add models

Mistral-Small-24B-3.1/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

Mistral-Small-24B-3.1/README.md

@@ -0,0 +1,561 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+library_name: vllm
+base_model:
+- mistralai/Mistral-Small-3.1-24B-Instruct-2503
+pipeline_tag: image-text-to-text
+tags:
+- neuralmagic
+- redhat
+- llmcompressor
+- quantized
+- int4
+---
+
+# Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16
+
+## Model Overview
+- **Model Architecture:** Mistral3ForConditionalGeneration
+  - **Input:** Text / Image
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** INT4
+- **Intended Use Cases:** It is ideal for:
+  - Fast-response conversational agents.
+  - Low-latency function calling.
+  - Subject matter experts via fine-tuning.
+  - Local inference for hobbyists and organizations handling sensitive data.
+  - Programming and math reasoning.
+  - Long document understanding.
+  - Visual understanding.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages not officially supported by the model.
+- **Release Date:** 04/15/2025
+- **Version:** 1.0
+- **Model Developers:** Red Hat (Neural Magic)
+
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights of [Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503) to INT4 data type.
+This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 75%.
+
+Only the weights of the linear operators within transformers blocks are quantized.
+Weights are quantized using a symmetric per-group scheme, with group size 128.
+The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library.
+
+
+## Deployment
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoProcessor
+
+model_id = "RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic"
+number_gpus = 1
+
+sampling_params = SamplingParams(temperature=0.7, top_p=0.8, max_tokens=256)
+processor = AutoProcessor.from_pretrained(model_id)
+
+messages = [{"role": "user", "content": "Give me a short introduction to large language model."}]
+
+prompts = processor.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+
+llm = LLM(model=model_id, tensor_parallel_size=number_gpus)
+
+outputs = llm.generate(prompts, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+<details>
+  <summary>Creation details</summary>
+  This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below. 
+
+
+  ```python
+  from transformers import AutoProcessor
+  from llmcompressor.modifiers.quantization import GPTQModifier
+  from llmcompressor.transformers import oneshot
+  from llmcompressor.transformers.tracing import TraceableMistral3ForConditionalGeneration
+  from datasets import load_dataset, interleave_datasets
+  from PIL import Image
+  import io
+  
+  # Load model
+  model_stub = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+  model_name = model_stub.split("/")[-1]
+  
+  num_text_samples = 1024
+  num_vision_samples = 1024
+  max_seq_len = 8192
+  
+  processor = AutoProcessor.from_pretrained(model_stub)
+  
+  model = TraceableMistral3ForConditionalGeneration.from_pretrained(
+      model_stub,
+      device_map="auto",
+      torch_dtype="auto",
+  )
+
+  # Text-only data subset
+  def preprocess_text(example):
+      input = {
+          "text": processor.apply_chat_template(
+              example["messages"],
+              add_generation_prompt=False,
+          ),
+          "images": None,
+      }
+      tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
+      tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
+      tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
+      return tokenized_input
+
+  dst = load_dataset("neuralmagic/calibration", name="LLM", split="train").select(range(num_text_samples))
+  dst = dst.map(preprocess_text, remove_columns=dst.column_names)
+
+  # Text + vision data subset
+  def preprocess_vision(example):
+      messages = []
+      image = None
+      for message in example["messages"]:
+          message_content = []
+          for content in message["content"]:
+              if content["type"] == "text":
+                  message_content.append({"type": "text", "text": content["text"]})
+              else:
+                  message_content.append({"type": "image"})
+                  image = Image.open(io.BytesIO(content["image"]))
+
+          messages.append(
+              {
+                  "role": message["role"],
+                  "content": message_content,
+              }
+          )
+
+      input = {
+          "text": processor.apply_chat_template(
+              messages,
+              add_generation_prompt=False,
+          ),
+          "images": image,
+      }
+      tokenized_input = processor(**input, max_length=max_seq_len, truncation=True)
+      tokenized_input["pixel_values"] = tokenized_input.get("pixel_values", None)
+      tokenized_input["image_sizes"] = tokenized_input.get("image_sizes", None)
+      return tokenized_input
+
+  dsv = load_dataset("neuralmagic/calibration", name="VLM", split="train").select(range(num_vision_samples))
+  dsv = dsv.map(preprocess_vision, remove_columns=dsv.column_names)
+
+  # Interleave subsets
+  ds = interleave_datasets((dsv, dst))
+
+  # Configure the quantization algorithm and scheme
+  recipe = GPTQModifier(
+      ignore=["language_model.lm_head", "re:vision_tower.*", "re:multi_modal_projector.*"],
+      sequential_targets=["MistralDecoderLayer"],
+      dampening_frac=0.01,
+      targets="Linear",
+      scheme="W4A16",
+  )
+
+  # Define data collator
+  def data_collator(batch):
+      import torch
+      assert len(batch) == 1
+      collated = {}
+      for k, v in batch[0].items():
+          if v is None:
+              continue
+          if k == "input_ids":
+              collated[k] = torch.LongTensor(v)
+          elif k == "pixel_values":
+              collated[k] = torch.tensor(v, dtype=torch.bfloat16)
+          else:
+              collated[k] = torch.tensor(v)
+      return collated
+
+
+  # Apply quantization
+  oneshot(
+      model=model,
+      dataset=ds, 
+      recipe=recipe,
+      max_seq_length=max_seq_len,
+      data_collator=data_collator,
+      num_calibration_samples=num_text_samples + num_vision_samples,
+  )
+  
+  # Save to disk in compressed-tensors format
+  save_path = model_name + "-quantized.w4a16"
+  model.save_pretrained(save_path)
+  processor.save_pretrained(save_path)
+  print(f"Model and tokenizer saved to: {save_path}")
+  ```
+</details>
+ 
+
+
+## Evaluation
+
+The model was evaluated on the OpenLLM leaderboard tasks (version 1), MMLU-pro, GPQA, HumanEval and MBPP.
+Non-coding tasks were evaluated with [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness), whereas coding tasks were evaluated with a fork of [evalplus](https://github.com/neuralmagic/evalplus).
+[vLLM](https://docs.vllm.ai/en/stable/) is used as the engine in all cases.
+
+<details>
+  <summary>Evaluation details</summary>
+
+  **MMLU**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks mmlu \
+    --num_fewshot 5 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **ARC Challenge**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks arc_challenge \
+    --num_fewshot 25 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **GSM8k**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks gsm8k \
+    --num_fewshot 8 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **Hellaswag**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks hellaswag \
+    --num_fewshot 10 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **Winogrande**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks winogrande \
+    --num_fewshot 5 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **TruthfulQA**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks truthfulqa \
+    --num_fewshot 0 \
+    --apply_chat_template\
+    --batch_size auto
+  ```
+
+  **MMLU-pro**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.5,max_model_len=8192,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks mmlu_pro \
+    --num_fewshot 5 \
+    --apply_chat_template\
+    --fewshot_as_multiturn \
+    --batch_size auto
+  ```
+
+  **MMMU**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_images=8,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks mmmu_val \
+    --apply_chat_template\
+    --batch_size auto
+  ```
+
+  **ChartQA**
+  ```
+  lm_eval \
+    --model vllm \
+    --model_args pretrained="RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16",dtype=auto,gpu_memory_utilization=0.9,max_images=8,enable_chunk_prefill=True,tensor_parallel_size=2 \
+    --tasks chartqa \
+    --apply_chat_template\
+    --batch_size auto
+  ```
+
+**Coding**
+
+The commands below can be used for mbpp by simply replacing the dataset name.
+
+*Generation*
+```
+python3 codegen/generate.py \
+  --model RedHatAI/Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16 \
+  --bs 16 \
+  --temperature 0.2 \
+  --n_samples 50 \
+  --root "." \
+  --dataset humaneval
+
+```
+
+*Sanitization*
+```
+python3 evalplus/sanitize.py \
+  humaneval/RedHatAI--Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16_vllm_temp_0.2
+```
+
+*Evaluation*
+```
+evalplus.evaluate \
+  --dataset humaneval \
+  --samples humaneval/RedHatAI--Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16_vllm_temp_0.2-sanitized
+```
+</details>
+
+### Accuracy
+
+<table>
+  <tr>
+   <th>Category
+   </th>
+   <th>Benchmark
+   </th>
+   <th>Mistral-Small-3.1-24B-Instruct-2503
+   </th>
+   <th>Mistral-Small-3.1-24B-Instruct-2503-quantized.w4a16<br>(this model)
+   </th>
+   <th>Recovery
+   </th>
+  </tr>
+  <tr>
+   <td rowspan="7" ><strong>OpenLLM v1</strong>
+   </td>
+   <td>MMLU (5-shot)
+   </td>
+   <td>80.67
+   </td>
+   <td>79.74
+   </td>
+   <td>98.9%
+   </td>
+  </tr>
+  <tr>
+   <td>ARC Challenge (25-shot)
+   </td>
+   <td>72.78
+   </td>
+   <td>72.18
+   </td>
+   <td>99.2%
+   </td>
+  </tr>
+  <tr>
+   <td>GSM-8K (5-shot, strict-match)
+   </td>
+   <td>58.68
+   </td>
+   <td>59.59
+   </td>
+   <td>101.6%
+   </td>
+  </tr>
+  <tr>
+   <td>Hellaswag (10-shot)
+   </td>
+   <td>83.70
+   </td>
+   <td>83.25
+   </td>
+   <td>99.5%
+   </td>
+  </tr>
+  <tr>
+   <td>Winogrande (5-shot)
+   </td>
+   <td>83.74
+   </td>
+   <td>83.43
+   </td>
+   <td>99.6%
+   </td>
+  </tr>
+  <tr>
+   <td>TruthfulQA (0-shot, mc2)
+   </td>
+   <td>70.62
+   </td>
+   <td>69.56
+   </td>
+   <td>98.5%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>75.03</strong>
+   </td>
+   <td><strong>74.63</strong>
+   </td>
+   <td><strong>99.5%</strong>
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="3" ><strong></strong>
+   </td>
+   <td>MMLU-Pro (5-shot)
+   </td>
+   <td>67.25
+   </td>
+   <td>66.56
+   </td>
+   <td>99.0%
+   </td>
+  </tr>
+  <tr>
+   <td>GPQA CoT main (5-shot)
+   </td>
+   <td>42.63
+   </td>
+   <td>47.10
+   </td>
+   <td>110.5%
+   </td>
+  </tr>
+  <tr>
+   <td>GPQA CoT diamond (5-shot)
+   </td>
+   <td>45.96
+   </td>
+   <td>44.95
+   </td>
+   <td>97.80%
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="4" ><strong>Coding</strong>
+   </td>
+   <td>HumanEval pass@1
+   </td>
+   <td>84.70
+   </td>
+   <td>84.60
+   </td>
+   <td>99.9%
+   </td>
+  </tr>
+  <tr>
+   <td>HumanEval+ pass@1
+   </td>
+   <td>79.50
+   </td>
+   <td>79.90
+   </td>
+   <td>100.5%
+   </td>
+  </tr>
+  <tr>
+   <td>MBPP pass@1
+   </td>
+   <td>71.10
+   </td>
+   <td>70.10
+   </td>
+   <td>98.6%
+   </td>
+  </tr>
+  <tr>
+   <td>MBPP+ pass@1
+   </td>
+   <td>60.60
+   </td>
+   <td>60.70
+   </td>
+   <td>100.2%
+   </td>
+  </tr>
+  <tr>
+   <td rowspan="2" ><strong>Vision</strong>
+   </td>
+   <td>MMMU (0-shot)
+   </td>
+   <td>52.11
+   </td>
+   <td>50.11
+   </td>
+   <td>96.2%
+   </td>
+  </tr>
+  <tr>
+   <td>ChartQA (0-shot)
+   </td>
+   <td>81.36
+   </td>
+   <td>80.92
+   </td>
+   <td>99.5%
+   </td>
+  </tr>
+  <tr>
+</table>
+

Mistral-Small-24B-3.1/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYour knowledge base was last updated on 2023-10-01. The current date is \" + today + \".\\n\\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \\\"What are some good restaurants around me?\\\" => \\\"Where are you?\\\" or \\\"When is the next flight to Tokyo\\\" => \\\"Where do you travel from?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content'] %}\n    {%- else %}\n        {%- set system_message = messages[0]['content'][0]['text'] %}\n    {%- endif %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = default_system_message %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n    {%- if message['role'] == 'user' %}\n        {%- if message['content'] is string %}\n            {{- '[INST]' + message['content'] + '[/INST]' }}\n        {%- else %}\n            {{- '[INST]' }}\n            {%- for block in message['content'] %}\n                {%- if block['type'] == 'text' %}\n                    {{- block['text'] }}\n                {%- elif block['type'] in ['image', 'image_url'] %}\n                    {{- '[IMG]' }}\n                {%- else %}\n                    {{- raise_exception('Only text and image blocks are supported in message content!') }}\n                {%- endif %}\n            {%- endfor %}\n            {{- '[/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'system' %}\n        {%- if message['content'] is string %}\n            {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n        {%- else %}\n            {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {%- if message['content'] is string %}\n            {{- message['content'] + eos_token }}\n        {%- else %}\n            {{- message['content'][0]['text'] + eos_token }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Only user, system and assistant roles are supported!') }}\n    {%- endif %}\n{%- endfor %}"
+}

Mistral-Small-24B-3.1/config.json

@@ -0,0 +1,249 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": "weight",
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": 1.4742778120818896,
+    "ignore": [
+      "vision_tower.transformer.layers.0.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.0.feed_forward.up_proj",
+      "vision_tower.transformer.layers.0.feed_forward.down_proj",
+      "vision_tower.transformer.layers.0.attention.k_proj",
+      "vision_tower.transformer.layers.0.attention.v_proj",
+      "vision_tower.transformer.layers.0.attention.q_proj",
+      "vision_tower.transformer.layers.0.attention.o_proj",
+      "vision_tower.transformer.layers.1.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.1.feed_forward.up_proj",
+      "vision_tower.transformer.layers.1.feed_forward.down_proj",
+      "vision_tower.transformer.layers.1.attention.k_proj",
+      "vision_tower.transformer.layers.1.attention.v_proj",
+      "vision_tower.transformer.layers.1.attention.q_proj",
+      "vision_tower.transformer.layers.1.attention.o_proj",
+      "vision_tower.transformer.layers.2.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.2.feed_forward.up_proj",
+      "vision_tower.transformer.layers.2.feed_forward.down_proj",
+      "vision_tower.transformer.layers.2.attention.k_proj",
+      "vision_tower.transformer.layers.2.attention.v_proj",
+      "vision_tower.transformer.layers.2.attention.q_proj",
+      "vision_tower.transformer.layers.2.attention.o_proj",
+      "vision_tower.transformer.layers.3.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.3.feed_forward.up_proj",
+      "vision_tower.transformer.layers.3.feed_forward.down_proj",
+      "vision_tower.transformer.layers.3.attention.k_proj",
+      "vision_tower.transformer.layers.3.attention.v_proj",
+      "vision_tower.transformer.layers.3.attention.q_proj",
+      "vision_tower.transformer.layers.3.attention.o_proj",
+      "vision_tower.transformer.layers.4.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.4.feed_forward.up_proj",
+      "vision_tower.transformer.layers.4.feed_forward.down_proj",
+      "vision_tower.transformer.layers.4.attention.k_proj",
+      "vision_tower.transformer.layers.4.attention.v_proj",
+      "vision_tower.transformer.layers.4.attention.q_proj",
+      "vision_tower.transformer.layers.4.attention.o_proj",
+      "vision_tower.transformer.layers.5.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.5.feed_forward.up_proj",
+      "vision_tower.transformer.layers.5.feed_forward.down_proj",
+      "vision_tower.transformer.layers.5.attention.k_proj",
+      "vision_tower.transformer.layers.5.attention.v_proj",
+      "vision_tower.transformer.layers.5.attention.q_proj",
+      "vision_tower.transformer.layers.5.attention.o_proj",
+      "vision_tower.transformer.layers.6.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.6.feed_forward.up_proj",
+      "vision_tower.transformer.layers.6.feed_forward.down_proj",
+      "vision_tower.transformer.layers.6.attention.k_proj",
+      "vision_tower.transformer.layers.6.attention.v_proj",
+      "vision_tower.transformer.layers.6.attention.q_proj",
+      "vision_tower.transformer.layers.6.attention.o_proj",
+      "vision_tower.transformer.layers.7.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.7.feed_forward.up_proj",
+      "vision_tower.transformer.layers.7.feed_forward.down_proj",
+      "vision_tower.transformer.layers.7.attention.k_proj",
+      "vision_tower.transformer.layers.7.attention.v_proj",
+      "vision_tower.transformer.layers.7.attention.q_proj",
+      "vision_tower.transformer.layers.7.attention.o_proj",
+      "vision_tower.transformer.layers.8.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.8.feed_forward.up_proj",
+      "vision_tower.transformer.layers.8.feed_forward.down_proj",
+      "vision_tower.transformer.layers.8.attention.k_proj",
+      "vision_tower.transformer.layers.8.attention.v_proj",
+      "vision_tower.transformer.layers.8.attention.q_proj",
+      "vision_tower.transformer.layers.8.attention.o_proj",
+      "vision_tower.transformer.layers.9.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.9.feed_forward.up_proj",
+      "vision_tower.transformer.layers.9.feed_forward.down_proj",
+      "vision_tower.transformer.layers.9.attention.k_proj",
+      "vision_tower.transformer.layers.9.attention.v_proj",
+      "vision_tower.transformer.layers.9.attention.q_proj",
+      "vision_tower.transformer.layers.9.attention.o_proj",
+      "vision_tower.transformer.layers.10.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.10.feed_forward.up_proj",
+      "vision_tower.transformer.layers.10.feed_forward.down_proj",
+      "vision_tower.transformer.layers.10.attention.k_proj",
+      "vision_tower.transformer.layers.10.attention.v_proj",
+      "vision_tower.transformer.layers.10.attention.q_proj",
+      "vision_tower.transformer.layers.10.attention.o_proj",
+      "vision_tower.transformer.layers.11.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.11.feed_forward.up_proj",
+      "vision_tower.transformer.layers.11.feed_forward.down_proj",
+      "vision_tower.transformer.layers.11.attention.k_proj",
+      "vision_tower.transformer.layers.11.attention.v_proj",
+      "vision_tower.transformer.layers.11.attention.q_proj",
+      "vision_tower.transformer.layers.11.attention.o_proj",
+      "vision_tower.transformer.layers.12.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.12.feed_forward.up_proj",
+      "vision_tower.transformer.layers.12.feed_forward.down_proj",
+      "vision_tower.transformer.layers.12.attention.k_proj",
+      "vision_tower.transformer.layers.12.attention.v_proj",
+      "vision_tower.transformer.layers.12.attention.q_proj",
+      "vision_tower.transformer.layers.12.attention.o_proj",
+      "vision_tower.transformer.layers.13.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.13.feed_forward.up_proj",
+      "vision_tower.transformer.layers.13.feed_forward.down_proj",
+      "vision_tower.transformer.layers.13.attention.k_proj",
+      "vision_tower.transformer.layers.13.attention.v_proj",
+      "vision_tower.transformer.layers.13.attention.q_proj",
+      "vision_tower.transformer.layers.13.attention.o_proj",
+      "vision_tower.transformer.layers.14.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.14.feed_forward.up_proj",
+      "vision_tower.transformer.layers.14.feed_forward.down_proj",
+      "vision_tower.transformer.layers.14.attention.k_proj",
+      "vision_tower.transformer.layers.14.attention.v_proj",
+      "vision_tower.transformer.layers.14.attention.q_proj",
+      "vision_tower.transformer.layers.14.attention.o_proj",
+      "vision_tower.transformer.layers.15.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.15.feed_forward.up_proj",
+      "vision_tower.transformer.layers.15.feed_forward.down_proj",
+      "vision_tower.transformer.layers.15.attention.k_proj",
+      "vision_tower.transformer.layers.15.attention.v_proj",
+      "vision_tower.transformer.layers.15.attention.q_proj",
+      "vision_tower.transformer.layers.15.attention.o_proj",
+      "vision_tower.transformer.layers.16.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.16.feed_forward.up_proj",
+      "vision_tower.transformer.layers.16.feed_forward.down_proj",
+      "vision_tower.transformer.layers.16.attention.k_proj",
+      "vision_tower.transformer.layers.16.attention.v_proj",
+      "vision_tower.transformer.layers.16.attention.q_proj",
+      "vision_tower.transformer.layers.16.attention.o_proj",
+      "vision_tower.transformer.layers.17.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.17.feed_forward.up_proj",
+      "vision_tower.transformer.layers.17.feed_forward.down_proj",
+      "vision_tower.transformer.layers.17.attention.k_proj",
+      "vision_tower.transformer.layers.17.attention.v_proj",
+      "vision_tower.transformer.layers.17.attention.q_proj",
+      "vision_tower.transformer.layers.17.attention.o_proj",
+      "vision_tower.transformer.layers.18.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.18.feed_forward.up_proj",
+      "vision_tower.transformer.layers.18.feed_forward.down_proj",
+      "vision_tower.transformer.layers.18.attention.k_proj",
+      "vision_tower.transformer.layers.18.attention.v_proj",
+      "vision_tower.transformer.layers.18.attention.q_proj",
+      "vision_tower.transformer.layers.18.attention.o_proj",
+      "vision_tower.transformer.layers.19.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.19.feed_forward.up_proj",
+      "vision_tower.transformer.layers.19.feed_forward.down_proj",
+      "vision_tower.transformer.layers.19.attention.k_proj",
+      "vision_tower.transformer.layers.19.attention.v_proj",
+      "vision_tower.transformer.layers.19.attention.q_proj",
+      "vision_tower.transformer.layers.19.attention.o_proj",
+      "vision_tower.transformer.layers.20.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.20.feed_forward.up_proj",
+      "vision_tower.transformer.layers.20.feed_forward.down_proj",
+      "vision_tower.transformer.layers.20.attention.k_proj",
+      "vision_tower.transformer.layers.20.attention.v_proj",
+      "vision_tower.transformer.layers.20.attention.q_proj",
+      "vision_tower.transformer.layers.20.attention.o_proj",
+      "vision_tower.transformer.layers.21.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.21.feed_forward.up_proj",
+      "vision_tower.transformer.layers.21.feed_forward.down_proj",
+      "vision_tower.transformer.layers.21.attention.k_proj",
+      "vision_tower.transformer.layers.21.attention.v_proj",
+      "vision_tower.transformer.layers.21.attention.q_proj",
+      "vision_tower.transformer.layers.21.attention.o_proj",
+      "vision_tower.transformer.layers.22.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.22.feed_forward.up_proj",
+      "vision_tower.transformer.layers.22.feed_forward.down_proj",
+      "vision_tower.transformer.layers.22.attention.k_proj",
+      "vision_tower.transformer.layers.22.attention.v_proj",
+      "vision_tower.transformer.layers.22.attention.q_proj",
+      "vision_tower.transformer.layers.22.attention.o_proj",
+      "vision_tower.transformer.layers.23.feed_forward.gate_proj",
+      "vision_tower.transformer.layers.23.feed_forward.up_proj",
+      "vision_tower.transformer.layers.23.feed_forward.down_proj",
+      "vision_tower.transformer.layers.23.attention.k_proj",
+      "vision_tower.transformer.layers.23.attention.v_proj",
+      "vision_tower.transformer.layers.23.attention.q_proj",
+      "vision_tower.transformer.layers.23.attention.o_proj",
+      "multi_modal_projector.patch_merger.merging_layer",
+      "multi_modal_projector.linear_1",
+      "multi_modal_projector.linear_2",
+      "language_model.lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed"
+  },
+  "spatial_merge_size": 2,
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 32768,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_theta": 10000.0
+  },
+  "vision_feature_layer": -1
+}

Mistral-Small-24B-3.1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.52.0.dev0"
+}

Mistral-Small-24B-3.1/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0410f5c2e3361be5b2ead577ffe59869ca858a394f27c8bbdb5e225152a36065
+size 4999392136

Mistral-Small-24B-3.1/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f489b95165422629849fd1207bf8b606bc20520256c9961752d9d34ca19a75e0
+size 4985419312

Mistral-Small-24B-3.1/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fafff9d17a87a9edff930708dd937b09c1d0861251160327731cbf9e721dbc
+size 3698511448

Mistral-Small-24B-3.1/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0712cb93d3b9d05902f1c99d04294296cdfa37829a5f56d6e9a879b280dc346e
+size 1342177424

Mistral-Small-24B-3.1/preprocessor_config.json

@@ -0,0 +1,34 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "patch_size": {
+    "height": 14,
+    "width": 14
+  },
+  "processor_class": "PixtralProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 1540
+  }
+}

Mistral-Small-24B-3.1/processor_config.json

@@ -0,0 +1,8 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_token": "[IMG]",
+  "patch_size": 14,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 2
+}

Mistral-Small-24B-3.1/recipe.yaml

@@ -0,0 +1,11 @@
+quant_stage:
+  quant_modifiers:
+    GPTQModifier:
+      ignore: [language_model.lm_head, 're:vision_tower.*', 're:multi_modal_projector.*']
+      sequential_targets: [MistralDecoderLayer]
+      dampening_frac: 0.01
+      config_groups:
+        group0:
+          targets: [Linear]
+          weights: {num_bits: 4, type: int, strategy: group, group_size: 128, symmetric: true,
+            actorder: weight, observer: minmax}

Mistral-Small-24B-3.1/special_tokens_map.json

@@ -0,0 +1,1032 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>",
+    "[INST]",
+    "[/INST]",
+    "[AVAILABLE_TOOLS]",
+    "[/AVAILABLE_TOOLS]",
+    "[TOOL_RESULTS]",
+    "[/TOOL_RESULTS]",
+    "[TOOL_CALLS]",
+    "[IMG]",
+    "<pad>",
+    "[IMG_BREAK]",
+    "[IMG_END]",
+    "[PREFIX]",
+    "[MIDDLE]",
+    "[SUFFIX]",
+    "[SYSTEM_PROMPT]",
+    "[/SYSTEM_PROMPT]",
+    "[TOOL_CONTENT]",
+    "<SPECIAL_20>",
+    "<SPECIAL_21>",
+    "<SPECIAL_22>",
+    "<SPECIAL_23>",
+    "<SPECIAL_24>",
+    "<SPECIAL_25>",
+    "<SPECIAL_26>",
+    "<SPECIAL_27>",
+    "<SPECIAL_28>",
+    "<SPECIAL_29>",
+    "<SPECIAL_30>",
+    "<SPECIAL_31>",
+    "<SPECIAL_32>",
+    "<SPECIAL_33>",
+    "<SPECIAL_34>",
+    "<SPECIAL_35>",
+    "<SPECIAL_36>",
+    "<SPECIAL_37>",
+    "<SPECIAL_38>",
+    "<SPECIAL_39>",
+    "<SPECIAL_40>",
+    "<SPECIAL_41>",
+    "<SPECIAL_42>",
+    "<SPECIAL_43>",
+    "<SPECIAL_44>",
+    "<SPECIAL_45>",
+    "<SPECIAL_46>",
+    "<SPECIAL_47>",
+    "<SPECIAL_48>",
+    "<SPECIAL_49>",
+    "<SPECIAL_50>",
+    "<SPECIAL_51>",
+    "<SPECIAL_52>",
+    "<SPECIAL_53>",
+    "<SPECIAL_54>",
+    "<SPECIAL_55>",
+    "<SPECIAL_56>",
+    "<SPECIAL_57>",
+    "<SPECIAL_58>",
+    "<SPECIAL_59>",
+    "<SPECIAL_60>",
+    "<SPECIAL_61>",
+    "<SPECIAL_62>",
+    "<SPECIAL_63>",
+    "<SPECIAL_64>",
+    "<SPECIAL_65>",
+    "<SPECIAL_66>",
+    "<SPECIAL_67>",
+    "<SPECIAL_68>",
+    "<SPECIAL_69>",
+    "<SPECIAL_70>",
+    "<SPECIAL_71>",
+    "<SPECIAL_72>",
+    "<SPECIAL_73>",
+    "<SPECIAL_74>",
+    "<SPECIAL_75>",
+    "<SPECIAL_76>",
+    "<SPECIAL_77>",
+    "<SPECIAL_78>",
+    "<SPECIAL_79>",
+    "<SPECIAL_80>",
+    "<SPECIAL_81>",
+    "<SPECIAL_82>",
+    "<SPECIAL_83>",
+    "<SPECIAL_84>",
+    "<SPECIAL_85>",
+    "<SPECIAL_86>",
+    "<SPECIAL_87>",
+    "<SPECIAL_88>",
+    "<SPECIAL_89>",
+    "<SPECIAL_90>",
+    "<SPECIAL_91>",
+    "<SPECIAL_92>",
+    "<SPECIAL_93>",
+    "<SPECIAL_94>",
+    "<SPECIAL_95>",
+    "<SPECIAL_96>",
+    "<SPECIAL_97>",
+    "<SPECIAL_98>",
+    "<SPECIAL_99>",
+    "<SPECIAL_100>",
+    "<SPECIAL_101>",
+    "<SPECIAL_102>",
+    "<SPECIAL_103>",
+    "<SPECIAL_104>",
+    "<SPECIAL_105>",
+    "<SPECIAL_106>",
+    "<SPECIAL_107>",
+    "<SPECIAL_108>",
+    "<SPECIAL_109>",
+    "<SPECIAL_110>",
+    "<SPECIAL_111>",
+    "<SPECIAL_112>",
+    "<SPECIAL_113>",
+    "<SPECIAL_114>",
+    "<SPECIAL_115>",
+    "<SPECIAL_116>",
+    "<SPECIAL_117>",
+    "<SPECIAL_118>",
+    "<SPECIAL_119>",
+    "<SPECIAL_120>",
+    "<SPECIAL_121>",
+    "<SPECIAL_122>",
+    "<SPECIAL_123>",
+    "<SPECIAL_124>",
+    "<SPECIAL_125>",
+    "<SPECIAL_126>",
+    "<SPECIAL_127>",
+    "<SPECIAL_128>",
+    "<SPECIAL_129>",
+    "<SPECIAL_130>",
+    "<SPECIAL_131>",
+    "<SPECIAL_132>",
+    "<SPECIAL_133>",
+    "<SPECIAL_134>",
+    "<SPECIAL_135>",
+    "<SPECIAL_136>",
+    "<SPECIAL_137>",
+    "<SPECIAL_138>",
+    "<SPECIAL_139>",
+    "<SPECIAL_140>",
+    "<SPECIAL_141>",
+    "<SPECIAL_142>",
+    "<SPECIAL_143>",
+    "<SPECIAL_144>",
+    "<SPECIAL_145>",
+    "<SPECIAL_146>",
+    "<SPECIAL_147>",
+    "<SPECIAL_148>",
+    "<SPECIAL_149>",
+    "<SPECIAL_150>",
+    "<SPECIAL_151>",
+    "<SPECIAL_152>",
+    "<SPECIAL_153>",
+    "<SPECIAL_154>",
+    "<SPECIAL_155>",
+    "<SPECIAL_156>",
+    "<SPECIAL_157>",
+    "<SPECIAL_158>",
+    "<SPECIAL_159>",
+    "<SPECIAL_160>",
+    "<SPECIAL_161>",
+    "<SPECIAL_162>",
+    "<SPECIAL_163>",
+    "<SPECIAL_164>",
+    "<SPECIAL_165>",
+    "<SPECIAL_166>",
+    "<SPECIAL_167>",
+    "<SPECIAL_168>",
+    "<SPECIAL_169>",
+    "<SPECIAL_170>",
+    "<SPECIAL_171>",
+    "<SPECIAL_172>",
+    "<SPECIAL_173>",
+    "<SPECIAL_174>",
+    "<SPECIAL_175>",
+    "<SPECIAL_176>",
+    "<SPECIAL_177>",
+    "<SPECIAL_178>",
+    "<SPECIAL_179>",
+    "<SPECIAL_180>",
+    "<SPECIAL_181>",
+    "<SPECIAL_182>",
+    "<SPECIAL_183>",
+    "<SPECIAL_184>",
+    "<SPECIAL_185>",
+    "<SPECIAL_186>",
+    "<SPECIAL_187>",
+    "<SPECIAL_188>",
+    "<SPECIAL_189>",
+    "<SPECIAL_190>",
+    "<SPECIAL_191>",
+    "<SPECIAL_192>",
+    "<SPECIAL_193>",
+    "<SPECIAL_194>",
+    "<SPECIAL_195>",
+    "<SPECIAL_196>",
+    "<SPECIAL_197>",
+    "<SPECIAL_198>",
+    "<SPECIAL_199>",
+    "<SPECIAL_200>",
+    "<SPECIAL_201>",
+    "<SPECIAL_202>",
+    "<SPECIAL_203>",
+    "<SPECIAL_204>",
+    "<SPECIAL_205>",
+    "<SPECIAL_206>",
+    "<SPECIAL_207>",
+    "<SPECIAL_208>",
+    "<SPECIAL_209>",
+    "<SPECIAL_210>",
+    "<SPECIAL_211>",
+    "<SPECIAL_212>",
+    "<SPECIAL_213>",
+    "<SPECIAL_214>",
+    "<SPECIAL_215>",
+    "<SPECIAL_216>",
+    "<SPECIAL_217>",
+    "<SPECIAL_218>",
+    "<SPECIAL_219>",
+    "<SPECIAL_220>",
+    "<SPECIAL_221>",
+    "<SPECIAL_222>",
+    "<SPECIAL_223>",
+    "<SPECIAL_224>",
+    "<SPECIAL_225>",
+    "<SPECIAL_226>",
+    "<SPECIAL_227>",
+    "<SPECIAL_228>",
+    "<SPECIAL_229>",
+    "<SPECIAL_230>",
+    "<SPECIAL_231>",
+    "<SPECIAL_232>",
+    "<SPECIAL_233>",
+    "<SPECIAL_234>",
+    "<SPECIAL_235>",
+    "<SPECIAL_236>",
+    "<SPECIAL_237>",
+    "<SPECIAL_238>",
+    "<SPECIAL_239>",
+    "<SPECIAL_240>",
+    "<SPECIAL_241>",
+    "<SPECIAL_242>",
+    "<SPECIAL_243>",
+    "<SPECIAL_244>",
+    "<SPECIAL_245>",
+    "<SPECIAL_246>",
+    "<SPECIAL_247>",
+    "<SPECIAL_248>",
+    "<SPECIAL_249>",
+    "<SPECIAL_250>",
+    "<SPECIAL_251>",
+    "<SPECIAL_252>",
+    "<SPECIAL_253>",
+    "<SPECIAL_254>",
+    "<SPECIAL_255>",
+    "<SPECIAL_256>",
+    "<SPECIAL_257>",
+    "<SPECIAL_258>",
+    "<SPECIAL_259>",
+    "<SPECIAL_260>",
+    "<SPECIAL_261>",
+    "<SPECIAL_262>",
+    "<SPECIAL_263>",
+    "<SPECIAL_264>",
+    "<SPECIAL_265>",
+    "<SPECIAL_266>",
+    "<SPECIAL_267>",
+    "<SPECIAL_268>",
+    "<SPECIAL_269>",
+    "<SPECIAL_270>",
+    "<SPECIAL_271>",
+    "<SPECIAL_272>",
+    "<SPECIAL_273>",
+    "<SPECIAL_274>",
+    "<SPECIAL_275>",
+    "<SPECIAL_276>",
+    "<SPECIAL_277>",
+    "<SPECIAL_278>",
+    "<SPECIAL_279>",
+    "<SPECIAL_280>",
+    "<SPECIAL_281>",
+    "<SPECIAL_282>",
+    "<SPECIAL_283>",
+    "<SPECIAL_284>",
+    "<SPECIAL_285>",
+    "<SPECIAL_286>",
+    "<SPECIAL_287>",
+    "<SPECIAL_288>",
+    "<SPECIAL_289>",
+    "<SPECIAL_290>",
+    "<SPECIAL_291>",
+    "<SPECIAL_292>",
+    "<SPECIAL_293>",
+    "<SPECIAL_294>",
+    "<SPECIAL_295>",
+    "<SPECIAL_296>",
+    "<SPECIAL_297>",
+    "<SPECIAL_298>",
+    "<SPECIAL_299>",
+    "<SPECIAL_300>",
+    "<SPECIAL_301>",
+    "<SPECIAL_302>",
+    "<SPECIAL_303>",
+    "<SPECIAL_304>",
+    "<SPECIAL_305>",
+    "<SPECIAL_306>",
+    "<SPECIAL_307>",
+    "<SPECIAL_308>",
+    "<SPECIAL_309>",
+    "<SPECIAL_310>",
+    "<SPECIAL_311>",
+    "<SPECIAL_312>",
+    "<SPECIAL_313>",
+    "<SPECIAL_314>",
+    "<SPECIAL_315>",
+    "<SPECIAL_316>",
+    "<SPECIAL_317>",
+    "<SPECIAL_318>",
+    "<SPECIAL_319>",
+    "<SPECIAL_320>",
+    "<SPECIAL_321>",
+    "<SPECIAL_322>",
+    "<SPECIAL_323>",
+    "<SPECIAL_324>",
+    "<SPECIAL_325>",
+    "<SPECIAL_326>",
+    "<SPECIAL_327>",
+    "<SPECIAL_328>",
+    "<SPECIAL_329>",
+    "<SPECIAL_330>",
+    "<SPECIAL_331>",
+    "<SPECIAL_332>",
+    "<SPECIAL_333>",
+    "<SPECIAL_334>",
+    "<SPECIAL_335>",
+    "<SPECIAL_336>",
+    "<SPECIAL_337>",
+    "<SPECIAL_338>",
+    "<SPECIAL_339>",
+    "<SPECIAL_340>",
+    "<SPECIAL_341>",
+    "<SPECIAL_342>",
+    "<SPECIAL_343>",
+    "<SPECIAL_344>",
+    "<SPECIAL_345>",
+    "<SPECIAL_346>",
+    "<SPECIAL_347>",
+    "<SPECIAL_348>",
+    "<SPECIAL_349>",
+    "<SPECIAL_350>",
+    "<SPECIAL_351>",
+    "<SPECIAL_352>",
+    "<SPECIAL_353>",
+    "<SPECIAL_354>",
+    "<SPECIAL_355>",
+    "<SPECIAL_356>",
+    "<SPECIAL_357>",
+    "<SPECIAL_358>",
+    "<SPECIAL_359>",
+    "<SPECIAL_360>",
+    "<SPECIAL_361>",
+    "<SPECIAL_362>",
+    "<SPECIAL_363>",
+    "<SPECIAL_364>",
+    "<SPECIAL_365>",
+    "<SPECIAL_366>",
+    "<SPECIAL_367>",
+    "<SPECIAL_368>",
+    "<SPECIAL_369>",
+    "<SPECIAL_370>",
+    "<SPECIAL_371>",
+    "<SPECIAL_372>",
+    "<SPECIAL_373>",
+    "<SPECIAL_374>",
+    "<SPECIAL_375>",
+    "<SPECIAL_376>",
+    "<SPECIAL_377>",
+    "<SPECIAL_378>",
+    "<SPECIAL_379>",
+    "<SPECIAL_380>",
+    "<SPECIAL_381>",
+    "<SPECIAL_382>",
+    "<SPECIAL_383>",
+    "<SPECIAL_384>",
+    "<SPECIAL_385>",
+    "<SPECIAL_386>",
+    "<SPECIAL_387>",
+    "<SPECIAL_388>",
+    "<SPECIAL_389>",
+    "<SPECIAL_390>",
+    "<SPECIAL_391>",
+    "<SPECIAL_392>",
+    "<SPECIAL_393>",
+    "<SPECIAL_394>",
+    "<SPECIAL_395>",
+    "<SPECIAL_396>",
+    "<SPECIAL_397>",
+    "<SPECIAL_398>",
+    "<SPECIAL_399>",
+    "<SPECIAL_400>",
+    "<SPECIAL_401>",
+    "<SPECIAL_402>",
+    "<SPECIAL_403>",
+    "<SPECIAL_404>",
+    "<SPECIAL_405>",
+    "<SPECIAL_406>",
+    "<SPECIAL_407>",
+    "<SPECIAL_408>",
+    "<SPECIAL_409>",
+    "<SPECIAL_410>",
+    "<SPECIAL_411>",
+    "<SPECIAL_412>",
+    "<SPECIAL_413>",
+    "<SPECIAL_414>",
+    "<SPECIAL_415>",
+    "<SPECIAL_416>",
+    "<SPECIAL_417>",
+    "<SPECIAL_418>",
+    "<SPECIAL_419>",
+    "<SPECIAL_420>",
+    "<SPECIAL_421>",
+    "<SPECIAL_422>",
+    "<SPECIAL_423>",
+    "<SPECIAL_424>",
+    "<SPECIAL_425>",
+    "<SPECIAL_426>",
+    "<SPECIAL_427>",
+    "<SPECIAL_428>",
+    "<SPECIAL_429>",
+    "<SPECIAL_430>",
+    "<SPECIAL_431>",
+    "<SPECIAL_432>",
+    "<SPECIAL_433>",
+    "<SPECIAL_434>",
+    "<SPECIAL_435>",
+    "<SPECIAL_436>",
+    "<SPECIAL_437>",
+    "<SPECIAL_438>",
+    "<SPECIAL_439>",
+    "<SPECIAL_440>",
+    "<SPECIAL_441>",
+    "<SPECIAL_442>",
+    "<SPECIAL_443>",
+    "<SPECIAL_444>",
+    "<SPECIAL_445>",
+    "<SPECIAL_446>",
+    "<SPECIAL_447>",
+    "<SPECIAL_448>",
+    "<SPECIAL_449>",
+    "<SPECIAL_450>",
+    "<SPECIAL_451>",
+    "<SPECIAL_452>",
+    "<SPECIAL_453>",
+    "<SPECIAL_454>",
+    "<SPECIAL_455>",
+    "<SPECIAL_456>",
+    "<SPECIAL_457>",
+    "<SPECIAL_458>",
+    "<SPECIAL_459>",
+    "<SPECIAL_460>",
+    "<SPECIAL_461>",
+    "<SPECIAL_462>",
+    "<SPECIAL_463>",
+    "<SPECIAL_464>",
+    "<SPECIAL_465>",
+    "<SPECIAL_466>",
+    "<SPECIAL_467>",
+    "<SPECIAL_468>",
+    "<SPECIAL_469>",
+    "<SPECIAL_470>",
+    "<SPECIAL_471>",
+    "<SPECIAL_472>",
+    "<SPECIAL_473>",
+    "<SPECIAL_474>",
+    "<SPECIAL_475>",
+    "<SPECIAL_476>",
+    "<SPECIAL_477>",
+    "<SPECIAL_478>",
+    "<SPECIAL_479>",
+    "<SPECIAL_480>",
+    "<SPECIAL_481>",
+    "<SPECIAL_482>",
+    "<SPECIAL_483>",
+    "<SPECIAL_484>",
+    "<SPECIAL_485>",
+    "<SPECIAL_486>",
+    "<SPECIAL_487>",
+    "<SPECIAL_488>",
+    "<SPECIAL_489>",
+    "<SPECIAL_490>",
+    "<SPECIAL_491>",
+    "<SPECIAL_492>",
+    "<SPECIAL_493>",
+    "<SPECIAL_494>",
+    "<SPECIAL_495>",
+    "<SPECIAL_496>",
+    "<SPECIAL_497>",
+    "<SPECIAL_498>",
+    "<SPECIAL_499>",
+    "<SPECIAL_500>",
+    "<SPECIAL_501>",
+    "<SPECIAL_502>",
+    "<SPECIAL_503>",
+    "<SPECIAL_504>",
+    "<SPECIAL_505>",
+    "<SPECIAL_506>",
+    "<SPECIAL_507>",
+    "<SPECIAL_508>",
+    "<SPECIAL_509>",
+    "<SPECIAL_510>",
+    "<SPECIAL_511>",
+    "<SPECIAL_512>",
+    "<SPECIAL_513>",
+    "<SPECIAL_514>",
+    "<SPECIAL_515>",
+    "<SPECIAL_516>",
+    "<SPECIAL_517>",
+    "<SPECIAL_518>",
+    "<SPECIAL_519>",
+    "<SPECIAL_520>",
+    "<SPECIAL_521>",
+    "<SPECIAL_522>",
+    "<SPECIAL_523>",
+    "<SPECIAL_524>",
+    "<SPECIAL_525>",
+    "<SPECIAL_526>",
+    "<SPECIAL_527>",
+    "<SPECIAL_528>",
+    "<SPECIAL_529>",
+    "<SPECIAL_530>",
+    "<SPECIAL_531>",
+    "<SPECIAL_532>",
+    "<SPECIAL_533>",
+    "<SPECIAL_534>",
+    "<SPECIAL_535>",
+    "<SPECIAL_536>",
+    "<SPECIAL_537>",
+    "<SPECIAL_538>",
+    "<SPECIAL_539>",
+    "<SPECIAL_540>",
+    "<SPECIAL_541>",
+    "<SPECIAL_542>",
+    "<SPECIAL_543>",
+    "<SPECIAL_544>",
+    "<SPECIAL_545>",
+    "<SPECIAL_546>",
+    "<SPECIAL_547>",
+    "<SPECIAL_548>",
+    "<SPECIAL_549>",
+    "<SPECIAL_550>",
+    "<SPECIAL_551>",
+    "<SPECIAL_552>",
+    "<SPECIAL_553>",
+    "<SPECIAL_554>",
+    "<SPECIAL_555>",
+    "<SPECIAL_556>",
+    "<SPECIAL_557>",
+    "<SPECIAL_558>",
+    "<SPECIAL_559>",
+    "<SPECIAL_560>",
+    "<SPECIAL_561>",
+    "<SPECIAL_562>",
+    "<SPECIAL_563>",
+    "<SPECIAL_564>",
+    "<SPECIAL_565>",
+    "<SPECIAL_566>",
+    "<SPECIAL_567>",
+    "<SPECIAL_568>",
+    "<SPECIAL_569>",
+    "<SPECIAL_570>",
+    "<SPECIAL_571>",
+    "<SPECIAL_572>",
+    "<SPECIAL_573>",
+    "<SPECIAL_574>",
+    "<SPECIAL_575>",
+    "<SPECIAL_576>",
+    "<SPECIAL_577>",
+    "<SPECIAL_578>",
+    "<SPECIAL_579>",
+    "<SPECIAL_580>",
+    "<SPECIAL_581>",
+    "<SPECIAL_582>",
+    "<SPECIAL_583>",
+    "<SPECIAL_584>",
+    "<SPECIAL_585>",
+    "<SPECIAL_586>",
+    "<SPECIAL_587>",
+    "<SPECIAL_588>",
+    "<SPECIAL_589>",
+    "<SPECIAL_590>",
+    "<SPECIAL_591>",
+    "<SPECIAL_592>",
+    "<SPECIAL_593>",
+    "<SPECIAL_594>",
+    "<SPECIAL_595>",
+    "<SPECIAL_596>",
+    "<SPECIAL_597>",
+    "<SPECIAL_598>",
+    "<SPECIAL_599>",
+    "<SPECIAL_600>",
+    "<SPECIAL_601>",
+    "<SPECIAL_602>",
+    "<SPECIAL_603>",
+    "<SPECIAL_604>",
+    "<SPECIAL_605>",
+    "<SPECIAL_606>",
+    "<SPECIAL_607>",
+    "<SPECIAL_608>",
+    "<SPECIAL_609>",
+    "<SPECIAL_610>",
+    "<SPECIAL_611>",
+    "<SPECIAL_612>",
+    "<SPECIAL_613>",
+    "<SPECIAL_614>",
+    "<SPECIAL_615>",
+    "<SPECIAL_616>",
+    "<SPECIAL_617>",
+    "<SPECIAL_618>",
+    "<SPECIAL_619>",
+    "<SPECIAL_620>",
+    "<SPECIAL_621>",
+    "<SPECIAL_622>",
+    "<SPECIAL_623>",
+    "<SPECIAL_624>",
+    "<SPECIAL_625>",
+    "<SPECIAL_626>",
+    "<SPECIAL_627>",
+    "<SPECIAL_628>",
+    "<SPECIAL_629>",
+    "<SPECIAL_630>",
+    "<SPECIAL_631>",
+    "<SPECIAL_632>",
+    "<SPECIAL_633>",
+    "<SPECIAL_634>",
+    "<SPECIAL_635>",
+    "<SPECIAL_636>",
+    "<SPECIAL_637>",
+    "<SPECIAL_638>",
+    "<SPECIAL_639>",
+    "<SPECIAL_640>",
+    "<SPECIAL_641>",
+    "<SPECIAL_642>",
+    "<SPECIAL_643>",
+    "<SPECIAL_644>",
+    "<SPECIAL_645>",
+    "<SPECIAL_646>",
+    "<SPECIAL_647>",
+    "<SPECIAL_648>",
+    "<SPECIAL_649>",
+    "<SPECIAL_650>",
+    "<SPECIAL_651>",
+    "<SPECIAL_652>",
+    "<SPECIAL_653>",
+    "<SPECIAL_654>",
+    "<SPECIAL_655>",
+    "<SPECIAL_656>",
+    "<SPECIAL_657>",
+    "<SPECIAL_658>",
+    "<SPECIAL_659>",
+    "<SPECIAL_660>",
+    "<SPECIAL_661>",
+    "<SPECIAL_662>",
+    "<SPECIAL_663>",
+    "<SPECIAL_664>",
+    "<SPECIAL_665>",
+    "<SPECIAL_666>",
+    "<SPECIAL_667>",
+    "<SPECIAL_668>",
+    "<SPECIAL_669>",
+    "<SPECIAL_670>",
+    "<SPECIAL_671>",
+    "<SPECIAL_672>",
+    "<SPECIAL_673>",
+    "<SPECIAL_674>",
+    "<SPECIAL_675>",
+    "<SPECIAL_676>",
+    "<SPECIAL_677>",
+    "<SPECIAL_678>",
+    "<SPECIAL_679>",
+    "<SPECIAL_680>",
+    "<SPECIAL_681>",
+    "<SPECIAL_682>",
+    "<SPECIAL_683>",
+    "<SPECIAL_684>",
+    "<SPECIAL_685>",
+    "<SPECIAL_686>",
+    "<SPECIAL_687>",
+    "<SPECIAL_688>",
+    "<SPECIAL_689>",
+    "<SPECIAL_690>",
+    "<SPECIAL_691>",
+    "<SPECIAL_692>",
+    "<SPECIAL_693>",
+    "<SPECIAL_694>",
+    "<SPECIAL_695>",
+    "<SPECIAL_696>",
+    "<SPECIAL_697>",
+    "<SPECIAL_698>",
+    "<SPECIAL_699>",
+    "<SPECIAL_700>",
+    "<SPECIAL_701>",
+    "<SPECIAL_702>",
+    "<SPECIAL_703>",
+    "<SPECIAL_704>",
+    "<SPECIAL_705>",
+    "<SPECIAL_706>",
+    "<SPECIAL_707>",
+    "<SPECIAL_708>",
+    "<SPECIAL_709>",
+    "<SPECIAL_710>",
+    "<SPECIAL_711>",
+    "<SPECIAL_712>",
+    "<SPECIAL_713>",
+    "<SPECIAL_714>",
+    "<SPECIAL_715>",
+    "<SPECIAL_716>",
+    "<SPECIAL_717>",
+    "<SPECIAL_718>",
+    "<SPECIAL_719>",
+    "<SPECIAL_720>",
+    "<SPECIAL_721>",
+    "<SPECIAL_722>",
+    "<SPECIAL_723>",
+    "<SPECIAL_724>",
+    "<SPECIAL_725>",
+    "<SPECIAL_726>",
+    "<SPECIAL_727>",
+    "<SPECIAL_728>",
+    "<SPECIAL_729>",
+    "<SPECIAL_730>",
+    "<SPECIAL_731>",
+    "<SPECIAL_732>",
+    "<SPECIAL_733>",
+    "<SPECIAL_734>",
+    "<SPECIAL_735>",
+    "<SPECIAL_736>",
+    "<SPECIAL_737>",
+    "<SPECIAL_738>",
+    "<SPECIAL_739>",
+    "<SPECIAL_740>",
+    "<SPECIAL_741>",
+    "<SPECIAL_742>",
+    "<SPECIAL_743>",
+    "<SPECIAL_744>",
+    "<SPECIAL_745>",
+    "<SPECIAL_746>",
+    "<SPECIAL_747>",
+    "<SPECIAL_748>",
+    "<SPECIAL_749>",
+    "<SPECIAL_750>",
+    "<SPECIAL_751>",
+    "<SPECIAL_752>",
+    "<SPECIAL_753>",
+    "<SPECIAL_754>",
+    "<SPECIAL_755>",
+    "<SPECIAL_756>",
+    "<SPECIAL_757>",
+    "<SPECIAL_758>",
+    "<SPECIAL_759>",
+    "<SPECIAL_760>",
+    "<SPECIAL_761>",
+    "<SPECIAL_762>",
+    "<SPECIAL_763>",
+    "<SPECIAL_764>",
+    "<SPECIAL_765>",
+    "<SPECIAL_766>",
+    "<SPECIAL_767>",
+    "<SPECIAL_768>",
+    "<SPECIAL_769>",
+    "<SPECIAL_770>",
+    "<SPECIAL_771>",
+    "<SPECIAL_772>",
+    "<SPECIAL_773>",
+    "<SPECIAL_774>",
+    "<SPECIAL_775>",
+    "<SPECIAL_776>",
+    "<SPECIAL_777>",
+    "<SPECIAL_778>",
+    "<SPECIAL_779>",
+    "<SPECIAL_780>",
+    "<SPECIAL_781>",
+    "<SPECIAL_782>",
+    "<SPECIAL_783>",
+    "<SPECIAL_784>",
+    "<SPECIAL_785>",
+    "<SPECIAL_786>",
+    "<SPECIAL_787>",
+    "<SPECIAL_788>",
+    "<SPECIAL_789>",
+    "<SPECIAL_790>",
+    "<SPECIAL_791>",
+    "<SPECIAL_792>",
+    "<SPECIAL_793>",
+    "<SPECIAL_794>",
+    "<SPECIAL_795>",
+    "<SPECIAL_796>",
+    "<SPECIAL_797>",
+    "<SPECIAL_798>",
+    "<SPECIAL_799>",
+    "<SPECIAL_800>",
+    "<SPECIAL_801>",
+    "<SPECIAL_802>",
+    "<SPECIAL_803>",
+    "<SPECIAL_804>",
+    "<SPECIAL_805>",
+    "<SPECIAL_806>",
+    "<SPECIAL_807>",
+    "<SPECIAL_808>",
+    "<SPECIAL_809>",
+    "<SPECIAL_810>",
+    "<SPECIAL_811>",
+    "<SPECIAL_812>",
+    "<SPECIAL_813>",
+    "<SPECIAL_814>",
+    "<SPECIAL_815>",
+    "<SPECIAL_816>",
+    "<SPECIAL_817>",
+    "<SPECIAL_818>",
+    "<SPECIAL_819>",
+    "<SPECIAL_820>",
+    "<SPECIAL_821>",
+    "<SPECIAL_822>",
+    "<SPECIAL_823>",
+    "<SPECIAL_824>",
+    "<SPECIAL_825>",
+    "<SPECIAL_826>",
+    "<SPECIAL_827>",
+    "<SPECIAL_828>",
+    "<SPECIAL_829>",
+    "<SPECIAL_830>",
+    "<SPECIAL_831>",
+    "<SPECIAL_832>",
+    "<SPECIAL_833>",
+    "<SPECIAL_834>",
+    "<SPECIAL_835>",
+    "<SPECIAL_836>",
+    "<SPECIAL_837>",
+    "<SPECIAL_838>",
+    "<SPECIAL_839>",
+    "<SPECIAL_840>",
+    "<SPECIAL_841>",
+    "<SPECIAL_842>",
+    "<SPECIAL_843>",
+    "<SPECIAL_844>",
+    "<SPECIAL_845>",
+    "<SPECIAL_846>",
+    "<SPECIAL_847>",
+    "<SPECIAL_848>",
+    "<SPECIAL_849>",
+    "<SPECIAL_850>",
+    "<SPECIAL_851>",
+    "<SPECIAL_852>",
+    "<SPECIAL_853>",
+    "<SPECIAL_854>",
+    "<SPECIAL_855>",
+    "<SPECIAL_856>",
+    "<SPECIAL_857>",
+    "<SPECIAL_858>",
+    "<SPECIAL_859>",
+    "<SPECIAL_860>",
+    "<SPECIAL_861>",
+    "<SPECIAL_862>",
+    "<SPECIAL_863>",
+    "<SPECIAL_864>",
+    "<SPECIAL_865>",
+    "<SPECIAL_866>",
+    "<SPECIAL_867>",
+    "<SPECIAL_868>",
+    "<SPECIAL_869>",
+    "<SPECIAL_870>",
+    "<SPECIAL_871>",
+    "<SPECIAL_872>",
+    "<SPECIAL_873>",
+    "<SPECIAL_874>",
+    "<SPECIAL_875>",
+    "<SPECIAL_876>",
+    "<SPECIAL_877>",
+    "<SPECIAL_878>",
+    "<SPECIAL_879>",
+    "<SPECIAL_880>",
+    "<SPECIAL_881>",
+    "<SPECIAL_882>",
+    "<SPECIAL_883>",
+    "<SPECIAL_884>",
+    "<SPECIAL_885>",
+    "<SPECIAL_886>",
+    "<SPECIAL_887>",
+    "<SPECIAL_888>",
+    "<SPECIAL_889>",
+    "<SPECIAL_890>",
+    "<SPECIAL_891>",
+    "<SPECIAL_892>",
+    "<SPECIAL_893>",
+    "<SPECIAL_894>",
+    "<SPECIAL_895>",
+    "<SPECIAL_896>",
+    "<SPECIAL_897>",
+    "<SPECIAL_898>",
+    "<SPECIAL_899>",
+    "<SPECIAL_900>",
+    "<SPECIAL_901>",
+    "<SPECIAL_902>",
+    "<SPECIAL_903>",
+    "<SPECIAL_904>",
+    "<SPECIAL_905>",
+    "<SPECIAL_906>",
+    "<SPECIAL_907>",
+    "<SPECIAL_908>",
+    "<SPECIAL_909>",
+    "<SPECIAL_910>",
+    "<SPECIAL_911>",
+    "<SPECIAL_912>",
+    "<SPECIAL_913>",
+    "<SPECIAL_914>",
+    "<SPECIAL_915>",
+    "<SPECIAL_916>",
+    "<SPECIAL_917>",
+    "<SPECIAL_918>",
+    "<SPECIAL_919>",
+    "<SPECIAL_920>",
+    "<SPECIAL_921>",
+    "<SPECIAL_922>",
+    "<SPECIAL_923>",
+    "<SPECIAL_924>",
+    "<SPECIAL_925>",
+    "<SPECIAL_926>",
+    "<SPECIAL_927>",
+    "<SPECIAL_928>",
+    "<SPECIAL_929>",
+    "<SPECIAL_930>",
+    "<SPECIAL_931>",
+    "<SPECIAL_932>",
+    "<SPECIAL_933>",
+    "<SPECIAL_934>",
+    "<SPECIAL_935>",
+    "<SPECIAL_936>",
+    "<SPECIAL_937>",
+    "<SPECIAL_938>",
+    "<SPECIAL_939>",
+    "<SPECIAL_940>",
+    "<SPECIAL_941>",
+    "<SPECIAL_942>",
+    "<SPECIAL_943>",
+    "<SPECIAL_944>",
+    "<SPECIAL_945>",
+    "<SPECIAL_946>",
+    "<SPECIAL_947>",
+    "<SPECIAL_948>",
+    "<SPECIAL_949>",
+    "<SPECIAL_950>",
+    "<SPECIAL_951>",
+    "<SPECIAL_952>",
+    "<SPECIAL_953>",
+    "<SPECIAL_954>",
+    "<SPECIAL_955>",
+    "<SPECIAL_956>",
+    "<SPECIAL_957>",
+    "<SPECIAL_958>",
+    "<SPECIAL_959>",
+    "<SPECIAL_960>",
+    "<SPECIAL_961>",
+    "<SPECIAL_962>",
+    "<SPECIAL_963>",
+    "<SPECIAL_964>",
+    "<SPECIAL_965>",
+    "<SPECIAL_966>",
+    "<SPECIAL_967>",
+    "<SPECIAL_968>",
+    "<SPECIAL_969>",
+    "<SPECIAL_970>",
+    "<SPECIAL_971>",
+    "<SPECIAL_972>",
+    "<SPECIAL_973>",
+    "<SPECIAL_974>",
+    "<SPECIAL_975>",
+    "<SPECIAL_976>",
+    "<SPECIAL_977>",
+    "<SPECIAL_978>",
+    "<SPECIAL_979>",
+    "<SPECIAL_980>",
+    "<SPECIAL_981>",
+    "<SPECIAL_982>",
+    "<SPECIAL_983>",
+    "<SPECIAL_984>",
+    "<SPECIAL_985>",
+    "<SPECIAL_986>",
+    "<SPECIAL_987>",
+    "<SPECIAL_988>",
+    "<SPECIAL_989>",
+    "<SPECIAL_990>",
+    "<SPECIAL_991>",
+    "<SPECIAL_992>",
+    "<SPECIAL_993>",
+    "<SPECIAL_994>",
+    "<SPECIAL_995>",
+    "<SPECIAL_996>",
+    "<SPECIAL_997>",
+    "<SPECIAL_998>",
+    "<SPECIAL_999>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

Mistral-Small-24B-3.1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9783353ab8f26d0949ac570b4cb747d520b8b638d7fb37d525fd382b21868e
+size 17078136

Phi-4-GPTQ/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Phi-4-GPTQ/README.md

@@ -0,0 +1,44 @@
+---
+license: mit
+language:
+- en
+base_model:
+- microsoft/phi-4
+---
+# Model Card for Microsoft-phi-4-Instruct-AutoRound-GPTQ-4bit
+
+## Model Overview
+
+**Model Name**: Microsoft-phi-4-Instruct-AutoRound-GPTQ-4bit  
+**Model Type**: Instruction-tuned, Quantized GPT-4-based language model  
+**Quantization**: GPTQ 4-bit  
+**Author**: Satwik11  
+**Hosted on**: Hugging Face
+
+## Description
+
+This model is a quantized version of the Microsoft phi-4 Instruct model, designed to deliver high performance while maintaining computational efficiency. By leveraging the GPTQ 4-bit quantization method, it enables deployment in environments with limited resources while retaining a high degree of accuracy.
+
+The model is fine-tuned for instruction-following tasks, making it ideal for applications in conversational AI, question answering, and general-purpose text generation.
+
+## Key Features
+
+- **Instruction-tuned**: Fine-tuned to follow human-like instructions effectively.
+- **Quantized for Efficiency**: Uses GPTQ 4-bit quantization to reduce memory requirements and inference latency.
+- **Pre-trained Base**: Built on the Microsoft phi-4 framework, ensuring state-of-the-art performance on NLP tasks.
+
+## Use Cases
+
+- Chatbots and virtual assistants.
+- Summarization and content generation.
+- Research and educational applications.
+- Semantic search and knowledge retrieval.
+
+## Model Details
+
+### Architecture
+
+- **Base Model**: Microsoft phi-4  
+- **Quantization Technique**: GPTQ (4-bit)  
+- **Language**: English  
+- **Training Objective**: Instruction-following fine-tuning

Phi-4-GPTQ/config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "microsoft/phi-4",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {},
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100257,
+  "quantization_config": {
+    "amp": true,
+    "autoround_version": "0.4.4",
+    "batch_size": 8,
+    "bits": 4,
+    "damp_percent": 0.01,
+    "data_type": "int",
+    "desc_act": false,
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "gradient_accumulate_steps": 1,
+    "group_size": 128,
+    "iters": 256,
+    "low_gpu_mem_usage": false,
+    "lr": 0.00390625,
+    "minmax_lr": 0.00390625,
+    "nsamples": 128,
+    "quant_method": "gptq",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "sym": true,
+    "to_quant_block_names": null,
+    "true_sequential": false
+  },
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 100352
+}

Phi-4-GPTQ/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100257,
+  "eos_token_id": [
+    100257,
+    100265
+  ],
+  "transformers_version": "4.47.1"
+}

Phi-4-GPTQ/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609fb22f6b382707a5ada5ce16351612c581aafac62ed0e7fbb7900b5bd47c7d
+size 4960209984

Phi-4-GPTQ/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72eb5170c5effca559be040bde2ee2124a4a796af7c1ee2beba530d1bfdde1fc
+size 4183219664

Phi-4-GPTQ/model.safetensors.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 9143347200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_up_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.qkv_proj.g_idx": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.qkv_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.qkv_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.qkv_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.g_idx": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.qkv_proj.scales": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

Phi-4-GPTQ/quantize_config.json

@@ -0,0 +1,25 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 2048,
+  "batch_size": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 0.00390625,
+  "minmax_lr": 0.00390625,
+  "gradient_accumulate_steps": 1,
+  "iters": 256,
+  "amp": true,
+  "nsamples": 128,
+  "low_gpu_mem_usage": false,
+  "to_quant_block_names": null,
+  "enable_norm_bias_tuning": false,
+  "autoround_version": "0.4.4",
+  "quant_method": "gptq",
+  "desc_act": false,
+  "true_sequential": false,
+  "damp_percent": 0.01
+}

Phi-4-GPTQ/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

Phi-4-GPTQ/tokenizer_config.json

@@ -0,0 +1,782 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}