Duplicate from n0kovo/Hermes-4.3-36B-heretic
Browse filesCo-authored-by: n0kovo <n0kovo@users.noreply.huggingface.co>
- .gitattributes +36 -0
- README.md +270 -0
- chat_template.jinja +76 -0
- config.json +34 -0
- generation_config.json +7 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +779 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1051 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,270 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: ByteDance-Seed/Seed-OSS-36B-Base
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
license: apache-2.0
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
tags:
|
| 9 |
+
- Bytedance Seed
|
| 10 |
+
- instruct
|
| 11 |
+
- finetune
|
| 12 |
+
- reasoning
|
| 13 |
+
- hybrid-mode
|
| 14 |
+
- chatml
|
| 15 |
+
- function calling
|
| 16 |
+
- tool use
|
| 17 |
+
- json mode
|
| 18 |
+
- structured outputs
|
| 19 |
+
- atropos
|
| 20 |
+
- dataforge
|
| 21 |
+
- long context
|
| 22 |
+
- roleplaying
|
| 23 |
+
- chat
|
| 24 |
+
- heretic
|
| 25 |
+
- uncensored
|
| 26 |
+
- decensored
|
| 27 |
+
- abliterated
|
| 28 |
+
widget:
|
| 29 |
+
- example_title: Hermes 4
|
| 30 |
+
messages:
|
| 31 |
+
- role: system
|
| 32 |
+
content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise,
|
| 33 |
+
correct answers.
|
| 34 |
+
- role: user
|
| 35 |
+
content: Explain the difference between BFS and DFS to a new CS student.
|
| 36 |
+
model-index:
|
| 37 |
+
- name: Hermes-4.3-ByteDance-Seed-36B
|
| 38 |
+
results: []
|
| 39 |
+
---
|
| 40 |
+
# This is a decensored version of [NousResearch/Hermes-4.3-36B](https://huggingface.co/NousResearch/Hermes-4.3-36B), made using [Heretic](https://github.com/p-e-w/heretic) v1.1.0
|
| 41 |
+
|
| 42 |
+
## Abliteration parameters
|
| 43 |
+
|
| 44 |
+
| Parameter | Value |
|
| 45 |
+
| :-------- | :---: |
|
| 46 |
+
| **direction_index** | 49.62 |
|
| 47 |
+
| **attn.o_proj.max_weight** | 1.24 |
|
| 48 |
+
| **attn.o_proj.max_weight_position** | 38.57 |
|
| 49 |
+
| **attn.o_proj.min_weight** | 0.64 |
|
| 50 |
+
| **attn.o_proj.min_weight_distance** | 28.83 |
|
| 51 |
+
| **mlp.down_proj.max_weight** | 1.14 |
|
| 52 |
+
| **mlp.down_proj.max_weight_position** | 51.51 |
|
| 53 |
+
| **mlp.down_proj.min_weight** | 1.05 |
|
| 54 |
+
| **mlp.down_proj.min_weight_distance** | 29.86 |
|
| 55 |
+
|
| 56 |
+
## Performance
|
| 57 |
+
|
| 58 |
+
| Metric | This model | Original model ([NousResearch/Hermes-4.3-36B](https://huggingface.co/NousResearch/Hermes-4.3-36B)) |
|
| 59 |
+
| :----- | :--------: | :---------------------------: |
|
| 60 |
+
| **KL divergence** | 0.0273 | 0 *(by definition)* |
|
| 61 |
+
| **Refusals** | 4/100 | 78/100 |
|
| 62 |
+
|
| 63 |
+
-----
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
# Hermes 4.3 - Seed 36B
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
## Model Description
|
| 71 |
+
|
| 72 |
+
Hermes 4.3 36B is a frontier, hybrid-mode **reasoning** model based on ByteDance Seed 36B base, made by Nous Research that is aligned to **you**.
|
| 73 |
+
|
| 74 |
+
This is our first Hermes model trained in a decentralized manner over the internet using [Psyche](https://psyche.network), read the blog post: https://nousresearch.com/introducing-hermes-4-3/
|
| 75 |
+
|
| 76 |
+
Read the Hermes 4 technical report here: <a href="https://arxiv.org/abs/2508.18255">Hermes 4 Technical Report</a>
|
| 77 |
+
|
| 78 |
+
Chat with Hermes in Nous Chat: https://chat.nousresearch.com
|
| 79 |
+
|
| 80 |
+
Training highlights include a newly synthesized post-training corpus emphasizing verified reasoning traces, massive improvements in math, code, STEM, logic, creativity, and format-faithful outputs, while preserving general assistant quality and broadly neutral alignment.
|
| 81 |
+
|
| 82 |
+
## What’s new vs Hermes 3
|
| 83 |
+
|
| 84 |
+
- **Post-training corpus**: Massively increased dataset size from 1M samples and 1.2B tokens to **~5M samples / ~60B tokens** blended across reasoning and non-reasoning data.
|
| 85 |
+
- **Hybrid reasoning mode** with explicit `<think>…</think>` segments when the model decides to deliberate, and options to make your responses faster when you want.
|
| 86 |
+
- **Reasoning** that is top quality, expressive, improves math, code, STEM, logic, and even creative writing and subjective responses.
|
| 87 |
+
- **Schema adherence & structured outputs**: trained to produce valid JSON for given schemas and to repair malformed objects.
|
| 88 |
+
- **Much easier to steer and align**: extreme improvements on steerability, especially on reduced refusal rates.
|
| 89 |
+
|
| 90 |
+
## Our Mission: Frontier Capabilities Aligned to You
|
| 91 |
+
|
| 92 |
+
In pursuit of the mission of producing models that are open, steerable and capable of producing the full range of human expression, while being able to be aligned to your values, we created a new benchmark, RefusalBench, that tests the models willingness to be helpful in a variety of scenarios commonly disallowed by closed and open models.
|
| 93 |
+
|
| 94 |
+
**Hermes 4.3 36B is now SOTA across non-abliterated models on the RefusalBench Leaderboard, surpassing our previous best of 59.5% on Hermes 4 70B**
|
| 95 |
+
### % of Questions Answered – RefusalBench
|
| 96 |
+
*(Average of 5 trials)*
|
| 97 |
+
| Model | % of Questions Answered |
|
| 98 |
+
| :--- | :--- |
|
| 99 |
+
| **Hermes 4.3 36B Non-Reasoning** | 74.60% |
|
| 100 |
+
| **Hermes 4.3 36B Reasoning** | 72.29% |
|
| 101 |
+
| Hermes 4 70B Reasoning | 59.50% |
|
| 102 |
+
| Hermes 4 405B Reasoning | 57.10% |
|
| 103 |
+
| grok4 | 51.30% |
|
| 104 |
+
| Hermes 4 70B | 49.07% |
|
| 105 |
+
| Hermes 4 405B | 43.20% |
|
| 106 |
+
| Qwen2.5 7B | 36.10% |
|
| 107 |
+
| Qwen3 235B Reasoning | 34.30% |
|
| 108 |
+
| DeepSeek V3 | 28.10% |
|
| 109 |
+
| Gemini 2.5 Pro | 24.23% |
|
| 110 |
+
| Llama 405B | 21.70% |
|
| 111 |
+
| Gemini 2.5 Flash | 19.13% |
|
| 112 |
+
| GPT4o | 17.67% |
|
| 113 |
+
| Sonnet 4 | 17.00% |
|
| 114 |
+
| GPT4-mini | 16.76% |
|
| 115 |
+
| R1 | 16.70% |
|
| 116 |
+
| cogito-v2-405B Reasoning| 15.40% |
|
| 117 |
+
| Opus 4.1 | 15.38% |
|
| 118 |
+
| Qwen3 235B | 15.30% |
|
| 119 |
+
| cogito-v2-405B | 14.94% |
|
| 120 |
+
| cogito-v2-405B | 12.10% |
|
| 121 |
+
| GPT 5 | 11.34% |
|
| 122 |
+
| gpt-oss 120B | 5.60% |
|
| 123 |
+
| gpt-oss 20B | 4.79% |
|
| 124 |
+
|
| 125 |
+
Hermes 4 achieves SOTA on RefusalBench across all popular closed and open models in being helpful and conforming to your values, without censorship.
|
| 126 |
+
|
| 127 |
+
## Benchmarks (Hermes 4.3 36B)
|
| 128 |
+
|
| 129 |
+
| | Hermes 4.3 36B Psyche | Hermes 4.3 36B Centralized | Hermes 4 70B Centralized |
|
| 130 |
+
| :--- | :--- | :--- | :--- |
|
| 131 |
+
| AIME 24 | 71.9 | 70.6 | 73.5 |
|
| 132 |
+
| AIME 25 | 69.3 | 66.8 | 67.4 |
|
| 133 |
+
| BBH | 86.4 | 84.7 | 87.8 |
|
| 134 |
+
| DROP | 83.5 | 81.6 | 85.0 |
|
| 135 |
+
| GPQA Diamond | 65.5 | 64.8 | 66.1 |
|
| 136 |
+
| IFEval | 77.9 | 73.9 | 78.7 |
|
| 137 |
+
| MATH-500 | 93.8 | 92.3 | 95.5 |
|
| 138 |
+
| MMLU | 87.7 | 86.5 | 88.4 |
|
| 139 |
+
| MMLU-Pro | 80.7 | 79.7 | 80.7 |
|
| 140 |
+
| MuSR | 69.7 | 64.7 | 70.4 |
|
| 141 |
+
| OBQA | 96.6 | 91.8 | 94.8 |
|
| 142 |
+
| SimpleQA | 6.0 | 5.6 | 17.9 |
|
| 143 |
+
|
| 144 |
+
## Prompt Format
|
| 145 |
+
|
| 146 |
+
Hermes 4 uses Llama-3-Chat format with role headers and special tags.
|
| 147 |
+
|
| 148 |
+
**Basic chat:**
|
| 149 |
+
```
|
| 150 |
+
<|start_header_id|>system<|end_header_id|>
|
| 151 |
+
|
| 152 |
+
You are Hermes 4. Be concise and helpful.<|eot_id|>
|
| 153 |
+
<|start_header_id|>user<|end_header_id|>
|
| 154 |
+
|
| 155 |
+
Explain the photoelectric effect simply.<|eot_id|>
|
| 156 |
+
<|start_header_id|>assistant<|end_header_id|>
|
| 157 |
+
```
|
| 158 |
+
|
| 159 |
+
### Reasoning mode
|
| 160 |
+
|
| 161 |
+
Reasoning mode can be activated with the chat template via the flag `thinking=True` or by using the following system prompt:
|
| 162 |
+
|
| 163 |
+
```
|
| 164 |
+
You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
|
| 165 |
+
```
|
| 166 |
+
|
| 167 |
+
Note that you can add any additional system instructions before or after this system message, and it will adjust the models policies, style, and effort of thinking, as well as its post-thinking style, format, identity, and more. You may also interleave the tool definition system message with the reasoning one.
|
| 168 |
+
|
| 169 |
+
When the model chooses to deliberate, it emits:
|
| 170 |
+
|
| 171 |
+
```
|
| 172 |
+
<|start_header_id|>assistant<|end_header_id|>
|
| 173 |
+
<think>
|
| 174 |
+
…model’s internal reasoning may appear here…
|
| 175 |
+
</think>
|
| 176 |
+
Final response starts here…<|eot_id|>
|
| 177 |
+
```
|
| 178 |
+
|
| 179 |
+
Additionally, we provide a flag to keep the content inbetween the `<think> ... </think>` that you can play with by setting `keep_cots=True`
|
| 180 |
+
|
| 181 |
+
|
| 182 |
+
## Function Calling & Tool Use
|
| 183 |
+
|
| 184 |
+
Hermes 4 supports function/tool calls *within* a single assistant turn, produced after it's reasoning:
|
| 185 |
+
|
| 186 |
+
**System message (example):**
|
| 187 |
+
|
| 188 |
+
```
|
| 189 |
+
<|start_header_id|>system<|end_header_id|>
|
| 190 |
+
You are a function-calling AI. Tools are provided inside <tools>…</tools>.
|
| 191 |
+
When appropriate, call a tool by emitting a <tool_call>{...}</tool_call> object.
|
| 192 |
+
After a tool responds (as <tool_response>), continue reasoning inside <think> and produce the final answer.
|
| 193 |
+
<tools>
|
| 194 |
+
{"type":"function","function":{"name":"get_weather","description":"Get weather by city","parameters":{"type":"object","properties":{"city":{"type":"string"}},"required":["city"]}}}
|
| 195 |
+
</tools><|eot_id|>
|
| 196 |
+
```
|
| 197 |
+
|
| 198 |
+
Note that you may also simply place tool definitions into the "tools:" field of your messages, and the chat template will parse and create the system prompt for you. This also works with reasoning mode for improved accuracy of tool use.
|
| 199 |
+
|
| 200 |
+
The model will then generate tool calls within `<tool_call> {tool_call} </tool_call>` tags, for easy parsing. The tool_call tags are also added tokens, so it makes it easy to parse while streaming! There are also automatic tool parsers built-in to VLLM and SGLang for Hermes, just set the tool parser in VLLM to `hermes` and in SGLang to `qwen25`.
|
| 201 |
+
|
| 202 |
+
## Inference Notes
|
| 203 |
+
|
| 204 |
+
- **Sampling defaults that work well:** `temperature=0.6, top_p=0.95, top_k=20`.
|
| 205 |
+
- **Template:** Use the Llama chat format for Hermes 4.3 36B, 70B, and 405B as shown above, or set `add_generation_prompt=True` when using `tokenizer.apply_chat_template(...)`.
|
| 206 |
+
|
| 207 |
+
### Transformers example
|
| 208 |
+
|
| 209 |
+
```python
|
| 210 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 211 |
+
import torch
|
| 212 |
+
|
| 213 |
+
model_id = "NousResearch/Hermes-4.3-36B"
|
| 214 |
+
|
| 215 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
| 216 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 217 |
+
model_id,
|
| 218 |
+
torch_dtype=torch.float16,
|
| 219 |
+
device_map="auto"
|
| 220 |
+
)
|
| 221 |
+
|
| 222 |
+
messages = [
|
| 223 |
+
{"role":"system","content":"You are Hermes 4. Be concise."},
|
| 224 |
+
{"role":"user","content":"Summarize CRISPR in 3 sentences."}
|
| 225 |
+
]
|
| 226 |
+
|
| 227 |
+
inputs = tokenizer.apply_chat_template(
|
| 228 |
+
messages, add_generation_prompt=True, return_tensors="pt"
|
| 229 |
+
).to(model.device)
|
| 230 |
+
|
| 231 |
+
outputs = model.generate(
|
| 232 |
+
**inputs, max_new_tokens=400, temperature=0.6, top_p=0.95, top_k=20, do_sample=True
|
| 233 |
+
)
|
| 234 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 235 |
+
```
|
| 236 |
+
|
| 237 |
+
For production serving on multi-GPU nodes, consider tensor parallel inference engines (e.g., SGLang/vLLM backends) with prefix caching.
|
| 238 |
+
|
| 239 |
+
## Inference Providers:
|
| 240 |
+
|
| 241 |
+
### Nous Portal:
|
| 242 |
+
|
| 243 |
+
<a href="https://portal.nousresearch.com"><img width=256 alt="chutes logo" src="https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/6YytY7N0mjCnBQvWo3qtv.png"></a>
|
| 244 |
+
|
| 245 |
+
### Chutes:
|
| 246 |
+
|
| 247 |
+
<a href="https://chutes.ai/app"><img width=256 alt="chutes logo" src="https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/l14AWPv6cSvaprpwK_IWY.png"></a>
|
| 248 |
+
|
| 249 |
+
# Quantized / Smaller Variants
|
| 250 |
+
|
| 251 |
+
Hermes 4 is available as BF16 original weights as well as BF16 as well as GGUF variants.
|
| 252 |
+
|
| 253 |
+
GGUF Verions (4, 5, 6, and 8bit): https://huggingface.co/NousResearch/Hermes-4.3-36B-GGUF
|
| 254 |
+
|
| 255 |
+
See the Hermes 4 collection to explore them all:
|
| 256 |
+
https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728
|
| 257 |
+
|
| 258 |
+
# How to cite
|
| 259 |
+
|
| 260 |
+
```bibtex
|
| 261 |
+
@misc{teknium2025hermes4technicalreport,
|
| 262 |
+
title={Hermes 4 Technical Report},
|
| 263 |
+
author={Ryan Teknium and Roger Jin and Jai Suphavadeeprasit and Dakota Mahan and Jeffrey Quesnelle and Joe Li and Chen Guang and Shannon Sands and Karan Malhotra},
|
| 264 |
+
year={2025},
|
| 265 |
+
eprint={2508.18255},
|
| 266 |
+
archivePrefix={arXiv},
|
| 267 |
+
primaryClass={cs.AI},
|
| 268 |
+
url={https://arxiv.org/abs/2508.18255},
|
| 269 |
+
}
|
| 270 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.' %}
|
| 2 |
+
{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %}
|
| 3 |
+
{%- if not thinking is defined %}{% set thinking = false %}{% endif %}
|
| 4 |
+
{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %}
|
| 5 |
+
{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %}
|
| 6 |
+
{%- if tools %}
|
| 7 |
+
{{- bos_token + '<|start_header_id|>system<|end_header_id|>\n' }}
|
| 8 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 9 |
+
{{- messages[0]['content'] }}
|
| 10 |
+
{%- else %}
|
| 11 |
+
{{- system_prompt }}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- "\n\n# Tools\n\nYou are a function calling AI model. You may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 14 |
+
{%- for tool in tools %}
|
| 15 |
+
{{- "\n" }}
|
| 16 |
+
{{- tool | tojson }}
|
| 17 |
+
{%- endfor %}
|
| 18 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": \"<function-name>\", \"arguments\": <args-json-object>}\n</tool_call><|eot_id|>" }}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 21 |
+
{{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] + '<|eot_id|>' }}
|
| 22 |
+
{%- else %}
|
| 23 |
+
{{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + system_prompt + '<|eot_id|>' }}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- for message in messages %}
|
| 27 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 28 |
+
{{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n\n' + message.content + '<|eot_id|>' }}
|
| 29 |
+
{%- elif (message.role == "assistant" and not message.tool_calls) %}
|
| 30 |
+
{{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }}
|
| 31 |
+
{%- if message.content %}
|
| 32 |
+
{%- set content = message['content'] -%}
|
| 33 |
+
{%- if thinking %}
|
| 34 |
+
{%- if not keep_cots %}
|
| 35 |
+
{%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- '\n' + content + '<|eot_id|>' }}
|
| 39 |
+
{%- endif %}
|
| 40 |
+
{%- elif message.role == "assistant" %}
|
| 41 |
+
{{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }}
|
| 42 |
+
{%- if message.content %}
|
| 43 |
+
{%- set content = message['content'] -%}
|
| 44 |
+
{%- if thinking %}
|
| 45 |
+
{%- if not keep_cots %}
|
| 46 |
+
{%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{{- '\n' + content }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- for tool_call in message.tool_calls %}
|
| 52 |
+
{%- if tool_call.function is defined %}
|
| 53 |
+
{%- set tool_call = tool_call.function %}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 56 |
+
{{- tool_call.name }}
|
| 57 |
+
{{- '", "arguments": ' }}
|
| 58 |
+
{{- tool_call.arguments | tojson }}
|
| 59 |
+
{{- '}\n</tool_call>' }}
|
| 60 |
+
{%- endfor %}
|
| 61 |
+
{{- '<|eot_id|>' }}
|
| 62 |
+
{%- elif message.role == "tool" %}
|
| 63 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 64 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{{- '\n<tool_response>\n' }}
|
| 67 |
+
{{- message.content }}
|
| 68 |
+
{{- '\n</tool_response>' }}
|
| 69 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 70 |
+
{{- '<|eot_id|>' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- endfor %}
|
| 74 |
+
{%- if add_generation_prompt %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 76 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SeedOssForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_out_bias": false,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"head_dim": 128,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 5120,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 27648,
|
| 16 |
+
"max_position_embeddings": 524288,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "seed_oss",
|
| 19 |
+
"num_attention_heads": 80,
|
| 20 |
+
"num_hidden_layers": 64,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"pretraining_tp": 1,
|
| 24 |
+
"residual_dropout": 0.0,
|
| 25 |
+
"rms_norm_eps": 1e-06,
|
| 26 |
+
"rope_scaling": {
|
| 27 |
+
"rope_type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 10000000.0,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"transformers_version": "4.57.3",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 155136
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.57.3"
|
| 7 |
+
}
|
model-00001-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e513b5b065d3f65f7993f7fd7f7496b1083ddc28a702938f702d5e993661a95e
|
| 3 |
+
size 4954686296
|
model-00002-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9cc85725b33510b41fa68869b40cd9f1857716485c587203dca3d80405b6c0
|
| 3 |
+
size 4991407840
|
model-00003-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb74356971589c58974c6fbe047c5312f9962f234026a68cfebad81f94d479e8
|
| 3 |
+
size 4834167328
|
model-00004-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fc341d68edc582a4bae93beabe4e5c6a35bb68710e0aed41fb04e16b65e1a09
|
| 3 |
+
size 4886550176
|
model-00005-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3970fee95ee3a07af44d0a4976d8544bb5904830a0ecea2028359f573b123acc
|
| 3 |
+
size 4834167360
|
model-00006-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad6cacb76ebe9251ba03ddfe2f2c36cf21b04ab652e6d1dc56aee172f90d926b
|
| 3 |
+
size 4886550176
|
model-00007-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08d7ee87a1156a485123bb0988eaaa824d72ccca43fea6e67911d64d1479f1a1
|
| 3 |
+
size 4834167360
|
model-00008-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2384563757ce0c977d05ba114afbe983ee901ccf59595ec08a95f6a5f3107433
|
| 3 |
+
size 4886550176
|
model-00009-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a98ab4712ac64ecce75881f9da54cf681ea3fadd2bc9bf75d8456eaee0be5d27
|
| 3 |
+
size 4834167360
|
model-00010-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6491b05e5bb857e325e1f3db96ec8cbfa028af41563ae229adf431a6fb3a4a67
|
| 3 |
+
size 4886550176
|
model-00011-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b40199b6527c2c261cbedacf6b9f7c3d67c35980c2c013e6fee51f9b263d2f65
|
| 3 |
+
size 4834167360
|
model-00012-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cbc9c98948a80d727a1d3a42fea99ca1e4699ac86be58d2be6e44fe9cbd8a8b
|
| 3 |
+
size 4886550176
|
model-00013-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54a5db799d8b8fa21741b1ebe9f7ff01fb4c41ad42cc5a5615da38237c2bc343
|
| 3 |
+
size 4834167360
|
model-00014-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3770eb5204a84d91b9ce9de2f4b35143ccacd3cfefd71a545e7a46d02a5bec
|
| 3 |
+
size 4886550176
|
model-00015-of-00015.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb7673b13149d9cc540213a4563dad47bce9ec4e8626548044c75b0912b33e5b
|
| 3 |
+
size 4031898896
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,779 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 36151104512,
|
| 4 |
+
"total_size": 72302209024
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00015-of-00015.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
|
| 20 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 21 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 22 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 23 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 24 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 25 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
|
| 32 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 33 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 34 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 35 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 36 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 37 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
| 44 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 45 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 46 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 47 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 48 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 49 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
| 56 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 57 |
+
"model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 58 |
+
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 59 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 60 |
+
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 61 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
| 68 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 69 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 70 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 71 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 72 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 73 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
| 80 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 81 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 82 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 83 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 84 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 85 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
| 92 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 93 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 94 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
| 95 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 96 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 97 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
| 104 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 105 |
+
"model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 106 |
+
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 107 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
| 108 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
| 109 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
| 116 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
| 117 |
+
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 118 |
+
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 119 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 120 |
+
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 121 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
| 128 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 129 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 130 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 131 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 132 |
+
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 133 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
| 140 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 141 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 142 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 143 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 144 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 145 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
| 152 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 153 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 154 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
| 155 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
| 156 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
| 157 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
|
| 164 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 165 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 166 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
| 167 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
| 168 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
| 169 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
| 176 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 177 |
+
"model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 178 |
+
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 179 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 180 |
+
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 181 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
| 188 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
| 189 |
+
"model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 190 |
+
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 191 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 192 |
+
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 193 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
| 200 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 201 |
+
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 202 |
+
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 203 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 204 |
+
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 205 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
| 212 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 213 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 214 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
| 215 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 216 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 217 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
| 224 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 225 |
+
"model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 226 |
+
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 227 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
| 228 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
| 229 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
| 236 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
| 237 |
+
"model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 238 |
+
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 239 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 240 |
+
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 241 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
| 248 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 249 |
+
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 250 |
+
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 251 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 252 |
+
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 253 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
| 260 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 261 |
+
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 262 |
+
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 263 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 264 |
+
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 265 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
| 272 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 273 |
+
"model.layers.29.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 274 |
+
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
| 275 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
| 276 |
+
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
| 277 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
| 284 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 285 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 286 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 287 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 288 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 289 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00015.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00015.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00015.safetensors",
|
| 296 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
| 297 |
+
"model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 298 |
+
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 299 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 300 |
+
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 301 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
| 308 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
| 309 |
+
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 310 |
+
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 311 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 312 |
+
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 313 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
| 320 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 321 |
+
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 322 |
+
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 323 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 324 |
+
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 325 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
| 332 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 333 |
+
"model.layers.33.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 334 |
+
"model.layers.33.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
| 335 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 336 |
+
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 337 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
| 344 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 345 |
+
"model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 346 |
+
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 347 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
| 348 |
+
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
| 349 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
| 356 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
| 357 |
+
"model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 358 |
+
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 359 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 360 |
+
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 361 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
| 368 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 369 |
+
"model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 370 |
+
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 371 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 372 |
+
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 373 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
| 380 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 381 |
+
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 382 |
+
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 383 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 384 |
+
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 385 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
| 392 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 393 |
+
"model.layers.38.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 394 |
+
"model.layers.38.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
| 395 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
| 396 |
+
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
| 397 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
| 404 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 405 |
+
"model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 406 |
+
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 407 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 408 |
+
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 409 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
| 416 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
| 417 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 418 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 419 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 420 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 421 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
| 428 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 429 |
+
"model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 430 |
+
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 431 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 432 |
+
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 433 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
| 440 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 441 |
+
"model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 442 |
+
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 443 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 444 |
+
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 445 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
| 452 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 453 |
+
"model.layers.42.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 454 |
+
"model.layers.42.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
| 455 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 456 |
+
"model.layers.42.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 457 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
| 464 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 465 |
+
"model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 466 |
+
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 467 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
| 468 |
+
"model.layers.43.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
| 469 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
| 476 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
| 477 |
+
"model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 478 |
+
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 479 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 480 |
+
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 481 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
| 488 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 489 |
+
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 490 |
+
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 491 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 492 |
+
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 493 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
| 500 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 501 |
+
"model.layers.46.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 502 |
+
"model.layers.46.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 503 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 504 |
+
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 505 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
| 512 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 513 |
+
"model.layers.47.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 514 |
+
"model.layers.47.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
| 515 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
| 516 |
+
"model.layers.47.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
| 517 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
| 524 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 525 |
+
"model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 526 |
+
"model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 527 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 528 |
+
"model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 529 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 530 |
+
"model.layers.48.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
| 531 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
| 532 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
| 533 |
+
"model.layers.48.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
| 534 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
| 535 |
+
"model.layers.48.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
| 536 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
| 537 |
+
"model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 538 |
+
"model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 539 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 540 |
+
"model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 541 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 542 |
+
"model.layers.49.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
| 543 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 544 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 545 |
+
"model.layers.49.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
| 546 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 547 |
+
"model.layers.49.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
| 548 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 549 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 550 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 551 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 552 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 553 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 554 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
| 555 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 556 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 557 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
| 558 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 559 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
| 560 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 561 |
+
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 562 |
+
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 563 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 564 |
+
"model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 565 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 566 |
+
"model.layers.50.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
| 567 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 568 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 569 |
+
"model.layers.50.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
| 570 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 571 |
+
"model.layers.50.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
| 572 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 573 |
+
"model.layers.51.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 574 |
+
"model.layers.51.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
| 575 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 576 |
+
"model.layers.51.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 577 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
| 578 |
+
"model.layers.51.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
| 579 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 580 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 581 |
+
"model.layers.51.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
| 582 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 583 |
+
"model.layers.51.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
| 584 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 585 |
+
"model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 586 |
+
"model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 587 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
| 588 |
+
"model.layers.52.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
| 589 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 590 |
+
"model.layers.52.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
| 591 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
| 592 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
| 593 |
+
"model.layers.52.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
| 594 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
| 595 |
+
"model.layers.52.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
| 596 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
| 597 |
+
"model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 598 |
+
"model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 599 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 600 |
+
"model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 601 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 602 |
+
"model.layers.53.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
| 603 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 604 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 605 |
+
"model.layers.53.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
| 606 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 607 |
+
"model.layers.53.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
| 608 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 609 |
+
"model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 610 |
+
"model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 611 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 612 |
+
"model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 613 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 614 |
+
"model.layers.54.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
| 615 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 616 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 617 |
+
"model.layers.54.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
| 618 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 619 |
+
"model.layers.54.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
| 620 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 621 |
+
"model.layers.55.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 622 |
+
"model.layers.55.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 623 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 624 |
+
"model.layers.55.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 625 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 626 |
+
"model.layers.55.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
| 627 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 628 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 629 |
+
"model.layers.55.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
| 630 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 631 |
+
"model.layers.55.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
| 632 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 633 |
+
"model.layers.56.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 634 |
+
"model.layers.56.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
| 635 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
| 636 |
+
"model.layers.56.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
| 637 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
| 638 |
+
"model.layers.56.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
| 639 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 640 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 641 |
+
"model.layers.56.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
| 642 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 643 |
+
"model.layers.56.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
| 644 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 645 |
+
"model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 646 |
+
"model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 647 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 648 |
+
"model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 649 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 650 |
+
"model.layers.57.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
| 651 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
| 652 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
| 653 |
+
"model.layers.57.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
| 654 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
| 655 |
+
"model.layers.57.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
| 656 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
| 657 |
+
"model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 658 |
+
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 659 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 660 |
+
"model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 661 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 662 |
+
"model.layers.58.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
| 663 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 664 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 665 |
+
"model.layers.58.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
| 666 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 667 |
+
"model.layers.58.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
| 668 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 669 |
+
"model.layers.59.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 670 |
+
"model.layers.59.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 671 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 672 |
+
"model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 673 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 674 |
+
"model.layers.59.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
| 675 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 676 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 677 |
+
"model.layers.59.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
| 678 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 679 |
+
"model.layers.59.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
| 680 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 681 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 682 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
| 683 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 684 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 685 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
| 686 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
| 687 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 688 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 689 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
| 690 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 691 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
| 692 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 693 |
+
"model.layers.60.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 694 |
+
"model.layers.60.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
| 695 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 696 |
+
"model.layers.60.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 697 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
| 698 |
+
"model.layers.60.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
| 699 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 700 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 701 |
+
"model.layers.60.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
| 702 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 703 |
+
"model.layers.60.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
| 704 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 705 |
+
"model.layers.61.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 706 |
+
"model.layers.61.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
| 707 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
| 708 |
+
"model.layers.61.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
| 709 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 710 |
+
"model.layers.61.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
| 711 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
| 712 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
| 713 |
+
"model.layers.61.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
| 714 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
| 715 |
+
"model.layers.61.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
| 716 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
| 717 |
+
"model.layers.62.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 718 |
+
"model.layers.62.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
| 719 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
|
| 720 |
+
"model.layers.62.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
|
| 721 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 722 |
+
"model.layers.62.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
|
| 723 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
|
| 724 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
|
| 725 |
+
"model.layers.62.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
|
| 726 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
|
| 727 |
+
"model.layers.62.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
|
| 728 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
|
| 729 |
+
"model.layers.63.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 730 |
+
"model.layers.63.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
| 731 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
|
| 732 |
+
"model.layers.63.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
|
| 733 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
| 734 |
+
"model.layers.63.self_attn.k_proj.bias": "model-00015-of-00015.safetensors",
|
| 735 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
|
| 736 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
|
| 737 |
+
"model.layers.63.self_attn.q_proj.bias": "model-00015-of-00015.safetensors",
|
| 738 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
|
| 739 |
+
"model.layers.63.self_attn.v_proj.bias": "model-00015-of-00015.safetensors",
|
| 740 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
|
| 741 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 742 |
+
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 743 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
| 744 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
| 745 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 746 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
| 747 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
| 748 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
| 749 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
| 750 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
| 751 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
| 752 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
| 753 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 754 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 755 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 756 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 757 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 758 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
| 759 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 760 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 761 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
| 762 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 763 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
| 764 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 765 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 766 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
| 767 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
| 768 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
| 769 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
| 770 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
| 771 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
| 772 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
| 773 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
| 774 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
| 775 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
| 776 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
| 777 |
+
"model.norm.weight": "model-00015-of-00015.safetensors"
|
| 778 |
+
}
|
| 779 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<seed:bos>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<seed:pad>",
|
| 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 sha256:6b956359a482606190190eb1b76e9472b192edf978e003c7f92f9df4d92df30f
|
| 3 |
+
size 11884224
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1051 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<seed:bos>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<seed:pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<seed:eos>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<seed:think>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "</seed:think>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<seed:cot_budget_reflect>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "</seed:cot_budget_reflect>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"14": {
|
| 60 |
+
"content": "<[PLHD14_never_used]>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"15": {
|
| 68 |
+
"content": "<[PLHD15_never_used]>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"16": {
|
| 76 |
+
"content": "<[PLHD16_never_used]>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"17": {
|
| 84 |
+
"content": "<[PLHD17_never_used]>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"18": {
|
| 92 |
+
"content": "<[PLHD18_never_used]>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"19": {
|
| 100 |
+
"content": "<[PLHD19_never_used]>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"20": {
|
| 108 |
+
"content": "<[PLHD20_never_used]>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"21": {
|
| 116 |
+
"content": "<[PLHD21_never_used]>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"22": {
|
| 124 |
+
"content": "<[PLHD22_never_used]>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"23": {
|
| 132 |
+
"content": "<[PLHD23_never_used]>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"24": {
|
| 140 |
+
"content": "<[PLHD24_never_used]>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"25": {
|
| 148 |
+
"content": "<[PLHD25_never_used]>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"26": {
|
| 156 |
+
"content": "<[PLHD26_never_used]>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"27": {
|
| 164 |
+
"content": "<[PLHD27_never_used]>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"28": {
|
| 172 |
+
"content": "<[PLHD28_never_used]>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"29": {
|
| 180 |
+
"content": "<[PLHD29_never_used]>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"30": {
|
| 188 |
+
"content": "<[PLHD30_never_used]>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"31": {
|
| 196 |
+
"content": "<[PLHD31_never_used]>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32": {
|
| 204 |
+
"content": "<[PLHD32_never_used]>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"33": {
|
| 212 |
+
"content": "<[PLHD33_never_used]>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"34": {
|
| 220 |
+
"content": "<[PLHD34_never_used]>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"35": {
|
| 228 |
+
"content": "<[PLHD35_never_used]>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"36": {
|
| 236 |
+
"content": "<[PLHD36_never_used]>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"37": {
|
| 244 |
+
"content": "<[PLHD37_never_used]>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"38": {
|
| 252 |
+
"content": "<[PLHD38_never_used]>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"39": {
|
| 260 |
+
"content": "<[PLHD39_never_used]>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"40": {
|
| 268 |
+
"content": "<[PLHD40_never_used]>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"41": {
|
| 276 |
+
"content": "<[PLHD41_never_used]>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"42": {
|
| 284 |
+
"content": "<[PLHD42_never_used]>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"43": {
|
| 292 |
+
"content": "<[PLHD43_never_used]>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"44": {
|
| 300 |
+
"content": "<[PLHD44_never_used]>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"45": {
|
| 308 |
+
"content": "<[PLHD45_never_used]>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"46": {
|
| 316 |
+
"content": "<[PLHD46_never_used]>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"47": {
|
| 324 |
+
"content": "<[PLHD47_never_used]>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"48": {
|
| 332 |
+
"content": "<[PLHD48_never_used]>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"49": {
|
| 340 |
+
"content": "<[PLHD49_never_used]>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"50": {
|
| 348 |
+
"content": "<[PLHD50_never_used]>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"51": {
|
| 356 |
+
"content": "<[PLHD51_never_used]>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"52": {
|
| 364 |
+
"content": "<[PLHD52_never_used]>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"53": {
|
| 372 |
+
"content": "<[PLHD53_never_used]>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"54": {
|
| 380 |
+
"content": "<[PLHD54_never_used]>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"55": {
|
| 388 |
+
"content": "<[PLHD55_never_used]>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"56": {
|
| 396 |
+
"content": "<[PLHD56_never_used]>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"57": {
|
| 404 |
+
"content": "<[PLHD57_never_used]>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"58": {
|
| 412 |
+
"content": "<[PLHD58_never_used]>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"59": {
|
| 420 |
+
"content": "<[PLHD59_never_used]>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"60": {
|
| 428 |
+
"content": "<[PLHD60_never_used]>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"61": {
|
| 436 |
+
"content": "<[PLHD61_never_used]>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"62": {
|
| 444 |
+
"content": "<[PLHD62_never_used]>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"63": {
|
| 452 |
+
"content": "<[PLHD63_never_used]>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"64": {
|
| 460 |
+
"content": "<[PLHD64_never_used]>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"65": {
|
| 468 |
+
"content": "<[PLHD65_never_used]>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"66": {
|
| 476 |
+
"content": "<[PLHD66_never_used]>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"67": {
|
| 484 |
+
"content": "<[PLHD67_never_used]>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"68": {
|
| 492 |
+
"content": "<[PLHD68_never_used]>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"69": {
|
| 500 |
+
"content": "<[PLHD69_never_used]>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"70": {
|
| 508 |
+
"content": "<[PLHD70_never_used]>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"71": {
|
| 516 |
+
"content": "<[PLHD71_never_used]>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"72": {
|
| 524 |
+
"content": "<[PLHD72_never_used]>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"73": {
|
| 532 |
+
"content": "<[PLHD73_never_used]>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"74": {
|
| 540 |
+
"content": "<[PLHD74_never_used]>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"75": {
|
| 548 |
+
"content": "<[PLHD75_never_used]>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"76": {
|
| 556 |
+
"content": "<[PLHD76_never_used]>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"77": {
|
| 564 |
+
"content": "<[PLHD77_never_used]>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"78": {
|
| 572 |
+
"content": "<[PLHD78_never_used]>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"79": {
|
| 580 |
+
"content": "<[PLHD79_never_used]>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"80": {
|
| 588 |
+
"content": "<[PLHD80_never_used]>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"81": {
|
| 596 |
+
"content": "<[PLHD81_never_used]>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"82": {
|
| 604 |
+
"content": "<[PLHD82_never_used]>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"83": {
|
| 612 |
+
"content": "<[PLHD83_never_used]>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"84": {
|
| 620 |
+
"content": "<[PLHD84_never_used]>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"85": {
|
| 628 |
+
"content": "<[PLHD85_never_used]>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"86": {
|
| 636 |
+
"content": "<[PLHD86_never_used]>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"87": {
|
| 644 |
+
"content": "<[PLHD87_never_used]>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"88": {
|
| 652 |
+
"content": "<[PLHD88_never_used]>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"89": {
|
| 660 |
+
"content": "<[PLHD89_never_used]>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"90": {
|
| 668 |
+
"content": "<[PLHD90_never_used]>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"91": {
|
| 676 |
+
"content": "<[PLHD91_never_used]>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"92": {
|
| 684 |
+
"content": "<[PLHD92_never_used]>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"93": {
|
| 692 |
+
"content": "<[PLHD93_never_used]>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"94": {
|
| 700 |
+
"content": "<[PLHD94_never_used]>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"95": {
|
| 708 |
+
"content": "<[PLHD95_never_used]>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"96": {
|
| 716 |
+
"content": "<[PLHD96_never_used]>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"97": {
|
| 724 |
+
"content": "<[PLHD97_never_used]>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"98": {
|
| 732 |
+
"content": "<[PLHD98_never_used]>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"99": {
|
| 740 |
+
"content": "<[PLHD99_never_used]>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"100": {
|
| 748 |
+
"content": "<[PLHD100_never_used]>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"101": {
|
| 756 |
+
"content": "<[PLHD101_never_used]>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"102": {
|
| 764 |
+
"content": "<[PLHD102_never_used]>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"103": {
|
| 772 |
+
"content": "<[PLHD103_never_used]>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"104": {
|
| 780 |
+
"content": "<[PLHD104_never_used]>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"105": {
|
| 788 |
+
"content": "<[PLHD105_never_used]>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"106": {
|
| 796 |
+
"content": "<[PLHD106_never_used]>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"107": {
|
| 804 |
+
"content": "<[PLHD107_never_used]>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"108": {
|
| 812 |
+
"content": "<[PLHD108_never_used]>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"109": {
|
| 820 |
+
"content": "<[PLHD109_never_used]>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"110": {
|
| 828 |
+
"content": "<[PLHD110_never_used]>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"111": {
|
| 836 |
+
"content": "<[PLHD111_never_used]>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"112": {
|
| 844 |
+
"content": "<[PLHD112_never_used]>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"113": {
|
| 852 |
+
"content": "<[PLHD113_never_used]>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"114": {
|
| 860 |
+
"content": "<[PLHD114_never_used]>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"115": {
|
| 868 |
+
"content": "<[PLHD115_never_used]>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"116": {
|
| 876 |
+
"content": "<[PLHD116_never_used]>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"117": {
|
| 884 |
+
"content": "<[PLHD117_never_used]>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"118": {
|
| 892 |
+
"content": "<[PLHD118_never_used]>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"119": {
|
| 900 |
+
"content": "<[PLHD119_never_used]>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"120": {
|
| 908 |
+
"content": "<[PLHD120_never_used]>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"121": {
|
| 916 |
+
"content": "<[PLHD121_never_used]>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"122": {
|
| 924 |
+
"content": "<[PLHD122_never_used]>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"123": {
|
| 932 |
+
"content": "<[PLHD123_never_used]>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"124": {
|
| 940 |
+
"content": "<[PLHD124_never_used]>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"125": {
|
| 948 |
+
"content": "<[PLHD125_never_used]>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"126": {
|
| 956 |
+
"content": "<[PLHD126_never_used]>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"127": {
|
| 964 |
+
"content": "<[PLHD127_never_used]>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"155121": {
|
| 972 |
+
"content": "<tool_call>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": false
|
| 978 |
+
},
|
| 979 |
+
"155122": {
|
| 980 |
+
"content": "</tool_call>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": false
|
| 986 |
+
},
|
| 987 |
+
"155123": {
|
| 988 |
+
"content": "<tool_response>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": false
|
| 994 |
+
},
|
| 995 |
+
"155124": {
|
| 996 |
+
"content": "</tool_response>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": false
|
| 1002 |
+
},
|
| 1003 |
+
"155125": {
|
| 1004 |
+
"content": "<|start_header_id|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": false
|
| 1010 |
+
},
|
| 1011 |
+
"155126": {
|
| 1012 |
+
"content": "<|end_header_id|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": false
|
| 1018 |
+
},
|
| 1019 |
+
"155127": {
|
| 1020 |
+
"content": "<|eot_id|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"155128": {
|
| 1028 |
+
"content": "<think>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": false
|
| 1034 |
+
},
|
| 1035 |
+
"155129": {
|
| 1036 |
+
"content": "</think>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": false
|
| 1042 |
+
}
|
| 1043 |
+
},
|
| 1044 |
+
"bos_token": "<seed:bos>",
|
| 1045 |
+
"clean_up_tokenization_spaces": false,
|
| 1046 |
+
"eos_token": "<|eot_id|>",
|
| 1047 |
+
"extra_special_tokens": {},
|
| 1048 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1049 |
+
"pad_token": "<seed:pad>",
|
| 1050 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 1051 |
+
}
|