True
|
| 141 |
+
|
| 142 |
+
pos_embed = torch.nn.utils.rnn.pad_sequence(
|
| 143 |
+
pos_embed, batch_first=True, padding_value=0.0).permute(1, 0, 2) # BLD => L * B * D
|
| 144 |
+
|
| 145 |
+
x = self.kv_proj(x) # B * L * D
|
| 146 |
+
x = self.ln_kv(x).permute(1, 0, 2) # L * B * D
|
| 147 |
+
|
| 148 |
+
q = self.ln_q(self.query) # Q * D
|
| 149 |
+
|
| 150 |
+
out = self.attn(
|
| 151 |
+
self._repeat(q, bs), # Q * B * D
|
| 152 |
+
x + pos_embed, # L * B * D + L * B * D
|
| 153 |
+
x,
|
| 154 |
+
key_padding_mask=key_padding_mask)[0]
|
| 155 |
+
# out: Q * B * D
|
| 156 |
+
x = out.permute(1, 0, 2) # B * Q * D
|
| 157 |
+
|
| 158 |
+
x = self.ln_post(x)
|
| 159 |
+
x = x @ self.proj
|
| 160 |
+
return x
|
| 161 |
+
|
| 162 |
+
def _repeat(self, query, N: int):
|
| 163 |
+
return query.unsqueeze(1).repeat(1, N, 1)
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end_of_text|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "!",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2072 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<image>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "</image>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<ref>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "</ref>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<box>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "</box>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<quad>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "</quad>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<point>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "</point>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<slice>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "</slice>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"auto_map": {
|
| 2053 |
+
"AutoTokenizer": [
|
| 2054 |
+
"modeling_minicpmv.PreTrainedTokenizerFastWrapper",
|
| 2055 |
+
null
|
| 2056 |
+
]
|
| 2057 |
+
},
|
| 2058 |
+
"bos_token": "<|begin_of_text|>",
|
| 2059 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
| 2060 |
+
"clean_up_tokenization_spaces": true,
|
| 2061 |
+
"eos_token": "<|end_of_text|>",
|
| 2062 |
+
"model_input_names": [
|
| 2063 |
+
"input_ids",
|
| 2064 |
+
"attention_mask"
|
| 2065 |
+
],
|
| 2066 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2067 |
+
"pad_token": "!",
|
| 2068 |
+
"padding_side": "right",
|
| 2069 |
+
"tokenizer_class": "PreTrainedTokenizerFastWrapper",
|
| 2070 |
+
"truncation_side": "right",
|
| 2071 |
+
"unk_token": "<unk>"
|
| 2072 |
+
}
|