Upload all model with 8 experts (6.6B params)
Browse files- .gitattributes +1 -0
- README.md +395 -0
- chat_template.jinja +331 -0
- citation.json +9 -0
- config.json +123 -0
- expert_mapping.json +242 -0
- generation_config.json +10 -0
- model-00001-of-00008.safetensors +3 -0
- model-00002-of-00008.safetensors +3 -0
- model-00003-of-00008.safetensors +3 -0
- model-00004-of-00008.safetensors +3 -0
- model-00005-of-00008.safetensors +3 -0
- model-00006-of-00008.safetensors +3 -0
- model-00007-of-00008.safetensors +3 -0
- model-00008-of-00008.safetensors +3 -0
- model.safetensors.index.json +419 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +183 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,395 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- mixture-of-experts
|
| 10 |
+
- moe
|
| 11 |
+
- expert-pruning
|
| 12 |
+
- gpt-oss
|
| 13 |
+
- openai
|
| 14 |
+
- reasoning
|
| 15 |
+
- all
|
| 16 |
+
- specialized
|
| 17 |
+
- efficient
|
| 18 |
+
- transformer
|
| 19 |
+
- causal-lm
|
| 20 |
+
- text-generation
|
| 21 |
+
- pytorch
|
| 22 |
+
- pruned-model
|
| 23 |
+
- domain-specific
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
# All GPT-OSS Model (8 Experts)
|
| 27 |
+
|
| 28 |
+
**Project**: https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/
|
| 29 |
+
|
| 30 |
+
<div align="center">
|
| 31 |
+
|
| 32 |
+
### 👥 Follow the Authors
|
| 33 |
+
|
| 34 |
+
**Aman Priyanshu**
|
| 35 |
+
[](https://www.linkedin.com/in/aman-priyanshu/)
|
| 36 |
+
[](https://x.com/AmanPriyanshu6)
|
| 37 |
+
[](https://amanpriyanshu.github.io/)
|
| 38 |
+
|
| 39 |
+
**Supriti Vijay**
|
| 40 |
+
[](https://www.linkedin.com/in/supriti-vijay/)
|
| 41 |
+
[](https://x.com/SupritiVijay)
|
| 42 |
+
[](https://supritivijay.github.io/)
|
| 43 |
+
|
| 44 |
+
</div>
|
| 45 |
+
|
| 46 |
+
## Introduction
|
| 47 |
+
|
| 48 |
+
This is a pruned variant of OpenAI's GPT-OSS-20B model, reduced to 8 experts per layer based on activation patterns from the [AmanPriyanshu/GPT-OSS-20B MoE Expert Activations dataset](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations). We analyzed router decisions across evaluation benchmarks to identify and retain experts most relevant for all tasks.
|
| 49 |
+
|
| 50 |
+
**⚠️ Experimental Model**: This is an experimental pruned model that may not work well - check the [examples below](#model-examples) to see if the outputs meet your needs before use.
|
| 51 |
+
|
| 52 |
+
This pruning approach reduces the model size while attempting to preserve performance on the target domain.
|
| 53 |
+
|
| 54 |
+
## Model Architecture & Statistics
|
| 55 |
+
|
| 56 |
+
| Metric | Value |
|
| 57 |
+
|--------|-------|
|
| 58 |
+
| **Base Model** | openai/gpt-oss-20b |
|
| 59 |
+
| **Architecture** | Mixture-of-Experts Transformer |
|
| 60 |
+
| **Total Parameters** | ~6.6B (pruned from 21B) |
|
| 61 |
+
| **Original Experts per Layer** | 32 |
|
| 62 |
+
| **Pruned Experts per Layer** | 8 |
|
| 63 |
+
| **Layers** | 24 |
|
| 64 |
+
| **Top-k Routing** | 4 |
|
| 65 |
+
| **Context Length** | 128K tokens |
|
| 66 |
+
| **Attention Heads** | 64 (Query), 8 (Key-Value) |
|
| 67 |
+
| **Residual Dimension** | 2880 |
|
| 68 |
+
| **Attention Pattern** | Alternating dense & sliding window (128 tokens) |
|
| 69 |
+
| **Positional Encoding** | RoPE (Rotary Position Embedding) |
|
| 70 |
+
| **Normalization** | RMSNorm |
|
| 71 |
+
| **Precision** | BF16 |
|
| 72 |
+
| **License** | Apache 2.0 |
|
| 73 |
+
| **Specialization** | All |
|
| 74 |
+
|
| 75 |
+
## Pruning Methodology
|
| 76 |
+
|
| 77 |
+
### What is Expert Pruning?
|
| 78 |
+
Mixture-of-Experts models contain multiple specialized sub-networks (experts) per layer. During inference, only a subset of experts are activated for each token. Expert pruning involves:
|
| 79 |
+
|
| 80 |
+
1. **Analyzing Usage Patterns**: Tracking which experts activate most frequently for specific tasks
|
| 81 |
+
2. **Removing Underutilized Experts**: Discarding experts with low activation rates for the target domain
|
| 82 |
+
3. **Preserving Router Functionality**: Maintaining the routing mechanism with fewer available experts
|
| 83 |
+
|
| 84 |
+
### Our Approach
|
| 85 |
+
- **Data-Driven Selection**: Used activation patterns from all evaluation tasks
|
| 86 |
+
- **Systematic Reduction**: Reduced from 32 to 8 experts per layer
|
| 87 |
+
- **No Retraining**: Direct removal without additional training steps
|
| 88 |
+
|
| 89 |
+
## Performance & Applications
|
| 90 |
+
|
| 91 |
+
### Pruning Benefits
|
| 92 |
+
- **Smaller Memory Footprint**: 25.0% of original expert parameters
|
| 93 |
+
- **Reduced Computational Load**: Fewer routing decisions during inference
|
| 94 |
+
- **Focused Capabilities**: Retains experts relevant to all tasks
|
| 95 |
+
|
| 96 |
+
### Use Cases
|
| 97 |
+
- **Speculative Decoding**: Draft model for full GPT-OSS-20B
|
| 98 |
+
- **Resource-Constrained Deployment**: Edge devices, mobile applications
|
| 99 |
+
- **Research**: Study expert specialization in MoE models
|
| 100 |
+
- **Fine-tuning**: Smaller base model for domain adaptation
|
| 101 |
+
|
| 102 |
+
*Note: Performance may vary depending on how well the pruned experts match your specific use case.*
|
| 103 |
+
|
| 104 |
+
## Motivation & Expert Selection
|
| 105 |
+
|
| 106 |
+
This general-purpose model maintains broad capabilities across all domains while significantly reducing computational requirements. It preserves the essential routing patterns discovered across our comprehensive analysis of diverse evaluation benchmarks including GPQA, MMLU, SORRY-Bench, and Tulu3 datasets.
|
| 107 |
+
|
| 108 |
+
The expert selection process utilized our comprehensive analysis of router activation patterns across multiple evaluation benchmarks:
|
| 109 |
+
|
| 110 |
+
- **GPQA**: Graduate-level questions in physics, chemistry, biology (Diamond & Expert subsets)
|
| 111 |
+
- **MMLU/MMLU-Pro**: Comprehensive knowledge across 57+ subjects including science, medicine, law
|
| 112 |
+
- **SORRY-Bench**: Safety evaluation across harmful content categories
|
| 113 |
+
- **Tulu3**: Persona-driven instruction following with verifiable constraints
|
| 114 |
+
- **Polyglot-or-Not**: Multilingual factual completion tasks
|
| 115 |
+
|
| 116 |
+
By identifying experts that consistently activated for all tasks, we created this specialized model that maintains domain expertise while significantly reducing computational requirements from 32 to 8 experts per layer.
|
| 117 |
+
|
| 118 |
+
## Dataset & Analysis Foundation
|
| 119 |
+
|
| 120 |
+
This model is based on analysis from the **GPT-OSS-20B MoE Expert Activations dataset** available at:
|
| 121 |
+
🔗 **https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations**
|
| 122 |
+
|
| 123 |
+
The dataset contains router activation patterns from OpenAI's GPT-OSS-20B model across diverse evaluation benchmarks, enabling the creation of these domain-optimized models through systematic expert pruning.
|
| 124 |
+
|
| 125 |
+
### Pruning Methodology
|
| 126 |
+
Our approach involves:
|
| 127 |
+
1. **Activation Analysis**: Comprehensive evaluation of expert usage patterns across domain-specific tasks
|
| 128 |
+
2. **Expert Ranking**: Identification of the most frequently activated experts for target domains
|
| 129 |
+
3. **Systematic Pruning**: Reduction from 32 to 8 experts while preserving router functionality
|
| 130 |
+
4. **Quality Validation**: Testing to ensure maintained performance on target tasks
|
| 131 |
+
|
| 132 |
+
*This is a direct pruning approach - no additional training was performed. The model inherits all capabilities from the original GPT-OSS-20B with focused expert selection.*
|
| 133 |
+
|
| 134 |
+
## Usage
|
| 135 |
+
|
| 136 |
+
### CPU Inference
|
| 137 |
+
|
| 138 |
+
```python
|
| 139 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 140 |
+
import torch
|
| 141 |
+
|
| 142 |
+
# Load the specialized model on CPU
|
| 143 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 144 |
+
"AmanPriyanshu/gpt-oss-6.6b-specialized-all-pruned-moe-only-8-experts",
|
| 145 |
+
torch_dtype=torch.bfloat16,
|
| 146 |
+
device_map="cpu",
|
| 147 |
+
trust_remote_code=True
|
| 148 |
+
)
|
| 149 |
+
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-6.6b-specialized-all-pruned-moe-only-8-experts")
|
| 150 |
+
|
| 151 |
+
# Generate with the model
|
| 152 |
+
messages = [
|
| 153 |
+
{"role": "user", "content": "What is artificial intelligence and how does it work?"}
|
| 154 |
+
]
|
| 155 |
+
|
| 156 |
+
inputs = tokenizer.apply_chat_template(
|
| 157 |
+
messages,
|
| 158 |
+
add_generation_prompt=True,
|
| 159 |
+
return_tensors="pt",
|
| 160 |
+
return_dict=True,
|
| 161 |
+
reasoning_effort="medium"
|
| 162 |
+
)
|
| 163 |
+
|
| 164 |
+
# Ensure inputs are on the same device as model
|
| 165 |
+
inputs = {k: v.to(model.device) for k, v in inputs.items()}
|
| 166 |
+
|
| 167 |
+
outputs = model.generate(
|
| 168 |
+
**inputs,
|
| 169 |
+
max_new_tokens=512,
|
| 170 |
+
do_sample=True,
|
| 171 |
+
temperature=0.1,
|
| 172 |
+
top_p=0.9,
|
| 173 |
+
pad_token_id=tokenizer.eos_token_id,
|
| 174 |
+
eos_token_id=tokenizer.eos_token_id
|
| 175 |
+
)
|
| 176 |
+
|
| 177 |
+
# Decode only the generated part
|
| 178 |
+
input_length = inputs['input_ids'].shape[1]
|
| 179 |
+
response_tokens = outputs[0][input_length:]
|
| 180 |
+
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
|
| 181 |
+
print(response)
|
| 182 |
+
```
|
| 183 |
+
|
| 184 |
+
### Apple Silicon (MPS) Inference
|
| 185 |
+
|
| 186 |
+
```python
|
| 187 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 188 |
+
import torch
|
| 189 |
+
|
| 190 |
+
# Check MPS availability and load model
|
| 191 |
+
device = "mps" if torch.backends.mps.is_available() else "cpu"
|
| 192 |
+
|
| 193 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 194 |
+
"AmanPriyanshu/gpt-oss-6.6b-specialized-all-pruned-moe-only-8-experts",
|
| 195 |
+
torch_dtype=torch.float16, # Better MPS compatibility
|
| 196 |
+
device_map=device,
|
| 197 |
+
trust_remote_code=True,
|
| 198 |
+
low_cpu_mem_usage=True
|
| 199 |
+
)
|
| 200 |
+
tokenizer = AutoTokenizer.from_pretrained("AmanPriyanshu/gpt-oss-6.6b-specialized-all-pruned-moe-only-8-experts")
|
| 201 |
+
|
| 202 |
+
# Generate with the model
|
| 203 |
+
messages = [
|
| 204 |
+
{"role": "user", "content": "What is artificial intelligence and how does it work?"}
|
| 205 |
+
]
|
| 206 |
+
|
| 207 |
+
inputs = tokenizer.apply_chat_template(
|
| 208 |
+
messages,
|
| 209 |
+
add_generation_prompt=True,
|
| 210 |
+
return_tensors="pt",
|
| 211 |
+
return_dict=True,
|
| 212 |
+
reasoning_effort="medium"
|
| 213 |
+
)
|
| 214 |
+
|
| 215 |
+
# Move inputs to model device
|
| 216 |
+
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
|
| 217 |
+
|
| 218 |
+
# Use torch.no_grad for MPS stability
|
| 219 |
+
with torch.no_grad():
|
| 220 |
+
outputs = model.generate(
|
| 221 |
+
**inputs,
|
| 222 |
+
max_new_tokens=512,
|
| 223 |
+
do_sample=True,
|
| 224 |
+
temperature=0.1,
|
| 225 |
+
top_p=0.9,
|
| 226 |
+
pad_token_id=tokenizer.eos_token_id,
|
| 227 |
+
eos_token_id=tokenizer.eos_token_id,
|
| 228 |
+
use_cache=True
|
| 229 |
+
)
|
| 230 |
+
|
| 231 |
+
# Decode only the generated part
|
| 232 |
+
input_length = inputs['input_ids'].shape[1]
|
| 233 |
+
response_tokens = outputs[0][input_length:]
|
| 234 |
+
response = tokenizer.decode(response_tokens, skip_special_tokens=True)
|
| 235 |
+
print(response)
|
| 236 |
+
```
|
| 237 |
+
|
| 238 |
+
### GPU Inference
|
| 239 |
+
|
| 240 |
+
For CUDA GPU inference, the models work with minimal modifications from the CPU example above. Simply change:
|
| 241 |
+
```python
|
| 242 |
+
device_map="auto" # Will automatically use GPU if available
|
| 243 |
+
torch_dtype=torch.bfloat16 # or torch.float16
|
| 244 |
+
```
|
| 245 |
+
|
| 246 |
+
## Model Examples
|
| 247 |
+
|
| 248 |
+
The following examples demonstrate the model's performance on all tasks:
|
| 249 |
+
|
| 250 |
+
### Example 1
|
| 251 |
+
**Question:** What is artificial intelligence and how does it work?
|
| 252 |
+
|
| 253 |
+
**Response:**
|
| 254 |
+
```
|
| 255 |
+
<|channel|>analysis<|message|>Need explain definition and workings.<|end|><|start|>assistant<|channel|>final<|message|>**What is Artificial Intelligence?**
|
| 256 |
+
|
| 257 |
+
Artificial Intelligence (AI) is a computer‑based system that can understand, reason, and act in a way that is similar to a human mind. In short, it is a machine that can “see” and “think” about a world of data, and it can learn, adapt, and improve over time.
|
| 258 |
+
|
| 259 |
+
---
|
| 260 |
+
|
| 261 |
+
### 1. The core idea
|
| 262 |
+
|
| 263 |
+
* **Data** – AI starts with a collection of facts, facts, and patterns. These facts can be text, numbers, images, audio, or even the “rules” that govern a game or a language.
|
| 264 |
+
* **Pattern‑recognance** – The system looks for the hidden structure in the data. It finds that two words are often used together, that a picture has a colour that is usually associated with a certain emotion, that a sentence is a likely answer to a question.
|
| 265 |
+
* **Inference** – Once a pattern is known, the system can guess what is true. It can predict, it can decide, it can “solve” a problem.
|
| 266 |
+
* **Learning** – The system can learn from the data it has, and from new data it receives. It can learn from a set of rules (called *training*), and it can learn from a set of random data (called *experience*).
|
| 267 |
+
* **Action** – Finally, the system can act. It can produce a text, a picture, a code, a recommendation, or a decision that it can be useful for a human.
|
| 268 |
+
|
| 269 |
+
---
|
| 270 |
+
|
| 271 |
+
### 2. How it works – the “layers” of a typical AI system
|
| 272 |
+
|
| 273 |
+
| **Input** | The system receives a set of data (text, image, audio, etc.)
|
| 274 |
+
| **Pre‑processing** | The data is cleaned, normalised, and split into a small set of features (e.g., *token* for a word, *pixel* for an image).
|
| 275 |
+
| **Pattern‑recognance** | The system uses a *prob‑based* or *frequency‑based* algorithm to find the hidden structure. The most common approach is *deep learning* (e.g., a convolutional neural‑network that learns a set of features from the data).
|
| 276 |
+
| **Inference** | The system uses a *decision‑tree* (e.g., a *branch‑tree* or *prob‑based* rule) to decide which is
|
| 277 |
+
```
|
| 278 |
+
|
| 279 |
+
---
|
| 280 |
+
|
| 281 |
+
### Example 2
|
| 282 |
+
**Question:** Explain Einstein's theory of relativity in simple terms.
|
| 283 |
+
|
| 284 |
+
**Response:**
|
| 285 |
+
```
|
| 286 |
+
<|channel|>analysis<|message|>Need to explain Einstein's theory of relatativity simply. Provide analogies, mention relatational vs. non-? Provide simple explanation.<|end|><|start|>assistant<|channel|>final<|message|>**Einstein’s Theory of Relativity – in plain words**
|
| 287 |
+
|
| 288 |
+
---
|
| 289 |
+
|
| 290 |
+
### 1. What is the problem?
|
| 291 |
+
|
| 292 |
+
Imagine a **plane** that is moving in a straight line.
|
| 293 |
+
If you look at the plane from the left side, you see a **point** that is on the right side of the plane.
|
| 294 |
+
If you look from the right side, you see a point that is on the left side of the plane.
|
| 295 |
+
|
| 296 |
+
The question is: **Which point is real?**
|
| 297 |
+
If the plane is moving, the point can’t exist on the same side of the plane.
|
| 298 |
+
If the plane is stationary, the point is real on the same side.
|
| 299 |
+
|
| 300 |
+
In physics, the **plane** is a *space* (the universe), and the **points** are *particles* (atoms, molecules, etc.).
|
| 301 |
+
The problem is: **How do we describe the motion of particles in a way that is consistent with the universe?**
|
| 302 |
+
|
| 303 |
+
---
|
| 304 |
+
|
| 305 |
+
### 2. What Einstein said?
|
| 306 |
+
|
| 307 |
+
Einstein’s idea is that the **universe is a “one‑world”** that is *continuous* in a single line.
|
| 308 |
+
If we treat the universe as a single line, the **particles are just points on that line**.
|
| 309 |
+
When a particle moves, it **shifts** along that line, but the line itself never changes.
|
| 310 |
+
|
| 311 |
+
In other words, **the universe is a fixed line; particles are points that move along that line.**
|
| 312 |
+
The *key* is that the **un universe is not moving** – only the particles move.
|
| 313 |
+
|
| 314 |
+
---
|
| 315 |
+
|
| 316 |
+
### 3. How does this work?
|
| 317 |
+
|
| 318 |
+
1. **Define a line (the universe)**
|
| 319 |
+
Let’s call the line **\(�space\)**.
|
| 320 |
+
It is a fixed length: **\(�space = 1\)** (you can choose any other length, but the length is fixed).
|
| 321 |
+
|
| 322 |
+
2. **Define a point (a particle)**
|
| 323 |
+
A particle is a point on that line.
|
| 324 |
+
If a particle is at point **\(P\)**, then the particle’s position is **\(P = 1\)** (the same point on the line).
|
| 325 |
+
|
| 326 |
+
3. **Move a particle**
|
| 327 |
+
If a particle moves, it changes its position **\(P\)**.
|
| 328 |
+
The particle’s new position is **\(P'** (a
|
| 329 |
+
```
|
| 330 |
+
|
| 331 |
+
---
|
| 332 |
+
|
| 333 |
+
### Example 3
|
| 334 |
+
**Question:** How does democracy function in modern governments?
|
| 335 |
+
|
| 336 |
+
**Response:**
|
| 337 |
+
```
|
| 338 |
+
<|channel|>analysis<|message|>Need to explain how democracy functions in modern governments. Provide overview, principles, institutions, checks.<|end|><|start|>assistant<|channel|>final<|message|>**How does democracy function in modern governments?**
|
| 339 |
+
Dem‑or‑**(** “dem” = “people” + “rule”)** is a system that lets the people of a state have a say in the policy, law, and public life. In modern governments, democracy is not a single set of rules; it is a mix of institutions, norms, and mechanisms that keep the power of the people in the decision‑making process. Below is a step‑by‑step explanation of how democracy works in contemporary states, from the day‑to‑day of the government, the judiciary, the economy, and the civil‑society.
|
| 340 |
+
|
| 341 |
+
---
|
| 342 |
+
|
| 343 |
+
## 1. The Core Principles
|
| 344 |
+
|
| 345 |
+
| **Representative** – The people elect a person or a group that represents them.
|
| 346 |
+
| **Accountable** – The elected officials must be answerable to the public, and can be removed or replaced.
|
| 347 |
+
| **Participative** – Citizens can vote, speak, and influence policy through public debate, petitions, and civic‑action.
|
| 348 |
+
| **Legistic** – The laws are made by the people, and the courts interpret them in a neutral way.
|
| 349 |
+
| **Pluralist** – A variety of views, parties, and minorities are allowed to exist.
|
| 350 |
+
|
| 351 |
+
These principles are the foundation of a democratic state.
|
| 352 |
+
|
| 353 |
+
---
|
| 354 |
+
|
| 355 |
+
## 2. The Institutions that Make Democracy Work
|
| 356 |
+
|
| 357 |
+
| **Parpar‑** – The parliament (or legislature) is the main body that makes laws.
|
| 358 |
+
| **Elect‑** – The electoral system (ball‑counting, polling, etc.) is the way to choose the leaders.
|
| 359 |
+
| **Jud‑** – The judiciary is the independent body that interpre‑s the laws and protects the rights of the people.
|
| 360 |
+
| **C‑** – Civil‑soc‑ (civil‑soc‑) is the body that can hold the power of the people in the public debate.
|
| 361 |
+
| **C‑** – The civil‑soc‑ (civil‑soc‑) is the body that can hold the power of the people in the public debate.
|
| 362 |
+
|
| 363 |
+
---
|
| 364 |
+
|
| 365 |
+
## 3. How Democracy Works in the Day‑to‑Day
|
| 366 |
+
|
| 367 |
+
### 3.1 Elections
|
| 368 |
+
|
| 369 |
+
| **Ball‑** – The people vote for the candidates.
|
| 370 |
+
| **Vote‑** – The vote is counted, and the candidate with the majority is
|
| 371 |
+
```
|
| 372 |
+
|
| 373 |
+
---
|
| 374 |
+
|
| 375 |
+
## Citation
|
| 376 |
+
|
| 377 |
+
If you use this model in your research, please cite:
|
| 378 |
+
|
| 379 |
+
```bibtex
|
| 380 |
+
@misc{priyanshu2025gptoss,
|
| 381 |
+
title={{GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models}},
|
| 382 |
+
author={Priyanshu, Aman and Vijay, Supriti},
|
| 383 |
+
year={2025},
|
| 384 |
+
howpublished={\url{https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/}},
|
| 385 |
+
note={Interactive analysis tool for expert activation patterns in MoE architectures}
|
| 386 |
+
}
|
| 387 |
+
```
|
| 388 |
+
|
| 389 |
+
## References & Resources
|
| 390 |
+
|
| 391 |
+
- **Original Model**: [OpenAI GPT-OSS Model Card](https://openai.com/index/introducing-gpt-oss/)
|
| 392 |
+
- **Model Hub**: [GPT-OSS-20B on Hugging Face](https://huggingface.co/openai/gpt-oss-20b)
|
| 393 |
+
- **Expert Analysis Dataset**: [GPT-OSS-20B MoE Expert Activations](https://huggingface.co/datasets/AmanPriyanshu/GPT-OSS-20B-MoE-expert-activations)
|
| 394 |
+
- **Project Page**: [GPT-OSS MoE Expert Fingerprinting](https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/)
|
| 395 |
+
- **GitHub Repository**: [OpenAI GPT-OSS](https://github.com/openai/gpt-oss)
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,331 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{#-
|
| 2 |
+
In addition to the normal inputs of `messages` and `tools`, this template also accepts the
|
| 3 |
+
following kwargs:
|
| 4 |
+
- "builtin_tools": A list, can contain "browser" and/or "python".
|
| 5 |
+
- "model_identity": A string that optionally describes the model identity.
|
| 6 |
+
- "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
|
| 7 |
+
#}
|
| 8 |
+
|
| 9 |
+
{#- Tool Definition Rendering ============================================== #}
|
| 10 |
+
{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
|
| 11 |
+
{%- if param_spec.type == "array" -%}
|
| 12 |
+
{%- if param_spec['items'] -%}
|
| 13 |
+
{%- if param_spec['items']['type'] == "string" -%}
|
| 14 |
+
{{- "string[]" }}
|
| 15 |
+
{%- elif param_spec['items']['type'] == "number" -%}
|
| 16 |
+
{{- "number[]" }}
|
| 17 |
+
{%- elif param_spec['items']['type'] == "integer" -%}
|
| 18 |
+
{{- "number[]" }}
|
| 19 |
+
{%- elif param_spec['items']['type'] == "boolean" -%}
|
| 20 |
+
{{- "boolean[]" }}
|
| 21 |
+
{%- else -%}
|
| 22 |
+
{%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
|
| 23 |
+
{%- if inner_type == "object | object" or inner_type|length > 50 -%}
|
| 24 |
+
{{- "any[]" }}
|
| 25 |
+
{%- else -%}
|
| 26 |
+
{{- inner_type + "[]" }}
|
| 27 |
+
{%- endif -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- if param_spec.nullable -%}
|
| 30 |
+
{{- " | null" }}
|
| 31 |
+
{%- endif -%}
|
| 32 |
+
{%- else -%}
|
| 33 |
+
{{- "any[]" }}
|
| 34 |
+
{%- if param_spec.nullable -%}
|
| 35 |
+
{{- " | null" }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endif -%}
|
| 38 |
+
{%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
|
| 39 |
+
{#- Handle array of types like ["object", "object"] from Union[dict, list] #}
|
| 40 |
+
{%- if param_spec.type | length > 1 -%}
|
| 41 |
+
{{- param_spec.type | join(" | ") }}
|
| 42 |
+
{%- else -%}
|
| 43 |
+
{{- param_spec.type[0] }}
|
| 44 |
+
{%- endif -%}
|
| 45 |
+
{%- elif param_spec.oneOf -%}
|
| 46 |
+
{#- Handle oneOf schemas - check for complex unions and fallback to any #}
|
| 47 |
+
{%- set has_object_variants = false -%}
|
| 48 |
+
{%- for variant in param_spec.oneOf -%}
|
| 49 |
+
{%- if variant.type == "object" -%}
|
| 50 |
+
{%- set has_object_variants = true -%}
|
| 51 |
+
{%- endif -%}
|
| 52 |
+
{%- endfor -%}
|
| 53 |
+
{%- if has_object_variants and param_spec.oneOf|length > 1 -%}
|
| 54 |
+
{{- "any" }}
|
| 55 |
+
{%- else -%}
|
| 56 |
+
{%- for variant in param_spec.oneOf -%}
|
| 57 |
+
{{- render_typescript_type(variant, required_params) -}}
|
| 58 |
+
{%- if variant.description %}
|
| 59 |
+
{{- "// " + variant.description }}
|
| 60 |
+
{%- endif -%}
|
| 61 |
+
{%- if variant.default is defined %}
|
| 62 |
+
{{ "// default: " + variant.default|tojson }}
|
| 63 |
+
{%- endif -%}
|
| 64 |
+
{%- if not loop.last %}
|
| 65 |
+
{{- " | " }}
|
| 66 |
+
{% endif -%}
|
| 67 |
+
{%- endfor -%}
|
| 68 |
+
{%- endif -%}
|
| 69 |
+
{%- elif param_spec.type == "string" -%}
|
| 70 |
+
{%- if param_spec.enum -%}
|
| 71 |
+
{{- '"' + param_spec.enum|join('" | "') + '"' -}}
|
| 72 |
+
{%- else -%}
|
| 73 |
+
{{- "string" }}
|
| 74 |
+
{%- if param_spec.nullable %}
|
| 75 |
+
{{- " | null" }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
{%- endif -%}
|
| 78 |
+
{%- elif param_spec.type == "number" -%}
|
| 79 |
+
{{- "number" }}
|
| 80 |
+
{%- elif param_spec.type == "integer" -%}
|
| 81 |
+
{{- "number" }}
|
| 82 |
+
{%- elif param_spec.type == "boolean" -%}
|
| 83 |
+
{{- "boolean" }}
|
| 84 |
+
|
| 85 |
+
{%- elif param_spec.type == "object" -%}
|
| 86 |
+
{%- if param_spec.properties -%}
|
| 87 |
+
{{- "{\n" }}
|
| 88 |
+
{%- for prop_name, prop_spec in param_spec.properties.items() -%}
|
| 89 |
+
{{- prop_name -}}
|
| 90 |
+
{%- if prop_name not in (param_spec.required or []) -%}
|
| 91 |
+
{{- "?" }}
|
| 92 |
+
{%- endif -%}
|
| 93 |
+
{{- ": " }}
|
| 94 |
+
{{ render_typescript_type(prop_spec, param_spec.required or []) }}
|
| 95 |
+
{%- if not loop.last -%}
|
| 96 |
+
{{-", " }}
|
| 97 |
+
{%- endif -%}
|
| 98 |
+
{%- endfor -%}
|
| 99 |
+
{{- "}" }}
|
| 100 |
+
{%- else -%}
|
| 101 |
+
{{- "object" }}
|
| 102 |
+
{%- endif -%}
|
| 103 |
+
{%- else -%}
|
| 104 |
+
{{- "any" }}
|
| 105 |
+
{%- endif -%}
|
| 106 |
+
{%- endmacro -%}
|
| 107 |
+
|
| 108 |
+
{%- macro render_tool_namespace(namespace_name, tools) -%}
|
| 109 |
+
{{- "## " + namespace_name + "\n\n" }}
|
| 110 |
+
{{- "namespace " + namespace_name + " {\n\n" }}
|
| 111 |
+
{%- for tool in tools %}
|
| 112 |
+
{%- set tool = tool.function %}
|
| 113 |
+
{{- "// " + tool.description + "\n" }}
|
| 114 |
+
{{- "type "+ tool.name + " = " }}
|
| 115 |
+
{%- if tool.parameters and tool.parameters.properties %}
|
| 116 |
+
{{- "(_: {\n" }}
|
| 117 |
+
{%- for param_name, param_spec in tool.parameters.properties.items() %}
|
| 118 |
+
{%- if param_spec.description %}
|
| 119 |
+
{{- "// " + param_spec.description + "\n" }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{{- param_name }}
|
| 122 |
+
{%- if param_name not in (tool.parameters.required or []) -%}
|
| 123 |
+
{{- "?" }}
|
| 124 |
+
{%- endif -%}
|
| 125 |
+
{{- ": " }}
|
| 126 |
+
{{- render_typescript_type(param_spec, tool.parameters.required or []) }}
|
| 127 |
+
{%- if param_spec.default is defined -%}
|
| 128 |
+
{%- if param_spec.enum %}
|
| 129 |
+
{{- ", // default: " + param_spec.default }}
|
| 130 |
+
{%- elif param_spec.oneOf %}
|
| 131 |
+
{{- "// default: " + param_spec.default }}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- ", // default: " + param_spec.default|tojson }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
{%- endif -%}
|
| 136 |
+
{%- if not loop.last %}
|
| 137 |
+
{{- ",\n" }}
|
| 138 |
+
{%- else %}
|
| 139 |
+
{{- ",\n" }}
|
| 140 |
+
{%- endif -%}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{{- "}) => any;\n\n" }}
|
| 143 |
+
{%- else -%}
|
| 144 |
+
{{- "() => any;\n\n" }}
|
| 145 |
+
{%- endif -%}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{{- "} // namespace " + namespace_name }}
|
| 148 |
+
{%- endmacro -%}
|
| 149 |
+
|
| 150 |
+
{%- macro render_builtin_tools(browser_tool, python_tool) -%}
|
| 151 |
+
{%- if browser_tool %}
|
| 152 |
+
{{- "## browser\n\n" }}
|
| 153 |
+
{{- "// Tool for browsing.\n" }}
|
| 154 |
+
{{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
|
| 155 |
+
{{- "// Cite information from the tool using the following format:\n" }}
|
| 156 |
+
{{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
|
| 157 |
+
{{- "// Do not quote more than 10 words directly from the tool output.\n" }}
|
| 158 |
+
{{- "// sources=web (default: web)\n" }}
|
| 159 |
+
{{- "namespace browser {\n\n" }}
|
| 160 |
+
{{- "// Searches for information related to `query` and displays `topn` results.\n" }}
|
| 161 |
+
{{- "type search = (_: {\n" }}
|
| 162 |
+
{{- "query: string,\n" }}
|
| 163 |
+
{{- "topn?: number, // default: 10\n" }}
|
| 164 |
+
{{- "source?: string,\n" }}
|
| 165 |
+
{{- "}) => any;\n\n" }}
|
| 166 |
+
{{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
|
| 167 |
+
{{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
|
| 168 |
+
{{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
|
| 169 |
+
{{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
|
| 170 |
+
{{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
|
| 171 |
+
{{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
|
| 172 |
+
{{- "type open = (_: {\n" }}
|
| 173 |
+
{{- "id?: number | string, // default: -1\n" }}
|
| 174 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 175 |
+
{{- "loc?: number, // default: -1\n" }}
|
| 176 |
+
{{- "num_lines?: number, // default: -1\n" }}
|
| 177 |
+
{{- "view_source?: boolean, // default: false\n" }}
|
| 178 |
+
{{- "source?: string,\n" }}
|
| 179 |
+
{{- "}) => any;\n\n" }}
|
| 180 |
+
{{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
|
| 181 |
+
{{- "type find = (_: {\n" }}
|
| 182 |
+
{{- "pattern: string,\n" }}
|
| 183 |
+
{{- "cursor?: number, // default: -1\n" }}
|
| 184 |
+
{{- "}) => any;\n\n" }}
|
| 185 |
+
{{- "} // namespace browser\n\n" }}
|
| 186 |
+
{%- endif -%}
|
| 187 |
+
|
| 188 |
+
{%- if python_tool %}
|
| 189 |
+
{{- "## python\n\n" }}
|
| 190 |
+
{{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
|
| 191 |
+
{{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
|
| 192 |
+
{%- endif -%}
|
| 193 |
+
{%- endmacro -%}
|
| 194 |
+
|
| 195 |
+
{#- System Message Construction ============================================ #}
|
| 196 |
+
{%- macro build_system_message() -%}
|
| 197 |
+
{%- if model_identity is not defined %}
|
| 198 |
+
{%- set model_identity = "You are ChatGPT, a large language model trained by OpenAI." %}
|
| 199 |
+
{%- endif %}
|
| 200 |
+
{{- model_identity + "\n" }}
|
| 201 |
+
{{- "Knowledge cutoff: 2024-06\n" }}
|
| 202 |
+
{{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
|
| 203 |
+
{%- if reasoning_effort is not defined %}
|
| 204 |
+
{%- set reasoning_effort = "medium" %}
|
| 205 |
+
{%- endif %}
|
| 206 |
+
{{- "Reasoning: " + reasoning_effort + "\n\n" }}
|
| 207 |
+
{%- if builtin_tools %}
|
| 208 |
+
{{- "# Tools\n\n" }}
|
| 209 |
+
{%- set available_builtin_tools = namespace(browser=false, python=false) %}
|
| 210 |
+
{%- for tool in builtin_tools %}
|
| 211 |
+
{%- if tool == "browser" %}
|
| 212 |
+
{%- set available_builtin_tools.browser = true %}
|
| 213 |
+
{%- elif tool == "python" %}
|
| 214 |
+
{%- set available_builtin_tools.python = true %}
|
| 215 |
+
{%- endif %}
|
| 216 |
+
{%- endfor %}
|
| 217 |
+
{{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
|
| 218 |
+
{%- endif -%}
|
| 219 |
+
{{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
|
| 220 |
+
{%- if tools -%}
|
| 221 |
+
{{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
|
| 222 |
+
{%- endif -%}
|
| 223 |
+
{%- endmacro -%}
|
| 224 |
+
|
| 225 |
+
{#- Main Template Logic ================================================= #}
|
| 226 |
+
{#- Set defaults #}
|
| 227 |
+
|
| 228 |
+
{#- Render system message #}
|
| 229 |
+
{{- "<|start|>system<|message|>" }}
|
| 230 |
+
{{- build_system_message() }}
|
| 231 |
+
{{- "<|end|>" }}
|
| 232 |
+
|
| 233 |
+
{#- Extract developer message #}
|
| 234 |
+
{%- if messages[0].role == "developer" or messages[0].role == "system" %}
|
| 235 |
+
{%- set developer_message = messages[0].content %}
|
| 236 |
+
{%- set loop_messages = messages[1:] %}
|
| 237 |
+
{%- else %}
|
| 238 |
+
{%- set developer_message = "" %}
|
| 239 |
+
{%- set loop_messages = messages %}
|
| 240 |
+
{%- endif %}
|
| 241 |
+
|
| 242 |
+
{#- Render developer message #}
|
| 243 |
+
{%- if developer_message or tools %}
|
| 244 |
+
{{- "<|start|>developer<|message|>" }}
|
| 245 |
+
{%- if developer_message %}
|
| 246 |
+
{{- "# Instructions\n\n" }}
|
| 247 |
+
{{- developer_message }}
|
| 248 |
+
{{- "\n\n" }}
|
| 249 |
+
{%- endif %}
|
| 250 |
+
{%- if tools -%}
|
| 251 |
+
{{- "# Tools\n\n" }}
|
| 252 |
+
{{- render_tool_namespace("functions", tools) }}
|
| 253 |
+
{%- endif -%}
|
| 254 |
+
{{- "<|end|>" }}
|
| 255 |
+
{%- endif %}
|
| 256 |
+
|
| 257 |
+
{#- Render messages #}
|
| 258 |
+
{%- set last_tool_call = namespace(name=none) %}
|
| 259 |
+
{%- for message in loop_messages -%}
|
| 260 |
+
{#- At this point only assistant/user/tool messages should remain #}
|
| 261 |
+
{%- if message.role == 'assistant' -%}
|
| 262 |
+
{#- Checks to ensure the messages are being passed in the format we expect #}
|
| 263 |
+
{%- if "content" in message %}
|
| 264 |
+
{%- if "<|channel|>analysis<|message|>" in message.content or "<|channel|>final<|message|>" in message.content %}
|
| 265 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the content field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 266 |
+
{%- endif %}
|
| 267 |
+
{%- endif %}
|
| 268 |
+
{%- if "thinking" in message %}
|
| 269 |
+
{%- if "<|channel|>analysis<|message|>" in message.thinking or "<|channel|>final<|message|>" in message.thinking %}
|
| 270 |
+
{{- raise_exception("You have passed a message containing <|channel|> tags in the thinking field. Instead of doing this, you should pass analysis messages (the string between '<|message|>' and '<|end|>') in the 'thinking' field, and final messages (the string between '<|message|>' and '<|end|>') in the 'content' field.") }}
|
| 271 |
+
{%- endif %}
|
| 272 |
+
{%- endif %}
|
| 273 |
+
{%- if "tool_calls" in message %}
|
| 274 |
+
{#- We need very careful handling here - we want to drop the tool call analysis message if the model #}
|
| 275 |
+
{#- has output a later <|final|> message, but otherwise we want to retain it. This is the only case #}
|
| 276 |
+
{#- when we render CoT/analysis messages in inference. #}
|
| 277 |
+
{%- set future_final_message = namespace(found=false) %}
|
| 278 |
+
{%- for future_message in loop_messages[loop.index:] %}
|
| 279 |
+
{%- if future_message.role == 'assistant' and "tool_calls" not in future_message %}
|
| 280 |
+
{%- set future_final_message.found = true %}
|
| 281 |
+
{%- endif %}
|
| 282 |
+
{%- endfor %}
|
| 283 |
+
{#- We assume max 1 tool call per message, and so we infer the tool call name #}
|
| 284 |
+
{#- in "tool" messages from the most recent assistant tool call name #}
|
| 285 |
+
{%- set tool_call = message.tool_calls[0] %}
|
| 286 |
+
{%- if tool_call.function %}
|
| 287 |
+
{%- set tool_call = tool_call.function %}
|
| 288 |
+
{%- endif %}
|
| 289 |
+
{%- if message.content and message.thinking %}
|
| 290 |
+
{{- raise_exception("Cannot pass both content and thinking in an assistant message with tool calls! Put the analysis message in one or the other, but not both.") }}
|
| 291 |
+
{%- elif message.content and not future_final_message.found %}
|
| 292 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
|
| 293 |
+
{%- elif message.thinking and not future_final_message.found %}
|
| 294 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 295 |
+
{%- endif %}
|
| 296 |
+
{{- "<|start|>assistant to=" }}
|
| 297 |
+
{{- "functions." + tool_call.name + "<|channel|>commentary " }}
|
| 298 |
+
{{- (tool_call.content_type if tool_call.content_type is defined else "json") + "<|message|>" }}
|
| 299 |
+
{{- tool_call.arguments|tojson }}
|
| 300 |
+
{{- "<|call|>" }}
|
| 301 |
+
{%- set last_tool_call.name = tool_call.name %}
|
| 302 |
+
{%- elif loop.last and not add_generation_prompt %}
|
| 303 |
+
{#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
|
| 304 |
+
{#- This is a situation that should only occur in training, never in inference. #}
|
| 305 |
+
{%- if "thinking" in message %}
|
| 306 |
+
{{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
|
| 307 |
+
{%- endif %}
|
| 308 |
+
{#- <|return|> indicates the end of generation, but <|end|> does not #}
|
| 309 |
+
{#- <|return|> should never be an input to the model, but we include it as the final token #}
|
| 310 |
+
{#- when training, so the model learns to emit it. #}
|
| 311 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
|
| 312 |
+
{%- else %}
|
| 313 |
+
{#- CoT is dropped during all previous turns, so we never render it for inference #}
|
| 314 |
+
{{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
|
| 315 |
+
{%- set last_tool_call.name = none %}
|
| 316 |
+
{%- endif %}
|
| 317 |
+
{%- elif message.role == 'tool' -%}
|
| 318 |
+
{%- if last_tool_call.name is none %}
|
| 319 |
+
{{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
|
| 320 |
+
{%- endif %}
|
| 321 |
+
{{- "<|start|>functions." + last_tool_call.name }}
|
| 322 |
+
{{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
|
| 323 |
+
{%- elif message.role == 'user' -%}
|
| 324 |
+
{{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
|
| 325 |
+
{%- endif -%}
|
| 326 |
+
{%- endfor -%}
|
| 327 |
+
|
| 328 |
+
{#- Generation prompt #}
|
| 329 |
+
{%- if add_generation_prompt -%}
|
| 330 |
+
<|start|>assistant
|
| 331 |
+
{%- endif -%}
|
citation.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"title": "GPT-OSS MoE Expert Fingerprinting: Analyzing Expert Activation Patterns in Mixture of Experts Models",
|
| 3 |
+
"authors": [
|
| 4 |
+
"Aman Priyanshu",
|
| 5 |
+
"Supriti Vijay"
|
| 6 |
+
],
|
| 7 |
+
"year": 2025,
|
| 8 |
+
"url": "https://amanpriyanshu.github.io/GPT-OSS-MoE-ExpertFingerprinting/"
|
| 9 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab_size": 201088,
|
| 3 |
+
"hidden_size": 2880,
|
| 4 |
+
"intermediate_size": 2880,
|
| 5 |
+
"num_hidden_layers": 24,
|
| 6 |
+
"num_attention_heads": 64,
|
| 7 |
+
"num_local_experts": 8,
|
| 8 |
+
"sliding_window": 128,
|
| 9 |
+
"num_experts_per_tok": 4,
|
| 10 |
+
"num_key_value_heads": 8,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"rms_norm_eps": 1e-05,
|
| 14 |
+
"rope_theta": 150000,
|
| 15 |
+
"rope_scaling": {
|
| 16 |
+
"beta_fast": 32.0,
|
| 17 |
+
"beta_slow": 1.0,
|
| 18 |
+
"factor": 32.0,
|
| 19 |
+
"original_max_position_embeddings": 4096,
|
| 20 |
+
"rope_type": "yarn",
|
| 21 |
+
"truncate": false
|
| 22 |
+
},
|
| 23 |
+
"attention_dropout": 0.0,
|
| 24 |
+
"head_dim": 64,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"sliding_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"sliding_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"sliding_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"sliding_attention",
|
| 49 |
+
"full_attention"
|
| 50 |
+
],
|
| 51 |
+
"attention_bias": true,
|
| 52 |
+
"max_position_embeddings": 131072,
|
| 53 |
+
"router_aux_loss_coef": 0.9,
|
| 54 |
+
"output_router_logits": false,
|
| 55 |
+
"use_cache": true,
|
| 56 |
+
"return_dict": true,
|
| 57 |
+
"output_hidden_states": false,
|
| 58 |
+
"torchscript": false,
|
| 59 |
+
"torch_dtype": null,
|
| 60 |
+
"pruned_heads": {},
|
| 61 |
+
"tie_word_embeddings": false,
|
| 62 |
+
"chunk_size_feed_forward": 0,
|
| 63 |
+
"is_encoder_decoder": false,
|
| 64 |
+
"is_decoder": false,
|
| 65 |
+
"cross_attention_hidden_size": null,
|
| 66 |
+
"add_cross_attention": false,
|
| 67 |
+
"tie_encoder_decoder": false,
|
| 68 |
+
"architectures": [
|
| 69 |
+
"GptOssForCausalLM"
|
| 70 |
+
],
|
| 71 |
+
"finetuning_task": null,
|
| 72 |
+
"id2label": {
|
| 73 |
+
"0": "LABEL_0",
|
| 74 |
+
"1": "LABEL_1"
|
| 75 |
+
},
|
| 76 |
+
"label2id": {
|
| 77 |
+
"LABEL_0": 0,
|
| 78 |
+
"LABEL_1": 1
|
| 79 |
+
},
|
| 80 |
+
"task_specific_params": null,
|
| 81 |
+
"problem_type": null,
|
| 82 |
+
"tokenizer_class": null,
|
| 83 |
+
"prefix": null,
|
| 84 |
+
"bos_token_id": null,
|
| 85 |
+
"pad_token_id": 199999,
|
| 86 |
+
"eos_token_id": 200002,
|
| 87 |
+
"sep_token_id": null,
|
| 88 |
+
"decoder_start_token_id": null,
|
| 89 |
+
"max_length": 20,
|
| 90 |
+
"min_length": 0,
|
| 91 |
+
"do_sample": false,
|
| 92 |
+
"early_stopping": false,
|
| 93 |
+
"num_beams": 1,
|
| 94 |
+
"num_beam_groups": 1,
|
| 95 |
+
"diversity_penalty": 0.0,
|
| 96 |
+
"temperature": 1.0,
|
| 97 |
+
"top_k": 50,
|
| 98 |
+
"top_p": 1.0,
|
| 99 |
+
"typical_p": 1.0,
|
| 100 |
+
"repetition_penalty": 1.0,
|
| 101 |
+
"length_penalty": 1.0,
|
| 102 |
+
"no_repeat_ngram_size": 0,
|
| 103 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 104 |
+
"bad_words_ids": null,
|
| 105 |
+
"num_return_sequences": 1,
|
| 106 |
+
"output_scores": false,
|
| 107 |
+
"return_dict_in_generate": false,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"remove_invalid_values": false,
|
| 111 |
+
"exponential_decay_length_penalty": null,
|
| 112 |
+
"suppress_tokens": null,
|
| 113 |
+
"begin_suppress_tokens": null,
|
| 114 |
+
"_name_or_path": "openai/gpt-oss-20b",
|
| 115 |
+
"transformers_version": "4.55.0",
|
| 116 |
+
"experts_per_token": 4,
|
| 117 |
+
"initial_context_length": 4096,
|
| 118 |
+
"model_type": "gpt_oss",
|
| 119 |
+
"swiglu_limit": 7.0,
|
| 120 |
+
"tf_legacy_loss": false,
|
| 121 |
+
"use_bfloat16": false,
|
| 122 |
+
"output_attentions": false
|
| 123 |
+
}
|
expert_mapping.json
ADDED
|
@@ -0,0 +1,242 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"0": {
|
| 3 |
+
"9": 0,
|
| 4 |
+
"11": 1,
|
| 5 |
+
"3": 2,
|
| 6 |
+
"17": 3,
|
| 7 |
+
"22": 4,
|
| 8 |
+
"16": 5,
|
| 9 |
+
"31": 6,
|
| 10 |
+
"1": 7
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"28": 0,
|
| 14 |
+
"25": 1,
|
| 15 |
+
"0": 2,
|
| 16 |
+
"27": 3,
|
| 17 |
+
"18": 4,
|
| 18 |
+
"6": 5,
|
| 19 |
+
"1": 6,
|
| 20 |
+
"12": 7
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"31": 0,
|
| 24 |
+
"21": 1,
|
| 25 |
+
"29": 2,
|
| 26 |
+
"10": 3,
|
| 27 |
+
"8": 4,
|
| 28 |
+
"5": 5,
|
| 29 |
+
"0": 6,
|
| 30 |
+
"22": 7
|
| 31 |
+
},
|
| 32 |
+
"3": {
|
| 33 |
+
"7": 0,
|
| 34 |
+
"31": 1,
|
| 35 |
+
"0": 2,
|
| 36 |
+
"23": 3,
|
| 37 |
+
"19": 4,
|
| 38 |
+
"2": 5,
|
| 39 |
+
"21": 6,
|
| 40 |
+
"11": 7
|
| 41 |
+
},
|
| 42 |
+
"4": {
|
| 43 |
+
"6": 0,
|
| 44 |
+
"15": 1,
|
| 45 |
+
"18": 2,
|
| 46 |
+
"20": 3,
|
| 47 |
+
"17": 4,
|
| 48 |
+
"24": 5,
|
| 49 |
+
"23": 6,
|
| 50 |
+
"14": 7
|
| 51 |
+
},
|
| 52 |
+
"5": {
|
| 53 |
+
"6": 0,
|
| 54 |
+
"0": 1,
|
| 55 |
+
"10": 2,
|
| 56 |
+
"31": 3,
|
| 57 |
+
"14": 4,
|
| 58 |
+
"15": 5,
|
| 59 |
+
"2": 6,
|
| 60 |
+
"24": 7
|
| 61 |
+
},
|
| 62 |
+
"6": {
|
| 63 |
+
"2": 0,
|
| 64 |
+
"9": 1,
|
| 65 |
+
"10": 2,
|
| 66 |
+
"5": 3,
|
| 67 |
+
"3": 4,
|
| 68 |
+
"16": 5,
|
| 69 |
+
"7": 6,
|
| 70 |
+
"15": 7
|
| 71 |
+
},
|
| 72 |
+
"7": {
|
| 73 |
+
"5": 0,
|
| 74 |
+
"1": 1,
|
| 75 |
+
"30": 2,
|
| 76 |
+
"13": 3,
|
| 77 |
+
"29": 4,
|
| 78 |
+
"10": 5,
|
| 79 |
+
"14": 6,
|
| 80 |
+
"4": 7
|
| 81 |
+
},
|
| 82 |
+
"8": {
|
| 83 |
+
"24": 0,
|
| 84 |
+
"20": 1,
|
| 85 |
+
"4": 2,
|
| 86 |
+
"17": 3,
|
| 87 |
+
"31": 4,
|
| 88 |
+
"5": 5,
|
| 89 |
+
"0": 6,
|
| 90 |
+
"13": 7
|
| 91 |
+
},
|
| 92 |
+
"9": {
|
| 93 |
+
"8": 0,
|
| 94 |
+
"19": 1,
|
| 95 |
+
"15": 2,
|
| 96 |
+
"30": 3,
|
| 97 |
+
"14": 4,
|
| 98 |
+
"16": 5,
|
| 99 |
+
"13": 6,
|
| 100 |
+
"21": 7
|
| 101 |
+
},
|
| 102 |
+
"10": {
|
| 103 |
+
"10": 0,
|
| 104 |
+
"5": 1,
|
| 105 |
+
"7": 2,
|
| 106 |
+
"23": 3,
|
| 107 |
+
"19": 4,
|
| 108 |
+
"26": 5,
|
| 109 |
+
"21": 6,
|
| 110 |
+
"11": 7
|
| 111 |
+
},
|
| 112 |
+
"11": {
|
| 113 |
+
"30": 0,
|
| 114 |
+
"9": 1,
|
| 115 |
+
"27": 2,
|
| 116 |
+
"11": 3,
|
| 117 |
+
"7": 4,
|
| 118 |
+
"20": 5,
|
| 119 |
+
"25": 6,
|
| 120 |
+
"21": 7
|
| 121 |
+
},
|
| 122 |
+
"12": {
|
| 123 |
+
"23": 0,
|
| 124 |
+
"14": 1,
|
| 125 |
+
"3": 2,
|
| 126 |
+
"21": 3,
|
| 127 |
+
"28": 4,
|
| 128 |
+
"1": 5,
|
| 129 |
+
"24": 6,
|
| 130 |
+
"25": 7
|
| 131 |
+
},
|
| 132 |
+
"13": {
|
| 133 |
+
"21": 0,
|
| 134 |
+
"9": 1,
|
| 135 |
+
"11": 2,
|
| 136 |
+
"1": 3,
|
| 137 |
+
"19": 4,
|
| 138 |
+
"24": 5,
|
| 139 |
+
"16": 6,
|
| 140 |
+
"3": 7
|
| 141 |
+
},
|
| 142 |
+
"14": {
|
| 143 |
+
"9": 0,
|
| 144 |
+
"0": 1,
|
| 145 |
+
"6": 2,
|
| 146 |
+
"18": 3,
|
| 147 |
+
"21": 4,
|
| 148 |
+
"26": 5,
|
| 149 |
+
"4": 6,
|
| 150 |
+
"24": 7
|
| 151 |
+
},
|
| 152 |
+
"15": {
|
| 153 |
+
"13": 0,
|
| 154 |
+
"18": 1,
|
| 155 |
+
"31": 2,
|
| 156 |
+
"26": 3,
|
| 157 |
+
"3": 4,
|
| 158 |
+
"9": 5,
|
| 159 |
+
"2": 6,
|
| 160 |
+
"29": 7
|
| 161 |
+
},
|
| 162 |
+
"16": {
|
| 163 |
+
"31": 0,
|
| 164 |
+
"30": 1,
|
| 165 |
+
"15": 2,
|
| 166 |
+
"11": 3,
|
| 167 |
+
"24": 4,
|
| 168 |
+
"5": 5,
|
| 169 |
+
"0": 6,
|
| 170 |
+
"18": 7
|
| 171 |
+
},
|
| 172 |
+
"17": {
|
| 173 |
+
"14": 0,
|
| 174 |
+
"30": 1,
|
| 175 |
+
"5": 2,
|
| 176 |
+
"4": 3,
|
| 177 |
+
"17": 4,
|
| 178 |
+
"11": 5,
|
| 179 |
+
"28": 6,
|
| 180 |
+
"7": 7
|
| 181 |
+
},
|
| 182 |
+
"18": {
|
| 183 |
+
"1": 0,
|
| 184 |
+
"18": 1,
|
| 185 |
+
"24": 2,
|
| 186 |
+
"14": 3,
|
| 187 |
+
"15": 4,
|
| 188 |
+
"27": 5,
|
| 189 |
+
"20": 6,
|
| 190 |
+
"23": 7
|
| 191 |
+
},
|
| 192 |
+
"19": {
|
| 193 |
+
"3": 0,
|
| 194 |
+
"19": 1,
|
| 195 |
+
"6": 2,
|
| 196 |
+
"29": 3,
|
| 197 |
+
"16": 4,
|
| 198 |
+
"31": 5,
|
| 199 |
+
"7": 6,
|
| 200 |
+
"0": 7
|
| 201 |
+
},
|
| 202 |
+
"20": {
|
| 203 |
+
"22": 0,
|
| 204 |
+
"16": 1,
|
| 205 |
+
"30": 2,
|
| 206 |
+
"24": 3,
|
| 207 |
+
"31": 4,
|
| 208 |
+
"21": 5,
|
| 209 |
+
"11": 6,
|
| 210 |
+
"12": 7
|
| 211 |
+
},
|
| 212 |
+
"21": {
|
| 213 |
+
"3": 0,
|
| 214 |
+
"9": 1,
|
| 215 |
+
"27": 2,
|
| 216 |
+
"21": 3,
|
| 217 |
+
"6": 4,
|
| 218 |
+
"1": 5,
|
| 219 |
+
"2": 6,
|
| 220 |
+
"20": 7
|
| 221 |
+
},
|
| 222 |
+
"22": {
|
| 223 |
+
"25": 0,
|
| 224 |
+
"16": 1,
|
| 225 |
+
"14": 2,
|
| 226 |
+
"8": 3,
|
| 227 |
+
"18": 4,
|
| 228 |
+
"22": 5,
|
| 229 |
+
"15": 6,
|
| 230 |
+
"4": 7
|
| 231 |
+
},
|
| 232 |
+
"23": {
|
| 233 |
+
"31": 0,
|
| 234 |
+
"18": 1,
|
| 235 |
+
"10": 2,
|
| 236 |
+
"16": 3,
|
| 237 |
+
"0": 4,
|
| 238 |
+
"22": 5,
|
| 239 |
+
"28": 6,
|
| 240 |
+
"17": 7
|
| 241 |
+
}
|
| 242 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 199998,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
200002,
|
| 6 |
+
199999
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 199999,
|
| 9 |
+
"transformers_version": "4.55.0"
|
| 10 |
+
}
|
model-00001-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bc6fca7ae00a3f3bfd5983012119e263aa72992644eeee2c20f093ccabf8d85
|
| 3 |
+
size 1928357080
|
model-00002-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cb457ce101b3a19aacc18a1e6743ad1525e051037259761fee24a87e263ff98
|
| 3 |
+
size 1991633080
|
model-00003-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e07a2cdb213f5e19bad2d1a9514232ce1265450b6d65f70e22a7965e4a84b494
|
| 3 |
+
size 1805716976
|
model-00004-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4618bc901e830eb3394dbb920578133128e651e8a3a9c931bf110d44b4b95394
|
| 3 |
+
size 1805717096
|
model-00005-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81d770554133af6913ea670dac0589483dfc40fa0ca8478c9cbb9bfb9e651a0d
|
| 3 |
+
size 1805717096
|
model-00006-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be73a02300f1e73768634b381d0f40d8723431ad4ed0e6633fdbd6d787f9e018
|
| 3 |
+
size 1805717096
|
model-00007-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dccf2fd2326660b27ad9b5b8a9aff20bea1d55208717acdc4e8c466301f7eb7e
|
| 3 |
+
size 849716784
|
model-00008-of-00008.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e257de1fa16cf80c8a36ca29c5974fc999f0dc7ada1468bfd0be18151af482
|
| 3 |
+
size 1158267008
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,419 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 6575397888,
|
| 4 |
+
"total_size": 13150795776
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00008-of-00008.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 10 |
+
"model.layers.0.mlp.experts.down_proj": "model-00001-of-00008.safetensors",
|
| 11 |
+
"model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00008.safetensors",
|
| 12 |
+
"model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00008.safetensors",
|
| 13 |
+
"model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00008.safetensors",
|
| 14 |
+
"model.layers.0.mlp.router.bias": "model-00001-of-00008.safetensors",
|
| 15 |
+
"model.layers.0.mlp.router.weight": "model-00001-of-00008.safetensors",
|
| 16 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 23 |
+
"model.layers.0.self_attn.sinks": "model-00001-of-00008.safetensors",
|
| 24 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 25 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 26 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 27 |
+
"model.layers.1.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
|
| 28 |
+
"model.layers.1.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
|
| 29 |
+
"model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00008.safetensors",
|
| 30 |
+
"model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00008.safetensors",
|
| 31 |
+
"model.layers.1.mlp.router.bias": "model-00001-of-00008.safetensors",
|
| 32 |
+
"model.layers.1.mlp.router.weight": "model-00001-of-00008.safetensors",
|
| 33 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 34 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00008.safetensors",
|
| 35 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
| 36 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00008.safetensors",
|
| 37 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
| 38 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00008.safetensors",
|
| 39 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
| 40 |
+
"model.layers.1.self_attn.sinks": "model-00001-of-00008.safetensors",
|
| 41 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00008.safetensors",
|
| 42 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
| 43 |
+
"model.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 44 |
+
"model.layers.10.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
|
| 45 |
+
"model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
|
| 46 |
+
"model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
|
| 47 |
+
"model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
|
| 48 |
+
"model.layers.10.mlp.router.bias": "model-00003-of-00008.safetensors",
|
| 49 |
+
"model.layers.10.mlp.router.weight": "model-00003-of-00008.safetensors",
|
| 50 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 51 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 52 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 53 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
|
| 54 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 55 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 56 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 57 |
+
"model.layers.10.self_attn.sinks": "model-00003-of-00008.safetensors",
|
| 58 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 59 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 60 |
+
"model.layers.11.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 61 |
+
"model.layers.11.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
|
| 62 |
+
"model.layers.11.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
|
| 63 |
+
"model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
|
| 64 |
+
"model.layers.11.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
|
| 65 |
+
"model.layers.11.mlp.router.bias": "model-00004-of-00008.safetensors",
|
| 66 |
+
"model.layers.11.mlp.router.weight": "model-00004-of-00008.safetensors",
|
| 67 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 68 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 69 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 70 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
|
| 71 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 72 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 73 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 74 |
+
"model.layers.11.self_attn.sinks": "model-00004-of-00008.safetensors",
|
| 75 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 76 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 77 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 78 |
+
"model.layers.12.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
|
| 79 |
+
"model.layers.12.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
|
| 80 |
+
"model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
|
| 81 |
+
"model.layers.12.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
|
| 82 |
+
"model.layers.12.mlp.router.bias": "model-00004-of-00008.safetensors",
|
| 83 |
+
"model.layers.12.mlp.router.weight": "model-00004-of-00008.safetensors",
|
| 84 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 85 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 86 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 87 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
|
| 88 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 89 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 90 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 91 |
+
"model.layers.12.self_attn.sinks": "model-00004-of-00008.safetensors",
|
| 92 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 93 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 94 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 95 |
+
"model.layers.13.mlp.experts.down_proj": "model-00004-of-00008.safetensors",
|
| 96 |
+
"model.layers.13.mlp.experts.down_proj_bias": "model-00004-of-00008.safetensors",
|
| 97 |
+
"model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00008.safetensors",
|
| 98 |
+
"model.layers.13.mlp.experts.gate_up_proj_bias": "model-00004-of-00008.safetensors",
|
| 99 |
+
"model.layers.13.mlp.router.bias": "model-00004-of-00008.safetensors",
|
| 100 |
+
"model.layers.13.mlp.router.weight": "model-00004-of-00008.safetensors",
|
| 101 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
| 102 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 103 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 104 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
|
| 105 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 106 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 107 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 108 |
+
"model.layers.13.self_attn.sinks": "model-00004-of-00008.safetensors",
|
| 109 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 110 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 111 |
+
"model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 112 |
+
"model.layers.14.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
|
| 113 |
+
"model.layers.14.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
|
| 114 |
+
"model.layers.14.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
|
| 115 |
+
"model.layers.14.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
|
| 116 |
+
"model.layers.14.mlp.router.bias": "model-00004-of-00008.safetensors",
|
| 117 |
+
"model.layers.14.mlp.router.weight": "model-00004-of-00008.safetensors",
|
| 118 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 119 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00008.safetensors",
|
| 120 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
| 121 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00004-of-00008.safetensors",
|
| 122 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
| 123 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00008.safetensors",
|
| 124 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
| 125 |
+
"model.layers.14.self_attn.sinks": "model-00004-of-00008.safetensors",
|
| 126 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00008.safetensors",
|
| 127 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
| 128 |
+
"model.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 129 |
+
"model.layers.15.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
|
| 130 |
+
"model.layers.15.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
|
| 131 |
+
"model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
|
| 132 |
+
"model.layers.15.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
|
| 133 |
+
"model.layers.15.mlp.router.bias": "model-00005-of-00008.safetensors",
|
| 134 |
+
"model.layers.15.mlp.router.weight": "model-00005-of-00008.safetensors",
|
| 135 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 136 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 137 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 138 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
|
| 139 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 140 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 141 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 142 |
+
"model.layers.15.self_attn.sinks": "model-00005-of-00008.safetensors",
|
| 143 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 144 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 145 |
+
"model.layers.16.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 146 |
+
"model.layers.16.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
|
| 147 |
+
"model.layers.16.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
|
| 148 |
+
"model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
|
| 149 |
+
"model.layers.16.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
|
| 150 |
+
"model.layers.16.mlp.router.bias": "model-00005-of-00008.safetensors",
|
| 151 |
+
"model.layers.16.mlp.router.weight": "model-00005-of-00008.safetensors",
|
| 152 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 153 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 154 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 155 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
|
| 156 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 157 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 158 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 159 |
+
"model.layers.16.self_attn.sinks": "model-00005-of-00008.safetensors",
|
| 160 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 161 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 162 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 163 |
+
"model.layers.17.mlp.experts.down_proj": "model-00005-of-00008.safetensors",
|
| 164 |
+
"model.layers.17.mlp.experts.down_proj_bias": "model-00005-of-00008.safetensors",
|
| 165 |
+
"model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00008.safetensors",
|
| 166 |
+
"model.layers.17.mlp.experts.gate_up_proj_bias": "model-00005-of-00008.safetensors",
|
| 167 |
+
"model.layers.17.mlp.router.bias": "model-00005-of-00008.safetensors",
|
| 168 |
+
"model.layers.17.mlp.router.weight": "model-00005-of-00008.safetensors",
|
| 169 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
| 170 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 171 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 172 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
|
| 173 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 174 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 175 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 176 |
+
"model.layers.17.self_attn.sinks": "model-00005-of-00008.safetensors",
|
| 177 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 178 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 179 |
+
"model.layers.18.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 180 |
+
"model.layers.18.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
|
| 181 |
+
"model.layers.18.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
|
| 182 |
+
"model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
|
| 183 |
+
"model.layers.18.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
|
| 184 |
+
"model.layers.18.mlp.router.bias": "model-00005-of-00008.safetensors",
|
| 185 |
+
"model.layers.18.mlp.router.weight": "model-00005-of-00008.safetensors",
|
| 186 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 187 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00005-of-00008.safetensors",
|
| 188 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
| 189 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00005-of-00008.safetensors",
|
| 190 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
| 191 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00005-of-00008.safetensors",
|
| 192 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
| 193 |
+
"model.layers.18.self_attn.sinks": "model-00005-of-00008.safetensors",
|
| 194 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00008.safetensors",
|
| 195 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
| 196 |
+
"model.layers.19.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 197 |
+
"model.layers.19.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
|
| 198 |
+
"model.layers.19.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
|
| 199 |
+
"model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
|
| 200 |
+
"model.layers.19.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
|
| 201 |
+
"model.layers.19.mlp.router.bias": "model-00006-of-00008.safetensors",
|
| 202 |
+
"model.layers.19.mlp.router.weight": "model-00006-of-00008.safetensors",
|
| 203 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 204 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 205 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 206 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
|
| 207 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 208 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 209 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 210 |
+
"model.layers.19.self_attn.sinks": "model-00006-of-00008.safetensors",
|
| 211 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 212 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 213 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 214 |
+
"model.layers.2.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
|
| 215 |
+
"model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
|
| 216 |
+
"model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
|
| 217 |
+
"model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
|
| 218 |
+
"model.layers.2.mlp.router.bias": "model-00002-of-00008.safetensors",
|
| 219 |
+
"model.layers.2.mlp.router.weight": "model-00002-of-00008.safetensors",
|
| 220 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 221 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 222 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 223 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
|
| 224 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 225 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 226 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 227 |
+
"model.layers.2.self_attn.sinks": "model-00002-of-00008.safetensors",
|
| 228 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 229 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 230 |
+
"model.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 231 |
+
"model.layers.20.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
|
| 232 |
+
"model.layers.20.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
|
| 233 |
+
"model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
|
| 234 |
+
"model.layers.20.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
|
| 235 |
+
"model.layers.20.mlp.router.bias": "model-00006-of-00008.safetensors",
|
| 236 |
+
"model.layers.20.mlp.router.weight": "model-00006-of-00008.safetensors",
|
| 237 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 238 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 239 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 240 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
|
| 241 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 242 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 243 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 244 |
+
"model.layers.20.self_attn.sinks": "model-00006-of-00008.safetensors",
|
| 245 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 246 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 247 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 248 |
+
"model.layers.21.mlp.experts.down_proj": "model-00006-of-00008.safetensors",
|
| 249 |
+
"model.layers.21.mlp.experts.down_proj_bias": "model-00006-of-00008.safetensors",
|
| 250 |
+
"model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00008.safetensors",
|
| 251 |
+
"model.layers.21.mlp.experts.gate_up_proj_bias": "model-00006-of-00008.safetensors",
|
| 252 |
+
"model.layers.21.mlp.router.bias": "model-00006-of-00008.safetensors",
|
| 253 |
+
"model.layers.21.mlp.router.weight": "model-00006-of-00008.safetensors",
|
| 254 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
| 255 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 256 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 257 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
|
| 258 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 259 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 260 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 261 |
+
"model.layers.21.self_attn.sinks": "model-00006-of-00008.safetensors",
|
| 262 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 263 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 264 |
+
"model.layers.22.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 265 |
+
"model.layers.22.mlp.experts.down_proj": "model-00007-of-00008.safetensors",
|
| 266 |
+
"model.layers.22.mlp.experts.down_proj_bias": "model-00007-of-00008.safetensors",
|
| 267 |
+
"model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00008.safetensors",
|
| 268 |
+
"model.layers.22.mlp.experts.gate_up_proj_bias": "model-00007-of-00008.safetensors",
|
| 269 |
+
"model.layers.22.mlp.router.bias": "model-00006-of-00008.safetensors",
|
| 270 |
+
"model.layers.22.mlp.router.weight": "model-00006-of-00008.safetensors",
|
| 271 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 272 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00006-of-00008.safetensors",
|
| 273 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
| 274 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00006-of-00008.safetensors",
|
| 275 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
| 276 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00006-of-00008.safetensors",
|
| 277 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
| 278 |
+
"model.layers.22.self_attn.sinks": "model-00006-of-00008.safetensors",
|
| 279 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00008.safetensors",
|
| 280 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
| 281 |
+
"model.layers.23.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 282 |
+
"model.layers.23.mlp.experts.down_proj": "model-00007-of-00008.safetensors",
|
| 283 |
+
"model.layers.23.mlp.experts.down_proj_bias": "model-00007-of-00008.safetensors",
|
| 284 |
+
"model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00008.safetensors",
|
| 285 |
+
"model.layers.23.mlp.experts.gate_up_proj_bias": "model-00007-of-00008.safetensors",
|
| 286 |
+
"model.layers.23.mlp.router.bias": "model-00007-of-00008.safetensors",
|
| 287 |
+
"model.layers.23.mlp.router.weight": "model-00007-of-00008.safetensors",
|
| 288 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
| 289 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00007-of-00008.safetensors",
|
| 290 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
| 291 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00007-of-00008.safetensors",
|
| 292 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
| 293 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00007-of-00008.safetensors",
|
| 294 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
| 295 |
+
"model.layers.23.self_attn.sinks": "model-00007-of-00008.safetensors",
|
| 296 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00007-of-00008.safetensors",
|
| 297 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
| 298 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 299 |
+
"model.layers.3.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
|
| 300 |
+
"model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
|
| 301 |
+
"model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
|
| 302 |
+
"model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
|
| 303 |
+
"model.layers.3.mlp.router.bias": "model-00002-of-00008.safetensors",
|
| 304 |
+
"model.layers.3.mlp.router.weight": "model-00002-of-00008.safetensors",
|
| 305 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 306 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 307 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 308 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
|
| 309 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 310 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 311 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 312 |
+
"model.layers.3.self_attn.sinks": "model-00002-of-00008.safetensors",
|
| 313 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 314 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 315 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 316 |
+
"model.layers.4.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
|
| 317 |
+
"model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
|
| 318 |
+
"model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
|
| 319 |
+
"model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
|
| 320 |
+
"model.layers.4.mlp.router.bias": "model-00002-of-00008.safetensors",
|
| 321 |
+
"model.layers.4.mlp.router.weight": "model-00002-of-00008.safetensors",
|
| 322 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 323 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 324 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 325 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
|
| 326 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 327 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 328 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 329 |
+
"model.layers.4.self_attn.sinks": "model-00002-of-00008.safetensors",
|
| 330 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 331 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 332 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 333 |
+
"model.layers.5.mlp.experts.down_proj": "model-00002-of-00008.safetensors",
|
| 334 |
+
"model.layers.5.mlp.experts.down_proj_bias": "model-00002-of-00008.safetensors",
|
| 335 |
+
"model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00008.safetensors",
|
| 336 |
+
"model.layers.5.mlp.experts.gate_up_proj_bias": "model-00002-of-00008.safetensors",
|
| 337 |
+
"model.layers.5.mlp.router.bias": "model-00002-of-00008.safetensors",
|
| 338 |
+
"model.layers.5.mlp.router.weight": "model-00002-of-00008.safetensors",
|
| 339 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
| 340 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 341 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 342 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
|
| 343 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 344 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 345 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 346 |
+
"model.layers.5.self_attn.sinks": "model-00002-of-00008.safetensors",
|
| 347 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 348 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 349 |
+
"model.layers.6.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 350 |
+
"model.layers.6.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
|
| 351 |
+
"model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
|
| 352 |
+
"model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
|
| 353 |
+
"model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
|
| 354 |
+
"model.layers.6.mlp.router.bias": "model-00002-of-00008.safetensors",
|
| 355 |
+
"model.layers.6.mlp.router.weight": "model-00002-of-00008.safetensors",
|
| 356 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 357 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00008.safetensors",
|
| 358 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
| 359 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00002-of-00008.safetensors",
|
| 360 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
| 361 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00008.safetensors",
|
| 362 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
| 363 |
+
"model.layers.6.self_attn.sinks": "model-00002-of-00008.safetensors",
|
| 364 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00008.safetensors",
|
| 365 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
| 366 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 367 |
+
"model.layers.7.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
|
| 368 |
+
"model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
|
| 369 |
+
"model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
|
| 370 |
+
"model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
|
| 371 |
+
"model.layers.7.mlp.router.bias": "model-00003-of-00008.safetensors",
|
| 372 |
+
"model.layers.7.mlp.router.weight": "model-00003-of-00008.safetensors",
|
| 373 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 374 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 375 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 376 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.sinks": "model-00003-of-00008.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 384 |
+
"model.layers.8.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
|
| 385 |
+
"model.layers.8.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
|
| 386 |
+
"model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
|
| 387 |
+
"model.layers.8.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
|
| 388 |
+
"model.layers.8.mlp.router.bias": "model-00003-of-00008.safetensors",
|
| 389 |
+
"model.layers.8.mlp.router.weight": "model-00003-of-00008.safetensors",
|
| 390 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 396 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 397 |
+
"model.layers.8.self_attn.sinks": "model-00003-of-00008.safetensors",
|
| 398 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 399 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 400 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 401 |
+
"model.layers.9.mlp.experts.down_proj": "model-00003-of-00008.safetensors",
|
| 402 |
+
"model.layers.9.mlp.experts.down_proj_bias": "model-00003-of-00008.safetensors",
|
| 403 |
+
"model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00008.safetensors",
|
| 404 |
+
"model.layers.9.mlp.experts.gate_up_proj_bias": "model-00003-of-00008.safetensors",
|
| 405 |
+
"model.layers.9.mlp.router.bias": "model-00003-of-00008.safetensors",
|
| 406 |
+
"model.layers.9.mlp.router.weight": "model-00003-of-00008.safetensors",
|
| 407 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
| 408 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00008.safetensors",
|
| 409 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
| 410 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00003-of-00008.safetensors",
|
| 411 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
| 412 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00008.safetensors",
|
| 413 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
| 414 |
+
"model.layers.9.self_attn.sinks": "model-00003-of-00008.safetensors",
|
| 415 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00008.safetensors",
|
| 416 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
| 417 |
+
"model.norm.weight": "model-00007-of-00008.safetensors"
|
| 418 |
+
}
|
| 419 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|startoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|return|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
|
| 3 |
+
size 27868174
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"199998": {
|
| 4 |
+
"content": "<|startoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"199999": {
|
| 12 |
+
"content": "<|endoftext|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"200000": {
|
| 20 |
+
"content": "<|reserved_200000|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"200001": {
|
| 28 |
+
"content": "<|reserved_200001|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"200002": {
|
| 36 |
+
"content": "<|return|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"200003": {
|
| 44 |
+
"content": "<|constrain|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"200004": {
|
| 52 |
+
"content": "<|reserved_200004|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"200005": {
|
| 60 |
+
"content": "<|channel|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"200006": {
|
| 68 |
+
"content": "<|start|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"200007": {
|
| 76 |
+
"content": "<|end|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"200008": {
|
| 84 |
+
"content": "<|message|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"200009": {
|
| 92 |
+
"content": "<|reserved_200009|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"200010": {
|
| 100 |
+
"content": "<|reserved_200010|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"200011": {
|
| 108 |
+
"content": "<|reserved_200011|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"200012": {
|
| 116 |
+
"content": "<|call|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"200013": {
|
| 124 |
+
"content": "<|reserved_200013|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"200014": {
|
| 132 |
+
"content": "<|reserved_200014|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"200015": {
|
| 140 |
+
"content": "<|reserved_200015|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"200016": {
|
| 148 |
+
"content": "<|reserved_200016|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"200017": {
|
| 156 |
+
"content": "<|reserved_200017|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"200018": {
|
| 164 |
+
"content": "<|endofprompt|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
}
|
| 171 |
+
},
|
| 172 |
+
"bos_token": "<|startoftext|>",
|
| 173 |
+
"clean_up_tokenization_spaces": false,
|
| 174 |
+
"eos_token": "<|return|>",
|
| 175 |
+
"extra_special_tokens": {},
|
| 176 |
+
"model_input_names": [
|
| 177 |
+
"input_ids",
|
| 178 |
+
"attention_mask"
|
| 179 |
+
],
|
| 180 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 181 |
+
"pad_token": "<|endoftext|>",
|
| 182 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 183 |
+
}
|