Commit
·
3576000
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse files- .gitattributes +37 -0
- README.md +234 -0
- added_tokens.json +28 -0
- chat_template.jinja +117 -0
- config.json +1892 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00017.safetensors +3 -0
- model-00002-of-00017.safetensors +3 -0
- model-00003-of-00017.safetensors +3 -0
- model-00004-of-00017.safetensors +3 -0
- model-00005-of-00017.safetensors +3 -0
- model-00006-of-00017.safetensors +3 -0
- model-00007-of-00017.safetensors +3 -0
- model-00008-of-00017.safetensors +3 -0
- model-00009-of-00017.safetensors +3 -0
- model-00010-of-00017.safetensors +3 -0
- model-00011-of-00017.safetensors +3 -0
- model-00012-of-00017.safetensors +3 -0
- model-00013-of-00017.safetensors +3 -0
- model-00014-of-00017.safetensors +3 -0
- model-00015-of-00017.safetensors +3 -0
- model-00016-of-00017.safetensors +3 -0
- model-00017-of-00017.safetensors +3 -0
- model.safetensors.index.json +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- qwen3_next
|
| 4 |
+
- unsloth
|
| 5 |
+
- qwen
|
| 6 |
+
- qwen3
|
| 7 |
+
base_model:
|
| 8 |
+
- Qwen/Qwen3-Coder-Next
|
| 9 |
+
library_name: transformers
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
license_link: https://huggingface.co/Qwen/Qwen3-Coder-Next/blob/main/LICENSE
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
---
|
| 14 |
+
<div>
|
| 15 |
+
<p style="margin-bottom: 0; margin-top: 0;">
|
| 16 |
+
<h1 style="margin-top: 0rem;">To Run Qwen3-Coder-Next locally - <a href="https://unsloth.ai/docs/models/qwen3-coder-next">Read our Guide!</a></h1>
|
| 17 |
+
</p>
|
| 18 |
+
<p style="margin-top: 0;margin-bottom: 0;">
|
| 19 |
+
<em><a href="https://unsloth.ai/docs/basics/unsloth-dynamic-2.0-ggufs">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
|
| 20 |
+
</p>
|
| 21 |
+
<div style="margin-top: 0;display: flex; gap: 5px; align-items: center; ">
|
| 22 |
+
<a href="https://github.com/unslothai/unsloth/">
|
| 23 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
|
| 24 |
+
</a>
|
| 25 |
+
<a href="https://discord.gg/unsloth">
|
| 26 |
+
<img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
|
| 27 |
+
</a>
|
| 28 |
+
<a href="https://unsloth.ai/docs/models/qwen3-coder-next">
|
| 29 |
+
<img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
|
| 30 |
+
</a>
|
| 31 |
+
</div>
|
| 32 |
+
</div>
|
| 33 |
+
|
| 34 |
+
# Qwen3-Coder-Next
|
| 35 |
+
|
| 36 |
+
## Highlights
|
| 37 |
+
|
| 38 |
+
Today, we're announcing **Qwen3-Coder-Next**, an open-weight language model designed specifically for coding agents and local development. It features the following key enhancements:
|
| 39 |
+
|
| 40 |
+
- **Super Efficient with Significant Performance**: With only 3B activated parameters (80B total parameters), it achieves performance comparable to models with 10–20x more active parameters, making it highly cost-effective for agent deployment.
|
| 41 |
+
- **Advanced Agentic Capabilities**: Through an elaborate training recipe, it excels at long-horizon reasoning, complex tool usage, and recovery from execution failures, ensuring robust performance in dynamic coding tasks.
|
| 42 |
+
- **Versatile Integration with Real-World IDE**: Its 256k context length, combined with adaptability to various scaffold templates, enables seamless integration with different CLI/IDE platforms (e.g., Claude Code, Qwen Code, Qoder, Kilo, Trae, Cline, etc.), supporting diverse development environments.
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
## Model Overview
|
| 49 |
+
|
| 50 |
+
**Qwen3-Coder-Next** has the following features:
|
| 51 |
+
- Type: Causal Language Models
|
| 52 |
+
- Training Stage: Pretraining & Post-training
|
| 53 |
+
- Number of Parameters: 80B in total and 3B activated
|
| 54 |
+
- Number of Parameters (Non-Embedding): 79B
|
| 55 |
+
- Hidden Dimension: 2048
|
| 56 |
+
- Number of Layers: 48
|
| 57 |
+
- Hybrid Layout: 12 \* (3 \* (Gated DeltaNet -> MoE) -> 1 \* (Gated Attention -> MoE))
|
| 58 |
+
- Gated Attention:
|
| 59 |
+
- Number of Attention Heads: 16 for Q and 2 for KV
|
| 60 |
+
- Head Dimension: 256
|
| 61 |
+
- Rotary Position Embedding Dimension: 64
|
| 62 |
+
- Gated DeltaNet:
|
| 63 |
+
- Number of Linear Attention Heads: 32 for V and 16 for QK
|
| 64 |
+
- Head Dimension: 128
|
| 65 |
+
- Mixture of Experts:
|
| 66 |
+
- Number of Experts: 512
|
| 67 |
+
- Number of Activated Experts: 10
|
| 68 |
+
- Number of Shared Experts: 1
|
| 69 |
+
- Expert Intermediate Dimension: 512
|
| 70 |
+
- Context Length: 262,144 natively
|
| 71 |
+
|
| 72 |
+
**NOTE: This model supports only non-thinking mode and does not generate ``<think></think>`` blocks in its output. Meanwhile, specifying `enable_thinking=False` is no longer required.**
|
| 73 |
+
|
| 74 |
+
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwen.ai/blog?id=qwen3-coder-next), [GitHub](https://github.com/QwenLM/Qwen3-Coder), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
## Quickstart
|
| 78 |
+
|
| 79 |
+
We advise you to use the latest version of `transformers`.
|
| 80 |
+
|
| 81 |
+
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
|
| 82 |
+
```python
|
| 83 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 84 |
+
|
| 85 |
+
model_name = "Qwen/Qwen3-Coder-Next"
|
| 86 |
+
|
| 87 |
+
# load the tokenizer and the model
|
| 88 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 89 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 90 |
+
model_name,
|
| 91 |
+
torch_dtype="auto",
|
| 92 |
+
device_map="auto"
|
| 93 |
+
)
|
| 94 |
+
|
| 95 |
+
# prepare the model input
|
| 96 |
+
prompt = "Write a quick sort algorithm."
|
| 97 |
+
messages = [
|
| 98 |
+
{"role": "user", "content": prompt}
|
| 99 |
+
]
|
| 100 |
+
text = tokenizer.apply_chat_template(
|
| 101 |
+
messages,
|
| 102 |
+
tokenize=False,
|
| 103 |
+
add_generation_prompt=True,
|
| 104 |
+
)
|
| 105 |
+
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 106 |
+
|
| 107 |
+
# conduct text completion
|
| 108 |
+
generated_ids = model.generate(
|
| 109 |
+
**model_inputs,
|
| 110 |
+
max_new_tokens=65536
|
| 111 |
+
)
|
| 112 |
+
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
| 113 |
+
|
| 114 |
+
content = tokenizer.decode(output_ids, skip_special_tokens=True)
|
| 115 |
+
|
| 116 |
+
print("content:", content)
|
| 117 |
+
```
|
| 118 |
+
|
| 119 |
+
**Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.**
|
| 120 |
+
|
| 121 |
+
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
|
| 122 |
+
|
| 123 |
+
## Deployment
|
| 124 |
+
|
| 125 |
+
For deployment, you can use the latest `sglang` or `vllm` to create an OpenAI-compatible API endpoint.
|
| 126 |
+
|
| 127 |
+
### SGLang
|
| 128 |
+
|
| 129 |
+
[SGLang](https://github.com/sgl-project/sglang) is a fast serving framework for large language models and vision language models.
|
| 130 |
+
SGLang could be used to launch a server with OpenAI-compatible API service.
|
| 131 |
+
|
| 132 |
+
`sglang>=v0.5.8` is required for Qwen3-Coder-Next, which can be installed using:
|
| 133 |
+
```shell
|
| 134 |
+
pip install 'sglang[all]>=v0.5.8'
|
| 135 |
+
```
|
| 136 |
+
See [its documentation](https://docs.sglang.ai/get_started/install.html) for more details.
|
| 137 |
+
|
| 138 |
+
The following command can be used to create an API endpoint at `http://localhost:30000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
|
| 139 |
+
```shell
|
| 140 |
+
python -m sglang.launch_server --model Qwen/Qwen3-Coder-Next --port 30000 --tp-size 2 --tool-call-parser qwen3_coder```
|
| 141 |
+
```
|
| 142 |
+
|
| 143 |
+
> [!Note]
|
| 144 |
+
> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
|
| 145 |
+
|
| 146 |
+
|
| 147 |
+
### vLLM
|
| 148 |
+
|
| 149 |
+
[vLLM](https://github.com/vllm-project/vllm) is a high-throughput and memory-efficient inference and serving engine for LLMs.
|
| 150 |
+
vLLM could be used to launch a server with OpenAI-compatible API service.
|
| 151 |
+
|
| 152 |
+
`vllm>=0.15.0` is required for Qwen3-Coder-Next, which can be installed using:
|
| 153 |
+
```shell
|
| 154 |
+
pip install 'vllm>=0.15.0'
|
| 155 |
+
```
|
| 156 |
+
See [its documentation](https://docs.vllm.ai/en/stable/getting_started/installation/index.html) for more details.
|
| 157 |
+
|
| 158 |
+
The following command can be used to create an API endpoint at `http://localhost:8000/v1` with maximum context length 256K tokens using tensor parallel on 4 GPUs.
|
| 159 |
+
```shell
|
| 160 |
+
vllm serve Qwen/Qwen3-Coder-Next --port 8000 --tensor-parallel-size 2 --enable-auto-tool-choice --tool-call-parser qwen3_coder
|
| 161 |
+
```
|
| 162 |
+
|
| 163 |
+
> [!Note]
|
| 164 |
+
> The default context length is 256K. Consider reducing the context length to a smaller value, e.g., `32768`, if the server fails to start.
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
## Agentic Coding
|
| 168 |
+
|
| 169 |
+
Qwen3-Coder-Next excels in tool calling capabilities.
|
| 170 |
+
|
| 171 |
+
You can simply define or use any tools as following example.
|
| 172 |
+
```python
|
| 173 |
+
# Your tool implementation
|
| 174 |
+
def square_the_number(num: float) -> dict:
|
| 175 |
+
return num ** 2
|
| 176 |
+
|
| 177 |
+
# Define Tools
|
| 178 |
+
tools=[
|
| 179 |
+
{
|
| 180 |
+
"type":"function",
|
| 181 |
+
"function":{
|
| 182 |
+
"name": "square_the_number",
|
| 183 |
+
"description": "output the square of the number.",
|
| 184 |
+
"parameters": {
|
| 185 |
+
"type": "object",
|
| 186 |
+
"required": ["input_num"],
|
| 187 |
+
"properties": {
|
| 188 |
+
'input_num': {
|
| 189 |
+
'type': 'number',
|
| 190 |
+
'description': 'input_num is a number that will be squared'
|
| 191 |
+
}
|
| 192 |
+
},
|
| 193 |
+
}
|
| 194 |
+
}
|
| 195 |
+
}
|
| 196 |
+
]
|
| 197 |
+
|
| 198 |
+
from openai import OpenAI
|
| 199 |
+
# Define LLM
|
| 200 |
+
client = OpenAI(
|
| 201 |
+
# Use a custom endpoint compatible with OpenAI API
|
| 202 |
+
base_url='http://localhost:8000/v1', # api_base
|
| 203 |
+
api_key="EMPTY"
|
| 204 |
+
)
|
| 205 |
+
|
| 206 |
+
messages = [{'role': 'user', 'content': 'square the number 1024'}]
|
| 207 |
+
|
| 208 |
+
completion = client.chat.completions.create(
|
| 209 |
+
messages=messages,
|
| 210 |
+
model="Qwen3-Coder-Next",
|
| 211 |
+
max_tokens=65536,
|
| 212 |
+
tools=tools,
|
| 213 |
+
)
|
| 214 |
+
|
| 215 |
+
print(completion.choices[0])
|
| 216 |
+
```
|
| 217 |
+
|
| 218 |
+
## Best Practices
|
| 219 |
+
|
| 220 |
+
To achieve optimal performance, we recommend the following sampling parameters: `temperature=1.0`, `top_p=0.95`, `top_k=40`.
|
| 221 |
+
|
| 222 |
+
|
| 223 |
+
## Citation
|
| 224 |
+
|
| 225 |
+
If you find our work helpful, feel free to give us a cite.
|
| 226 |
+
|
| 227 |
+
```
|
| 228 |
+
@techreport{qwen_qwen3_coder_next_tech_report,
|
| 229 |
+
title = {Qwen3-Coder-Next Technical Report},
|
| 230 |
+
author = {{Qwen Team}},
|
| 231 |
+
url = {https://github.com/QwenLM/Qwen3-Coder/blob/main/qwen3_coder_next_tech_report.pdf},
|
| 232 |
+
note = {Accessed: 2026-02-03}
|
| 233 |
+
}
|
| 234 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% macro render_extra_keys(json_dict, handled_keys) %}
|
| 2 |
+
{%- if json_dict is mapping %}
|
| 3 |
+
{%- for json_key in json_dict if json_key not in handled_keys %}
|
| 4 |
+
{%- if json_dict[json_key] is string %}
|
| 5 |
+
{{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
|
| 8 |
+
{%- endif %}
|
| 9 |
+
{%- endfor %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endmacro %}
|
| 12 |
+
|
| 13 |
+
{%- if messages[0]["role"] == "system" %}
|
| 14 |
+
{%- set system_message = messages[0]["content"] %}
|
| 15 |
+
{%- set loop_messages = messages[1:] %}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- set loop_messages = messages %}
|
| 18 |
+
{%- endif %}
|
| 19 |
+
|
| 20 |
+
{%- if not tools is defined %}
|
| 21 |
+
{%- set tools = [] %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
|
| 24 |
+
{%- if system_message is defined %}
|
| 25 |
+
{{- "<|im_start|>system\n" + system_message }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 28 |
+
{{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
|
| 29 |
+
{%- endif %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 32 |
+
{{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
|
| 33 |
+
{{- "<tools>" }}
|
| 34 |
+
{%- for tool in tools %}
|
| 35 |
+
{%- if tool.function is defined %}
|
| 36 |
+
{%- set tool = tool.function %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
|
| 39 |
+
{%- if tool.description is defined %}
|
| 40 |
+
{{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- '\n<parameters>' }}
|
| 43 |
+
{%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
|
| 44 |
+
{%- for param_name, param_fields in tool.parameters.properties|items %}
|
| 45 |
+
{{- '\n<parameter>' }}
|
| 46 |
+
{{- '\n<name>' ~ param_name ~ '</name>' }}
|
| 47 |
+
{%- if param_fields.type is defined %}
|
| 48 |
+
{{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- if param_fields.description is defined %}
|
| 51 |
+
{{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- set handled_keys = ['name', 'type', 'description'] %}
|
| 54 |
+
{{- render_extra_keys(param_fields, handled_keys) }}
|
| 55 |
+
{{- '\n</parameter>' }}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{%- set handled_keys = ['type', 'properties'] %}
|
| 59 |
+
{{- render_extra_keys(tool.parameters, handled_keys) }}
|
| 60 |
+
{{- '\n</parameters>' }}
|
| 61 |
+
{%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
|
| 62 |
+
{{- render_extra_keys(tool, handled_keys) }}
|
| 63 |
+
{{- '\n</function>' }}
|
| 64 |
+
{%- endfor %}
|
| 65 |
+
{{- "\n</tools>" }}
|
| 66 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- if system_message is defined %}
|
| 69 |
+
{{- '<|im_end|>\n' }}
|
| 70 |
+
{%- else %}
|
| 71 |
+
{%- if tools is iterable and tools | length > 0 %}
|
| 72 |
+
{{- '<|im_end|>\n' }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- for message in loop_messages %}
|
| 76 |
+
{%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
|
| 77 |
+
{{- '<|im_start|>' + message.role }}
|
| 78 |
+
{%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
|
| 79 |
+
{{- '\n' + message.content | trim + '\n' }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for tool_call in message.tool_calls %}
|
| 82 |
+
{%- if tool_call.function is defined %}
|
| 83 |
+
{%- set tool_call = tool_call.function %}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 86 |
+
{%- if tool_call.arguments is defined %}
|
| 87 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 88 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 89 |
+
{%- set args_value = args_value if args_value is string else args_value | tojson | safe %}
|
| 90 |
+
{{- args_value }}
|
| 91 |
+
{{- '\n</parameter>\n' }}
|
| 92 |
+
{%- endfor %}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '</function>\n</tool_call>' }}
|
| 95 |
+
{%- endfor %}
|
| 96 |
+
{{- '<|im_end|>\n' }}
|
| 97 |
+
{%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
|
| 98 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 99 |
+
{%- elif message.role == "tool" %}
|
| 100 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 101 |
+
{{- '<|im_start|>user' }}
|
| 102 |
+
{%- endif %}
|
| 103 |
+
{{- '\n<tool_response>\n' }}
|
| 104 |
+
{{- message.content }}
|
| 105 |
+
{{- '\n</tool_response>' }}
|
| 106 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 107 |
+
{{- '<|im_end|>\n' }}
|
| 108 |
+
{%- elif loop.last %}
|
| 109 |
+
{{- '<|im_end|>\n' }}
|
| 110 |
+
{%- endif %}
|
| 111 |
+
{%- else %}
|
| 112 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
|
| 113 |
+
{%- endif %}
|
| 114 |
+
{%- endfor %}
|
| 115 |
+
{%- if add_generation_prompt %}
|
| 116 |
+
{{- '<|im_start|>assistant\n' }}
|
| 117 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,1892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3NextForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"decoder_sparse_step": 1,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 151645,
|
| 10 |
+
"full_attention_interval": 4,
|
| 11 |
+
"head_dim": 256,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 5120,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"linear_attention",
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"full_attention"
|
| 65 |
+
],
|
| 66 |
+
"linear_conv_kernel_dim": 4,
|
| 67 |
+
"linear_key_head_dim": 128,
|
| 68 |
+
"linear_num_key_heads": 16,
|
| 69 |
+
"linear_num_value_heads": 32,
|
| 70 |
+
"linear_value_head_dim": 128,
|
| 71 |
+
"max_position_embeddings": 262144,
|
| 72 |
+
"mlp_only_layers": [],
|
| 73 |
+
"model_type": "qwen3_next",
|
| 74 |
+
"moe_intermediate_size": 512,
|
| 75 |
+
"norm_topk_prob": true,
|
| 76 |
+
"num_attention_heads": 16,
|
| 77 |
+
"num_experts": 512,
|
| 78 |
+
"num_experts_per_tok": 10,
|
| 79 |
+
"num_hidden_layers": 48,
|
| 80 |
+
"num_key_value_heads": 2,
|
| 81 |
+
"output_router_logits": false,
|
| 82 |
+
"pad_token_id": 151654,
|
| 83 |
+
"partial_rotary_factor": 0.25,
|
| 84 |
+
"quantization_config": {
|
| 85 |
+
"config_groups": {
|
| 86 |
+
"group_0": {
|
| 87 |
+
"format": "float-quantized",
|
| 88 |
+
"input_activations": {
|
| 89 |
+
"actorder": null,
|
| 90 |
+
"block_structure": null,
|
| 91 |
+
"dynamic": true,
|
| 92 |
+
"group_size": null,
|
| 93 |
+
"num_bits": 8,
|
| 94 |
+
"observer": null,
|
| 95 |
+
"observer_kwargs": {},
|
| 96 |
+
"scale_dtype": null,
|
| 97 |
+
"strategy": "token",
|
| 98 |
+
"symmetric": true,
|
| 99 |
+
"type": "float",
|
| 100 |
+
"zp_dtype": null
|
| 101 |
+
},
|
| 102 |
+
"output_activations": null,
|
| 103 |
+
"targets": [
|
| 104 |
+
"Linear"
|
| 105 |
+
],
|
| 106 |
+
"weights": {
|
| 107 |
+
"actorder": null,
|
| 108 |
+
"block_structure": null,
|
| 109 |
+
"dynamic": false,
|
| 110 |
+
"group_size": null,
|
| 111 |
+
"num_bits": 8,
|
| 112 |
+
"observer": "memoryless_minmax",
|
| 113 |
+
"observer_kwargs": {},
|
| 114 |
+
"scale_dtype": null,
|
| 115 |
+
"strategy": "channel",
|
| 116 |
+
"symmetric": true,
|
| 117 |
+
"type": "float",
|
| 118 |
+
"zp_dtype": null
|
| 119 |
+
}
|
| 120 |
+
}
|
| 121 |
+
},
|
| 122 |
+
"format": "float-quantized",
|
| 123 |
+
"global_compression_ratio": null,
|
| 124 |
+
"ignore": [
|
| 125 |
+
"model.layers.0.linear_attn.in_proj_qkvz",
|
| 126 |
+
"model.layers.0.linear_attn.in_proj_ba",
|
| 127 |
+
"model.layers.0.linear_attn.out_proj",
|
| 128 |
+
"model.layers.0.mlp.gate",
|
| 129 |
+
"model.layers.0.mlp.shared_expert_gate",
|
| 130 |
+
"model.layers.1.linear_attn.in_proj_qkvz",
|
| 131 |
+
"model.layers.1.linear_attn.in_proj_ba",
|
| 132 |
+
"model.layers.1.linear_attn.out_proj",
|
| 133 |
+
"model.layers.1.mlp.gate",
|
| 134 |
+
"model.layers.1.mlp.shared_expert_gate",
|
| 135 |
+
"model.layers.2.linear_attn.in_proj_qkvz",
|
| 136 |
+
"model.layers.2.linear_attn.in_proj_ba",
|
| 137 |
+
"model.layers.2.linear_attn.out_proj",
|
| 138 |
+
"model.layers.2.mlp.gate",
|
| 139 |
+
"model.layers.2.mlp.shared_expert_gate",
|
| 140 |
+
"model.layers.3.mlp.gate",
|
| 141 |
+
"model.layers.3.mlp.shared_expert_gate",
|
| 142 |
+
"model.layers.4.linear_attn.in_proj_qkvz",
|
| 143 |
+
"model.layers.4.linear_attn.in_proj_ba",
|
| 144 |
+
"model.layers.4.linear_attn.out_proj",
|
| 145 |
+
"model.layers.4.mlp.gate",
|
| 146 |
+
"model.layers.4.mlp.shared_expert_gate",
|
| 147 |
+
"model.layers.5.linear_attn.in_proj_qkvz",
|
| 148 |
+
"model.layers.5.linear_attn.in_proj_ba",
|
| 149 |
+
"model.layers.5.linear_attn.out_proj",
|
| 150 |
+
"model.layers.5.mlp.gate",
|
| 151 |
+
"model.layers.5.mlp.shared_expert_gate",
|
| 152 |
+
"model.layers.6.linear_attn.in_proj_qkvz",
|
| 153 |
+
"model.layers.6.linear_attn.in_proj_ba",
|
| 154 |
+
"model.layers.6.linear_attn.out_proj",
|
| 155 |
+
"model.layers.6.mlp.gate",
|
| 156 |
+
"model.layers.6.mlp.shared_expert_gate",
|
| 157 |
+
"model.layers.7.mlp.gate",
|
| 158 |
+
"model.layers.7.mlp.shared_expert_gate",
|
| 159 |
+
"model.layers.8.linear_attn.in_proj_qkvz",
|
| 160 |
+
"model.layers.8.linear_attn.in_proj_ba",
|
| 161 |
+
"model.layers.8.linear_attn.out_proj",
|
| 162 |
+
"model.layers.8.mlp.gate",
|
| 163 |
+
"model.layers.8.mlp.shared_expert_gate",
|
| 164 |
+
"model.layers.9.linear_attn.in_proj_qkvz",
|
| 165 |
+
"model.layers.9.linear_attn.in_proj_ba",
|
| 166 |
+
"model.layers.9.linear_attn.out_proj",
|
| 167 |
+
"model.layers.9.mlp.gate",
|
| 168 |
+
"model.layers.9.mlp.shared_expert_gate",
|
| 169 |
+
"model.layers.10.linear_attn.in_proj_qkvz",
|
| 170 |
+
"model.layers.10.linear_attn.in_proj_ba",
|
| 171 |
+
"model.layers.10.linear_attn.out_proj",
|
| 172 |
+
"model.layers.10.mlp.gate",
|
| 173 |
+
"model.layers.10.mlp.shared_expert_gate",
|
| 174 |
+
"model.layers.11.mlp.gate",
|
| 175 |
+
"model.layers.11.mlp.shared_expert_gate",
|
| 176 |
+
"model.layers.12.linear_attn.in_proj_qkvz",
|
| 177 |
+
"model.layers.12.linear_attn.in_proj_ba",
|
| 178 |
+
"model.layers.12.linear_attn.out_proj",
|
| 179 |
+
"model.layers.12.mlp.gate",
|
| 180 |
+
"model.layers.12.mlp.shared_expert_gate",
|
| 181 |
+
"model.layers.13.linear_attn.in_proj_qkvz",
|
| 182 |
+
"model.layers.13.linear_attn.in_proj_ba",
|
| 183 |
+
"model.layers.13.linear_attn.out_proj",
|
| 184 |
+
"model.layers.13.mlp.gate",
|
| 185 |
+
"model.layers.13.mlp.shared_expert_gate",
|
| 186 |
+
"model.layers.14.linear_attn.in_proj_qkvz",
|
| 187 |
+
"model.layers.14.linear_attn.in_proj_ba",
|
| 188 |
+
"model.layers.14.linear_attn.out_proj",
|
| 189 |
+
"model.layers.14.mlp.gate",
|
| 190 |
+
"model.layers.14.mlp.shared_expert_gate",
|
| 191 |
+
"model.layers.15.mlp.gate",
|
| 192 |
+
"model.layers.15.mlp.shared_expert_gate",
|
| 193 |
+
"model.layers.16.linear_attn.in_proj_qkvz",
|
| 194 |
+
"model.layers.16.linear_attn.in_proj_ba",
|
| 195 |
+
"model.layers.16.linear_attn.out_proj",
|
| 196 |
+
"model.layers.16.mlp.gate",
|
| 197 |
+
"model.layers.16.mlp.shared_expert_gate",
|
| 198 |
+
"model.layers.17.linear_attn.in_proj_qkvz",
|
| 199 |
+
"model.layers.17.linear_attn.in_proj_ba",
|
| 200 |
+
"model.layers.17.linear_attn.out_proj",
|
| 201 |
+
"model.layers.17.mlp.gate",
|
| 202 |
+
"model.layers.17.mlp.shared_expert_gate",
|
| 203 |
+
"model.layers.18.linear_attn.in_proj_qkvz",
|
| 204 |
+
"model.layers.18.linear_attn.in_proj_ba",
|
| 205 |
+
"model.layers.18.linear_attn.out_proj",
|
| 206 |
+
"model.layers.18.mlp.gate",
|
| 207 |
+
"model.layers.18.mlp.shared_expert_gate",
|
| 208 |
+
"model.layers.19.mlp.gate",
|
| 209 |
+
"model.layers.19.mlp.shared_expert_gate",
|
| 210 |
+
"model.layers.20.linear_attn.in_proj_qkvz",
|
| 211 |
+
"model.layers.20.linear_attn.in_proj_ba",
|
| 212 |
+
"model.layers.20.linear_attn.out_proj",
|
| 213 |
+
"model.layers.20.mlp.gate",
|
| 214 |
+
"model.layers.20.mlp.shared_expert_gate",
|
| 215 |
+
"model.layers.21.linear_attn.in_proj_qkvz",
|
| 216 |
+
"model.layers.21.linear_attn.in_proj_ba",
|
| 217 |
+
"model.layers.21.linear_attn.out_proj",
|
| 218 |
+
"model.layers.21.mlp.gate",
|
| 219 |
+
"model.layers.21.mlp.shared_expert_gate",
|
| 220 |
+
"model.layers.22.linear_attn.in_proj_qkvz",
|
| 221 |
+
"model.layers.22.linear_attn.in_proj_ba",
|
| 222 |
+
"model.layers.22.linear_attn.out_proj",
|
| 223 |
+
"model.layers.22.mlp.gate",
|
| 224 |
+
"model.layers.22.mlp.shared_expert_gate",
|
| 225 |
+
"model.layers.23.mlp.gate",
|
| 226 |
+
"model.layers.23.mlp.shared_expert_gate",
|
| 227 |
+
"model.layers.24.linear_attn.in_proj_qkvz",
|
| 228 |
+
"model.layers.24.linear_attn.in_proj_ba",
|
| 229 |
+
"model.layers.24.linear_attn.out_proj",
|
| 230 |
+
"model.layers.24.mlp.gate",
|
| 231 |
+
"model.layers.24.mlp.shared_expert_gate",
|
| 232 |
+
"model.layers.25.linear_attn.in_proj_qkvz",
|
| 233 |
+
"model.layers.25.linear_attn.in_proj_ba",
|
| 234 |
+
"model.layers.25.linear_attn.out_proj",
|
| 235 |
+
"model.layers.25.mlp.gate",
|
| 236 |
+
"model.layers.25.mlp.shared_expert_gate",
|
| 237 |
+
"model.layers.26.linear_attn.in_proj_qkvz",
|
| 238 |
+
"model.layers.26.linear_attn.in_proj_ba",
|
| 239 |
+
"model.layers.26.linear_attn.out_proj",
|
| 240 |
+
"model.layers.26.mlp.gate",
|
| 241 |
+
"model.layers.26.mlp.shared_expert_gate",
|
| 242 |
+
"model.layers.27.mlp.gate",
|
| 243 |
+
"model.layers.27.mlp.shared_expert_gate",
|
| 244 |
+
"model.layers.28.linear_attn.in_proj_qkvz",
|
| 245 |
+
"model.layers.28.linear_attn.in_proj_ba",
|
| 246 |
+
"model.layers.28.linear_attn.out_proj",
|
| 247 |
+
"model.layers.28.mlp.gate",
|
| 248 |
+
"model.layers.28.mlp.shared_expert_gate",
|
| 249 |
+
"model.layers.29.linear_attn.in_proj_qkvz",
|
| 250 |
+
"model.layers.29.linear_attn.in_proj_ba",
|
| 251 |
+
"model.layers.29.linear_attn.out_proj",
|
| 252 |
+
"model.layers.29.mlp.gate",
|
| 253 |
+
"model.layers.29.mlp.shared_expert_gate",
|
| 254 |
+
"model.layers.30.linear_attn.in_proj_qkvz",
|
| 255 |
+
"model.layers.30.linear_attn.in_proj_ba",
|
| 256 |
+
"model.layers.30.linear_attn.out_proj",
|
| 257 |
+
"model.layers.30.mlp.gate",
|
| 258 |
+
"model.layers.30.mlp.shared_expert_gate",
|
| 259 |
+
"model.layers.31.mlp.gate",
|
| 260 |
+
"model.layers.31.mlp.shared_expert_gate",
|
| 261 |
+
"model.layers.32.linear_attn.in_proj_qkvz",
|
| 262 |
+
"model.layers.32.linear_attn.in_proj_ba",
|
| 263 |
+
"model.layers.32.linear_attn.out_proj",
|
| 264 |
+
"model.layers.32.mlp.gate",
|
| 265 |
+
"model.layers.32.mlp.shared_expert_gate",
|
| 266 |
+
"model.layers.33.linear_attn.in_proj_qkvz",
|
| 267 |
+
"model.layers.33.linear_attn.in_proj_ba",
|
| 268 |
+
"model.layers.33.linear_attn.out_proj",
|
| 269 |
+
"model.layers.33.mlp.gate",
|
| 270 |
+
"model.layers.33.mlp.shared_expert_gate",
|
| 271 |
+
"model.layers.34.linear_attn.in_proj_qkvz",
|
| 272 |
+
"model.layers.34.linear_attn.in_proj_ba",
|
| 273 |
+
"model.layers.34.linear_attn.out_proj",
|
| 274 |
+
"model.layers.34.mlp.gate",
|
| 275 |
+
"model.layers.34.mlp.shared_expert_gate",
|
| 276 |
+
"model.layers.35.mlp.gate",
|
| 277 |
+
"model.layers.35.mlp.shared_expert_gate",
|
| 278 |
+
"model.layers.36.linear_attn.in_proj_qkvz",
|
| 279 |
+
"model.layers.36.linear_attn.in_proj_ba",
|
| 280 |
+
"model.layers.36.linear_attn.out_proj",
|
| 281 |
+
"model.layers.36.mlp.gate",
|
| 282 |
+
"model.layers.36.mlp.shared_expert_gate",
|
| 283 |
+
"model.layers.37.linear_attn.in_proj_qkvz",
|
| 284 |
+
"model.layers.37.linear_attn.in_proj_ba",
|
| 285 |
+
"model.layers.37.linear_attn.out_proj",
|
| 286 |
+
"model.layers.37.mlp.gate",
|
| 287 |
+
"model.layers.37.mlp.shared_expert_gate",
|
| 288 |
+
"model.layers.38.linear_attn.in_proj_qkvz",
|
| 289 |
+
"model.layers.38.linear_attn.in_proj_ba",
|
| 290 |
+
"model.layers.38.linear_attn.out_proj",
|
| 291 |
+
"model.layers.38.mlp.gate",
|
| 292 |
+
"model.layers.38.mlp.shared_expert_gate",
|
| 293 |
+
"model.layers.39.mlp.gate",
|
| 294 |
+
"model.layers.39.mlp.shared_expert_gate",
|
| 295 |
+
"model.layers.40.linear_attn.in_proj_qkvz",
|
| 296 |
+
"model.layers.40.linear_attn.in_proj_ba",
|
| 297 |
+
"model.layers.40.linear_attn.out_proj",
|
| 298 |
+
"model.layers.40.mlp.gate",
|
| 299 |
+
"model.layers.40.mlp.shared_expert_gate",
|
| 300 |
+
"model.layers.41.linear_attn.in_proj_qkvz",
|
| 301 |
+
"model.layers.41.linear_attn.in_proj_ba",
|
| 302 |
+
"model.layers.41.linear_attn.out_proj",
|
| 303 |
+
"model.layers.41.mlp.gate",
|
| 304 |
+
"model.layers.41.mlp.shared_expert_gate",
|
| 305 |
+
"model.layers.42.linear_attn.in_proj_qkvz",
|
| 306 |
+
"model.layers.42.linear_attn.in_proj_ba",
|
| 307 |
+
"model.layers.42.linear_attn.out_proj",
|
| 308 |
+
"model.layers.42.mlp.gate",
|
| 309 |
+
"model.layers.42.mlp.shared_expert_gate",
|
| 310 |
+
"model.layers.43.mlp.gate",
|
| 311 |
+
"model.layers.43.mlp.shared_expert_gate",
|
| 312 |
+
"model.layers.44.linear_attn.in_proj_qkvz",
|
| 313 |
+
"model.layers.44.linear_attn.in_proj_ba",
|
| 314 |
+
"model.layers.44.linear_attn.out_proj",
|
| 315 |
+
"model.layers.44.mlp.gate",
|
| 316 |
+
"model.layers.44.mlp.shared_expert_gate",
|
| 317 |
+
"model.layers.45.linear_attn.in_proj_qkvz",
|
| 318 |
+
"model.layers.45.linear_attn.in_proj_ba",
|
| 319 |
+
"model.layers.45.linear_attn.out_proj",
|
| 320 |
+
"model.layers.45.mlp.gate",
|
| 321 |
+
"model.layers.45.mlp.shared_expert_gate",
|
| 322 |
+
"model.layers.46.linear_attn.in_proj_qkvz",
|
| 323 |
+
"model.layers.46.linear_attn.in_proj_ba",
|
| 324 |
+
"model.layers.46.linear_attn.out_proj",
|
| 325 |
+
"model.layers.46.mlp.gate",
|
| 326 |
+
"model.layers.46.mlp.shared_expert_gate",
|
| 327 |
+
"model.layers.47.self_attn.q_proj",
|
| 328 |
+
"model.layers.47.self_attn.k_proj",
|
| 329 |
+
"model.layers.47.self_attn.v_proj",
|
| 330 |
+
"model.layers.47.self_attn.o_proj",
|
| 331 |
+
"model.layers.47.mlp.gate",
|
| 332 |
+
"model.layers.47.mlp.experts.0.gate_proj",
|
| 333 |
+
"model.layers.47.mlp.experts.0.up_proj",
|
| 334 |
+
"model.layers.47.mlp.experts.0.down_proj",
|
| 335 |
+
"model.layers.47.mlp.experts.1.gate_proj",
|
| 336 |
+
"model.layers.47.mlp.experts.1.up_proj",
|
| 337 |
+
"model.layers.47.mlp.experts.1.down_proj",
|
| 338 |
+
"model.layers.47.mlp.experts.2.gate_proj",
|
| 339 |
+
"model.layers.47.mlp.experts.2.up_proj",
|
| 340 |
+
"model.layers.47.mlp.experts.2.down_proj",
|
| 341 |
+
"model.layers.47.mlp.experts.3.gate_proj",
|
| 342 |
+
"model.layers.47.mlp.experts.3.up_proj",
|
| 343 |
+
"model.layers.47.mlp.experts.3.down_proj",
|
| 344 |
+
"model.layers.47.mlp.experts.4.gate_proj",
|
| 345 |
+
"model.layers.47.mlp.experts.4.up_proj",
|
| 346 |
+
"model.layers.47.mlp.experts.4.down_proj",
|
| 347 |
+
"model.layers.47.mlp.experts.5.gate_proj",
|
| 348 |
+
"model.layers.47.mlp.experts.5.up_proj",
|
| 349 |
+
"model.layers.47.mlp.experts.5.down_proj",
|
| 350 |
+
"model.layers.47.mlp.experts.6.gate_proj",
|
| 351 |
+
"model.layers.47.mlp.experts.6.up_proj",
|
| 352 |
+
"model.layers.47.mlp.experts.6.down_proj",
|
| 353 |
+
"model.layers.47.mlp.experts.7.gate_proj",
|
| 354 |
+
"model.layers.47.mlp.experts.7.up_proj",
|
| 355 |
+
"model.layers.47.mlp.experts.7.down_proj",
|
| 356 |
+
"model.layers.47.mlp.experts.8.gate_proj",
|
| 357 |
+
"model.layers.47.mlp.experts.8.up_proj",
|
| 358 |
+
"model.layers.47.mlp.experts.8.down_proj",
|
| 359 |
+
"model.layers.47.mlp.experts.9.gate_proj",
|
| 360 |
+
"model.layers.47.mlp.experts.9.up_proj",
|
| 361 |
+
"model.layers.47.mlp.experts.9.down_proj",
|
| 362 |
+
"model.layers.47.mlp.experts.10.gate_proj",
|
| 363 |
+
"model.layers.47.mlp.experts.10.up_proj",
|
| 364 |
+
"model.layers.47.mlp.experts.10.down_proj",
|
| 365 |
+
"model.layers.47.mlp.experts.11.gate_proj",
|
| 366 |
+
"model.layers.47.mlp.experts.11.up_proj",
|
| 367 |
+
"model.layers.47.mlp.experts.11.down_proj",
|
| 368 |
+
"model.layers.47.mlp.experts.12.gate_proj",
|
| 369 |
+
"model.layers.47.mlp.experts.12.up_proj",
|
| 370 |
+
"model.layers.47.mlp.experts.12.down_proj",
|
| 371 |
+
"model.layers.47.mlp.experts.13.gate_proj",
|
| 372 |
+
"model.layers.47.mlp.experts.13.up_proj",
|
| 373 |
+
"model.layers.47.mlp.experts.13.down_proj",
|
| 374 |
+
"model.layers.47.mlp.experts.14.gate_proj",
|
| 375 |
+
"model.layers.47.mlp.experts.14.up_proj",
|
| 376 |
+
"model.layers.47.mlp.experts.14.down_proj",
|
| 377 |
+
"model.layers.47.mlp.experts.15.gate_proj",
|
| 378 |
+
"model.layers.47.mlp.experts.15.up_proj",
|
| 379 |
+
"model.layers.47.mlp.experts.15.down_proj",
|
| 380 |
+
"model.layers.47.mlp.experts.16.gate_proj",
|
| 381 |
+
"model.layers.47.mlp.experts.16.up_proj",
|
| 382 |
+
"model.layers.47.mlp.experts.16.down_proj",
|
| 383 |
+
"model.layers.47.mlp.experts.17.gate_proj",
|
| 384 |
+
"model.layers.47.mlp.experts.17.up_proj",
|
| 385 |
+
"model.layers.47.mlp.experts.17.down_proj",
|
| 386 |
+
"model.layers.47.mlp.experts.18.gate_proj",
|
| 387 |
+
"model.layers.47.mlp.experts.18.up_proj",
|
| 388 |
+
"model.layers.47.mlp.experts.18.down_proj",
|
| 389 |
+
"model.layers.47.mlp.experts.19.gate_proj",
|
| 390 |
+
"model.layers.47.mlp.experts.19.up_proj",
|
| 391 |
+
"model.layers.47.mlp.experts.19.down_proj",
|
| 392 |
+
"model.layers.47.mlp.experts.20.gate_proj",
|
| 393 |
+
"model.layers.47.mlp.experts.20.up_proj",
|
| 394 |
+
"model.layers.47.mlp.experts.20.down_proj",
|
| 395 |
+
"model.layers.47.mlp.experts.21.gate_proj",
|
| 396 |
+
"model.layers.47.mlp.experts.21.up_proj",
|
| 397 |
+
"model.layers.47.mlp.experts.21.down_proj",
|
| 398 |
+
"model.layers.47.mlp.experts.22.gate_proj",
|
| 399 |
+
"model.layers.47.mlp.experts.22.up_proj",
|
| 400 |
+
"model.layers.47.mlp.experts.22.down_proj",
|
| 401 |
+
"model.layers.47.mlp.experts.23.gate_proj",
|
| 402 |
+
"model.layers.47.mlp.experts.23.up_proj",
|
| 403 |
+
"model.layers.47.mlp.experts.23.down_proj",
|
| 404 |
+
"model.layers.47.mlp.experts.24.gate_proj",
|
| 405 |
+
"model.layers.47.mlp.experts.24.up_proj",
|
| 406 |
+
"model.layers.47.mlp.experts.24.down_proj",
|
| 407 |
+
"model.layers.47.mlp.experts.25.gate_proj",
|
| 408 |
+
"model.layers.47.mlp.experts.25.up_proj",
|
| 409 |
+
"model.layers.47.mlp.experts.25.down_proj",
|
| 410 |
+
"model.layers.47.mlp.experts.26.gate_proj",
|
| 411 |
+
"model.layers.47.mlp.experts.26.up_proj",
|
| 412 |
+
"model.layers.47.mlp.experts.26.down_proj",
|
| 413 |
+
"model.layers.47.mlp.experts.27.gate_proj",
|
| 414 |
+
"model.layers.47.mlp.experts.27.up_proj",
|
| 415 |
+
"model.layers.47.mlp.experts.27.down_proj",
|
| 416 |
+
"model.layers.47.mlp.experts.28.gate_proj",
|
| 417 |
+
"model.layers.47.mlp.experts.28.up_proj",
|
| 418 |
+
"model.layers.47.mlp.experts.28.down_proj",
|
| 419 |
+
"model.layers.47.mlp.experts.29.gate_proj",
|
| 420 |
+
"model.layers.47.mlp.experts.29.up_proj",
|
| 421 |
+
"model.layers.47.mlp.experts.29.down_proj",
|
| 422 |
+
"model.layers.47.mlp.experts.30.gate_proj",
|
| 423 |
+
"model.layers.47.mlp.experts.30.up_proj",
|
| 424 |
+
"model.layers.47.mlp.experts.30.down_proj",
|
| 425 |
+
"model.layers.47.mlp.experts.31.gate_proj",
|
| 426 |
+
"model.layers.47.mlp.experts.31.up_proj",
|
| 427 |
+
"model.layers.47.mlp.experts.31.down_proj",
|
| 428 |
+
"model.layers.47.mlp.experts.32.gate_proj",
|
| 429 |
+
"model.layers.47.mlp.experts.32.up_proj",
|
| 430 |
+
"model.layers.47.mlp.experts.32.down_proj",
|
| 431 |
+
"model.layers.47.mlp.experts.33.gate_proj",
|
| 432 |
+
"model.layers.47.mlp.experts.33.up_proj",
|
| 433 |
+
"model.layers.47.mlp.experts.33.down_proj",
|
| 434 |
+
"model.layers.47.mlp.experts.34.gate_proj",
|
| 435 |
+
"model.layers.47.mlp.experts.34.up_proj",
|
| 436 |
+
"model.layers.47.mlp.experts.34.down_proj",
|
| 437 |
+
"model.layers.47.mlp.experts.35.gate_proj",
|
| 438 |
+
"model.layers.47.mlp.experts.35.up_proj",
|
| 439 |
+
"model.layers.47.mlp.experts.35.down_proj",
|
| 440 |
+
"model.layers.47.mlp.experts.36.gate_proj",
|
| 441 |
+
"model.layers.47.mlp.experts.36.up_proj",
|
| 442 |
+
"model.layers.47.mlp.experts.36.down_proj",
|
| 443 |
+
"model.layers.47.mlp.experts.37.gate_proj",
|
| 444 |
+
"model.layers.47.mlp.experts.37.up_proj",
|
| 445 |
+
"model.layers.47.mlp.experts.37.down_proj",
|
| 446 |
+
"model.layers.47.mlp.experts.38.gate_proj",
|
| 447 |
+
"model.layers.47.mlp.experts.38.up_proj",
|
| 448 |
+
"model.layers.47.mlp.experts.38.down_proj",
|
| 449 |
+
"model.layers.47.mlp.experts.39.gate_proj",
|
| 450 |
+
"model.layers.47.mlp.experts.39.up_proj",
|
| 451 |
+
"model.layers.47.mlp.experts.39.down_proj",
|
| 452 |
+
"model.layers.47.mlp.experts.40.gate_proj",
|
| 453 |
+
"model.layers.47.mlp.experts.40.up_proj",
|
| 454 |
+
"model.layers.47.mlp.experts.40.down_proj",
|
| 455 |
+
"model.layers.47.mlp.experts.41.gate_proj",
|
| 456 |
+
"model.layers.47.mlp.experts.41.up_proj",
|
| 457 |
+
"model.layers.47.mlp.experts.41.down_proj",
|
| 458 |
+
"model.layers.47.mlp.experts.42.gate_proj",
|
| 459 |
+
"model.layers.47.mlp.experts.42.up_proj",
|
| 460 |
+
"model.layers.47.mlp.experts.42.down_proj",
|
| 461 |
+
"model.layers.47.mlp.experts.43.gate_proj",
|
| 462 |
+
"model.layers.47.mlp.experts.43.up_proj",
|
| 463 |
+
"model.layers.47.mlp.experts.43.down_proj",
|
| 464 |
+
"model.layers.47.mlp.experts.44.gate_proj",
|
| 465 |
+
"model.layers.47.mlp.experts.44.up_proj",
|
| 466 |
+
"model.layers.47.mlp.experts.44.down_proj",
|
| 467 |
+
"model.layers.47.mlp.experts.45.gate_proj",
|
| 468 |
+
"model.layers.47.mlp.experts.45.up_proj",
|
| 469 |
+
"model.layers.47.mlp.experts.45.down_proj",
|
| 470 |
+
"model.layers.47.mlp.experts.46.gate_proj",
|
| 471 |
+
"model.layers.47.mlp.experts.46.up_proj",
|
| 472 |
+
"model.layers.47.mlp.experts.46.down_proj",
|
| 473 |
+
"model.layers.47.mlp.experts.47.gate_proj",
|
| 474 |
+
"model.layers.47.mlp.experts.47.up_proj",
|
| 475 |
+
"model.layers.47.mlp.experts.47.down_proj",
|
| 476 |
+
"model.layers.47.mlp.experts.48.gate_proj",
|
| 477 |
+
"model.layers.47.mlp.experts.48.up_proj",
|
| 478 |
+
"model.layers.47.mlp.experts.48.down_proj",
|
| 479 |
+
"model.layers.47.mlp.experts.49.gate_proj",
|
| 480 |
+
"model.layers.47.mlp.experts.49.up_proj",
|
| 481 |
+
"model.layers.47.mlp.experts.49.down_proj",
|
| 482 |
+
"model.layers.47.mlp.experts.50.gate_proj",
|
| 483 |
+
"model.layers.47.mlp.experts.50.up_proj",
|
| 484 |
+
"model.layers.47.mlp.experts.50.down_proj",
|
| 485 |
+
"model.layers.47.mlp.experts.51.gate_proj",
|
| 486 |
+
"model.layers.47.mlp.experts.51.up_proj",
|
| 487 |
+
"model.layers.47.mlp.experts.51.down_proj",
|
| 488 |
+
"model.layers.47.mlp.experts.52.gate_proj",
|
| 489 |
+
"model.layers.47.mlp.experts.52.up_proj",
|
| 490 |
+
"model.layers.47.mlp.experts.52.down_proj",
|
| 491 |
+
"model.layers.47.mlp.experts.53.gate_proj",
|
| 492 |
+
"model.layers.47.mlp.experts.53.up_proj",
|
| 493 |
+
"model.layers.47.mlp.experts.53.down_proj",
|
| 494 |
+
"model.layers.47.mlp.experts.54.gate_proj",
|
| 495 |
+
"model.layers.47.mlp.experts.54.up_proj",
|
| 496 |
+
"model.layers.47.mlp.experts.54.down_proj",
|
| 497 |
+
"model.layers.47.mlp.experts.55.gate_proj",
|
| 498 |
+
"model.layers.47.mlp.experts.55.up_proj",
|
| 499 |
+
"model.layers.47.mlp.experts.55.down_proj",
|
| 500 |
+
"model.layers.47.mlp.experts.56.gate_proj",
|
| 501 |
+
"model.layers.47.mlp.experts.56.up_proj",
|
| 502 |
+
"model.layers.47.mlp.experts.56.down_proj",
|
| 503 |
+
"model.layers.47.mlp.experts.57.gate_proj",
|
| 504 |
+
"model.layers.47.mlp.experts.57.up_proj",
|
| 505 |
+
"model.layers.47.mlp.experts.57.down_proj",
|
| 506 |
+
"model.layers.47.mlp.experts.58.gate_proj",
|
| 507 |
+
"model.layers.47.mlp.experts.58.up_proj",
|
| 508 |
+
"model.layers.47.mlp.experts.58.down_proj",
|
| 509 |
+
"model.layers.47.mlp.experts.59.gate_proj",
|
| 510 |
+
"model.layers.47.mlp.experts.59.up_proj",
|
| 511 |
+
"model.layers.47.mlp.experts.59.down_proj",
|
| 512 |
+
"model.layers.47.mlp.experts.60.gate_proj",
|
| 513 |
+
"model.layers.47.mlp.experts.60.up_proj",
|
| 514 |
+
"model.layers.47.mlp.experts.60.down_proj",
|
| 515 |
+
"model.layers.47.mlp.experts.61.gate_proj",
|
| 516 |
+
"model.layers.47.mlp.experts.61.up_proj",
|
| 517 |
+
"model.layers.47.mlp.experts.61.down_proj",
|
| 518 |
+
"model.layers.47.mlp.experts.62.gate_proj",
|
| 519 |
+
"model.layers.47.mlp.experts.62.up_proj",
|
| 520 |
+
"model.layers.47.mlp.experts.62.down_proj",
|
| 521 |
+
"model.layers.47.mlp.experts.63.gate_proj",
|
| 522 |
+
"model.layers.47.mlp.experts.63.up_proj",
|
| 523 |
+
"model.layers.47.mlp.experts.63.down_proj",
|
| 524 |
+
"model.layers.47.mlp.experts.64.gate_proj",
|
| 525 |
+
"model.layers.47.mlp.experts.64.up_proj",
|
| 526 |
+
"model.layers.47.mlp.experts.64.down_proj",
|
| 527 |
+
"model.layers.47.mlp.experts.65.gate_proj",
|
| 528 |
+
"model.layers.47.mlp.experts.65.up_proj",
|
| 529 |
+
"model.layers.47.mlp.experts.65.down_proj",
|
| 530 |
+
"model.layers.47.mlp.experts.66.gate_proj",
|
| 531 |
+
"model.layers.47.mlp.experts.66.up_proj",
|
| 532 |
+
"model.layers.47.mlp.experts.66.down_proj",
|
| 533 |
+
"model.layers.47.mlp.experts.67.gate_proj",
|
| 534 |
+
"model.layers.47.mlp.experts.67.up_proj",
|
| 535 |
+
"model.layers.47.mlp.experts.67.down_proj",
|
| 536 |
+
"model.layers.47.mlp.experts.68.gate_proj",
|
| 537 |
+
"model.layers.47.mlp.experts.68.up_proj",
|
| 538 |
+
"model.layers.47.mlp.experts.68.down_proj",
|
| 539 |
+
"model.layers.47.mlp.experts.69.gate_proj",
|
| 540 |
+
"model.layers.47.mlp.experts.69.up_proj",
|
| 541 |
+
"model.layers.47.mlp.experts.69.down_proj",
|
| 542 |
+
"model.layers.47.mlp.experts.70.gate_proj",
|
| 543 |
+
"model.layers.47.mlp.experts.70.up_proj",
|
| 544 |
+
"model.layers.47.mlp.experts.70.down_proj",
|
| 545 |
+
"model.layers.47.mlp.experts.71.gate_proj",
|
| 546 |
+
"model.layers.47.mlp.experts.71.up_proj",
|
| 547 |
+
"model.layers.47.mlp.experts.71.down_proj",
|
| 548 |
+
"model.layers.47.mlp.experts.72.gate_proj",
|
| 549 |
+
"model.layers.47.mlp.experts.72.up_proj",
|
| 550 |
+
"model.layers.47.mlp.experts.72.down_proj",
|
| 551 |
+
"model.layers.47.mlp.experts.73.gate_proj",
|
| 552 |
+
"model.layers.47.mlp.experts.73.up_proj",
|
| 553 |
+
"model.layers.47.mlp.experts.73.down_proj",
|
| 554 |
+
"model.layers.47.mlp.experts.74.gate_proj",
|
| 555 |
+
"model.layers.47.mlp.experts.74.up_proj",
|
| 556 |
+
"model.layers.47.mlp.experts.74.down_proj",
|
| 557 |
+
"model.layers.47.mlp.experts.75.gate_proj",
|
| 558 |
+
"model.layers.47.mlp.experts.75.up_proj",
|
| 559 |
+
"model.layers.47.mlp.experts.75.down_proj",
|
| 560 |
+
"model.layers.47.mlp.experts.76.gate_proj",
|
| 561 |
+
"model.layers.47.mlp.experts.76.up_proj",
|
| 562 |
+
"model.layers.47.mlp.experts.76.down_proj",
|
| 563 |
+
"model.layers.47.mlp.experts.77.gate_proj",
|
| 564 |
+
"model.layers.47.mlp.experts.77.up_proj",
|
| 565 |
+
"model.layers.47.mlp.experts.77.down_proj",
|
| 566 |
+
"model.layers.47.mlp.experts.78.gate_proj",
|
| 567 |
+
"model.layers.47.mlp.experts.78.up_proj",
|
| 568 |
+
"model.layers.47.mlp.experts.78.down_proj",
|
| 569 |
+
"model.layers.47.mlp.experts.79.gate_proj",
|
| 570 |
+
"model.layers.47.mlp.experts.79.up_proj",
|
| 571 |
+
"model.layers.47.mlp.experts.79.down_proj",
|
| 572 |
+
"model.layers.47.mlp.experts.80.gate_proj",
|
| 573 |
+
"model.layers.47.mlp.experts.80.up_proj",
|
| 574 |
+
"model.layers.47.mlp.experts.80.down_proj",
|
| 575 |
+
"model.layers.47.mlp.experts.81.gate_proj",
|
| 576 |
+
"model.layers.47.mlp.experts.81.up_proj",
|
| 577 |
+
"model.layers.47.mlp.experts.81.down_proj",
|
| 578 |
+
"model.layers.47.mlp.experts.82.gate_proj",
|
| 579 |
+
"model.layers.47.mlp.experts.82.up_proj",
|
| 580 |
+
"model.layers.47.mlp.experts.82.down_proj",
|
| 581 |
+
"model.layers.47.mlp.experts.83.gate_proj",
|
| 582 |
+
"model.layers.47.mlp.experts.83.up_proj",
|
| 583 |
+
"model.layers.47.mlp.experts.83.down_proj",
|
| 584 |
+
"model.layers.47.mlp.experts.84.gate_proj",
|
| 585 |
+
"model.layers.47.mlp.experts.84.up_proj",
|
| 586 |
+
"model.layers.47.mlp.experts.84.down_proj",
|
| 587 |
+
"model.layers.47.mlp.experts.85.gate_proj",
|
| 588 |
+
"model.layers.47.mlp.experts.85.up_proj",
|
| 589 |
+
"model.layers.47.mlp.experts.85.down_proj",
|
| 590 |
+
"model.layers.47.mlp.experts.86.gate_proj",
|
| 591 |
+
"model.layers.47.mlp.experts.86.up_proj",
|
| 592 |
+
"model.layers.47.mlp.experts.86.down_proj",
|
| 593 |
+
"model.layers.47.mlp.experts.87.gate_proj",
|
| 594 |
+
"model.layers.47.mlp.experts.87.up_proj",
|
| 595 |
+
"model.layers.47.mlp.experts.87.down_proj",
|
| 596 |
+
"model.layers.47.mlp.experts.88.gate_proj",
|
| 597 |
+
"model.layers.47.mlp.experts.88.up_proj",
|
| 598 |
+
"model.layers.47.mlp.experts.88.down_proj",
|
| 599 |
+
"model.layers.47.mlp.experts.89.gate_proj",
|
| 600 |
+
"model.layers.47.mlp.experts.89.up_proj",
|
| 601 |
+
"model.layers.47.mlp.experts.89.down_proj",
|
| 602 |
+
"model.layers.47.mlp.experts.90.gate_proj",
|
| 603 |
+
"model.layers.47.mlp.experts.90.up_proj",
|
| 604 |
+
"model.layers.47.mlp.experts.90.down_proj",
|
| 605 |
+
"model.layers.47.mlp.experts.91.gate_proj",
|
| 606 |
+
"model.layers.47.mlp.experts.91.up_proj",
|
| 607 |
+
"model.layers.47.mlp.experts.91.down_proj",
|
| 608 |
+
"model.layers.47.mlp.experts.92.gate_proj",
|
| 609 |
+
"model.layers.47.mlp.experts.92.up_proj",
|
| 610 |
+
"model.layers.47.mlp.experts.92.down_proj",
|
| 611 |
+
"model.layers.47.mlp.experts.93.gate_proj",
|
| 612 |
+
"model.layers.47.mlp.experts.93.up_proj",
|
| 613 |
+
"model.layers.47.mlp.experts.93.down_proj",
|
| 614 |
+
"model.layers.47.mlp.experts.94.gate_proj",
|
| 615 |
+
"model.layers.47.mlp.experts.94.up_proj",
|
| 616 |
+
"model.layers.47.mlp.experts.94.down_proj",
|
| 617 |
+
"model.layers.47.mlp.experts.95.gate_proj",
|
| 618 |
+
"model.layers.47.mlp.experts.95.up_proj",
|
| 619 |
+
"model.layers.47.mlp.experts.95.down_proj",
|
| 620 |
+
"model.layers.47.mlp.experts.96.gate_proj",
|
| 621 |
+
"model.layers.47.mlp.experts.96.up_proj",
|
| 622 |
+
"model.layers.47.mlp.experts.96.down_proj",
|
| 623 |
+
"model.layers.47.mlp.experts.97.gate_proj",
|
| 624 |
+
"model.layers.47.mlp.experts.97.up_proj",
|
| 625 |
+
"model.layers.47.mlp.experts.97.down_proj",
|
| 626 |
+
"model.layers.47.mlp.experts.98.gate_proj",
|
| 627 |
+
"model.layers.47.mlp.experts.98.up_proj",
|
| 628 |
+
"model.layers.47.mlp.experts.98.down_proj",
|
| 629 |
+
"model.layers.47.mlp.experts.99.gate_proj",
|
| 630 |
+
"model.layers.47.mlp.experts.99.up_proj",
|
| 631 |
+
"model.layers.47.mlp.experts.99.down_proj",
|
| 632 |
+
"model.layers.47.mlp.experts.100.gate_proj",
|
| 633 |
+
"model.layers.47.mlp.experts.100.up_proj",
|
| 634 |
+
"model.layers.47.mlp.experts.100.down_proj",
|
| 635 |
+
"model.layers.47.mlp.experts.101.gate_proj",
|
| 636 |
+
"model.layers.47.mlp.experts.101.up_proj",
|
| 637 |
+
"model.layers.47.mlp.experts.101.down_proj",
|
| 638 |
+
"model.layers.47.mlp.experts.102.gate_proj",
|
| 639 |
+
"model.layers.47.mlp.experts.102.up_proj",
|
| 640 |
+
"model.layers.47.mlp.experts.102.down_proj",
|
| 641 |
+
"model.layers.47.mlp.experts.103.gate_proj",
|
| 642 |
+
"model.layers.47.mlp.experts.103.up_proj",
|
| 643 |
+
"model.layers.47.mlp.experts.103.down_proj",
|
| 644 |
+
"model.layers.47.mlp.experts.104.gate_proj",
|
| 645 |
+
"model.layers.47.mlp.experts.104.up_proj",
|
| 646 |
+
"model.layers.47.mlp.experts.104.down_proj",
|
| 647 |
+
"model.layers.47.mlp.experts.105.gate_proj",
|
| 648 |
+
"model.layers.47.mlp.experts.105.up_proj",
|
| 649 |
+
"model.layers.47.mlp.experts.105.down_proj",
|
| 650 |
+
"model.layers.47.mlp.experts.106.gate_proj",
|
| 651 |
+
"model.layers.47.mlp.experts.106.up_proj",
|
| 652 |
+
"model.layers.47.mlp.experts.106.down_proj",
|
| 653 |
+
"model.layers.47.mlp.experts.107.gate_proj",
|
| 654 |
+
"model.layers.47.mlp.experts.107.up_proj",
|
| 655 |
+
"model.layers.47.mlp.experts.107.down_proj",
|
| 656 |
+
"model.layers.47.mlp.experts.108.gate_proj",
|
| 657 |
+
"model.layers.47.mlp.experts.108.up_proj",
|
| 658 |
+
"model.layers.47.mlp.experts.108.down_proj",
|
| 659 |
+
"model.layers.47.mlp.experts.109.gate_proj",
|
| 660 |
+
"model.layers.47.mlp.experts.109.up_proj",
|
| 661 |
+
"model.layers.47.mlp.experts.109.down_proj",
|
| 662 |
+
"model.layers.47.mlp.experts.110.gate_proj",
|
| 663 |
+
"model.layers.47.mlp.experts.110.up_proj",
|
| 664 |
+
"model.layers.47.mlp.experts.110.down_proj",
|
| 665 |
+
"model.layers.47.mlp.experts.111.gate_proj",
|
| 666 |
+
"model.layers.47.mlp.experts.111.up_proj",
|
| 667 |
+
"model.layers.47.mlp.experts.111.down_proj",
|
| 668 |
+
"model.layers.47.mlp.experts.112.gate_proj",
|
| 669 |
+
"model.layers.47.mlp.experts.112.up_proj",
|
| 670 |
+
"model.layers.47.mlp.experts.112.down_proj",
|
| 671 |
+
"model.layers.47.mlp.experts.113.gate_proj",
|
| 672 |
+
"model.layers.47.mlp.experts.113.up_proj",
|
| 673 |
+
"model.layers.47.mlp.experts.113.down_proj",
|
| 674 |
+
"model.layers.47.mlp.experts.114.gate_proj",
|
| 675 |
+
"model.layers.47.mlp.experts.114.up_proj",
|
| 676 |
+
"model.layers.47.mlp.experts.114.down_proj",
|
| 677 |
+
"model.layers.47.mlp.experts.115.gate_proj",
|
| 678 |
+
"model.layers.47.mlp.experts.115.up_proj",
|
| 679 |
+
"model.layers.47.mlp.experts.115.down_proj",
|
| 680 |
+
"model.layers.47.mlp.experts.116.gate_proj",
|
| 681 |
+
"model.layers.47.mlp.experts.116.up_proj",
|
| 682 |
+
"model.layers.47.mlp.experts.116.down_proj",
|
| 683 |
+
"model.layers.47.mlp.experts.117.gate_proj",
|
| 684 |
+
"model.layers.47.mlp.experts.117.up_proj",
|
| 685 |
+
"model.layers.47.mlp.experts.117.down_proj",
|
| 686 |
+
"model.layers.47.mlp.experts.118.gate_proj",
|
| 687 |
+
"model.layers.47.mlp.experts.118.up_proj",
|
| 688 |
+
"model.layers.47.mlp.experts.118.down_proj",
|
| 689 |
+
"model.layers.47.mlp.experts.119.gate_proj",
|
| 690 |
+
"model.layers.47.mlp.experts.119.up_proj",
|
| 691 |
+
"model.layers.47.mlp.experts.119.down_proj",
|
| 692 |
+
"model.layers.47.mlp.experts.120.gate_proj",
|
| 693 |
+
"model.layers.47.mlp.experts.120.up_proj",
|
| 694 |
+
"model.layers.47.mlp.experts.120.down_proj",
|
| 695 |
+
"model.layers.47.mlp.experts.121.gate_proj",
|
| 696 |
+
"model.layers.47.mlp.experts.121.up_proj",
|
| 697 |
+
"model.layers.47.mlp.experts.121.down_proj",
|
| 698 |
+
"model.layers.47.mlp.experts.122.gate_proj",
|
| 699 |
+
"model.layers.47.mlp.experts.122.up_proj",
|
| 700 |
+
"model.layers.47.mlp.experts.122.down_proj",
|
| 701 |
+
"model.layers.47.mlp.experts.123.gate_proj",
|
| 702 |
+
"model.layers.47.mlp.experts.123.up_proj",
|
| 703 |
+
"model.layers.47.mlp.experts.123.down_proj",
|
| 704 |
+
"model.layers.47.mlp.experts.124.gate_proj",
|
| 705 |
+
"model.layers.47.mlp.experts.124.up_proj",
|
| 706 |
+
"model.layers.47.mlp.experts.124.down_proj",
|
| 707 |
+
"model.layers.47.mlp.experts.125.gate_proj",
|
| 708 |
+
"model.layers.47.mlp.experts.125.up_proj",
|
| 709 |
+
"model.layers.47.mlp.experts.125.down_proj",
|
| 710 |
+
"model.layers.47.mlp.experts.126.gate_proj",
|
| 711 |
+
"model.layers.47.mlp.experts.126.up_proj",
|
| 712 |
+
"model.layers.47.mlp.experts.126.down_proj",
|
| 713 |
+
"model.layers.47.mlp.experts.127.gate_proj",
|
| 714 |
+
"model.layers.47.mlp.experts.127.up_proj",
|
| 715 |
+
"model.layers.47.mlp.experts.127.down_proj",
|
| 716 |
+
"model.layers.47.mlp.experts.128.gate_proj",
|
| 717 |
+
"model.layers.47.mlp.experts.128.up_proj",
|
| 718 |
+
"model.layers.47.mlp.experts.128.down_proj",
|
| 719 |
+
"model.layers.47.mlp.experts.129.gate_proj",
|
| 720 |
+
"model.layers.47.mlp.experts.129.up_proj",
|
| 721 |
+
"model.layers.47.mlp.experts.129.down_proj",
|
| 722 |
+
"model.layers.47.mlp.experts.130.gate_proj",
|
| 723 |
+
"model.layers.47.mlp.experts.130.up_proj",
|
| 724 |
+
"model.layers.47.mlp.experts.130.down_proj",
|
| 725 |
+
"model.layers.47.mlp.experts.131.gate_proj",
|
| 726 |
+
"model.layers.47.mlp.experts.131.up_proj",
|
| 727 |
+
"model.layers.47.mlp.experts.131.down_proj",
|
| 728 |
+
"model.layers.47.mlp.experts.132.gate_proj",
|
| 729 |
+
"model.layers.47.mlp.experts.132.up_proj",
|
| 730 |
+
"model.layers.47.mlp.experts.132.down_proj",
|
| 731 |
+
"model.layers.47.mlp.experts.133.gate_proj",
|
| 732 |
+
"model.layers.47.mlp.experts.133.up_proj",
|
| 733 |
+
"model.layers.47.mlp.experts.133.down_proj",
|
| 734 |
+
"model.layers.47.mlp.experts.134.gate_proj",
|
| 735 |
+
"model.layers.47.mlp.experts.134.up_proj",
|
| 736 |
+
"model.layers.47.mlp.experts.134.down_proj",
|
| 737 |
+
"model.layers.47.mlp.experts.135.gate_proj",
|
| 738 |
+
"model.layers.47.mlp.experts.135.up_proj",
|
| 739 |
+
"model.layers.47.mlp.experts.135.down_proj",
|
| 740 |
+
"model.layers.47.mlp.experts.136.gate_proj",
|
| 741 |
+
"model.layers.47.mlp.experts.136.up_proj",
|
| 742 |
+
"model.layers.47.mlp.experts.136.down_proj",
|
| 743 |
+
"model.layers.47.mlp.experts.137.gate_proj",
|
| 744 |
+
"model.layers.47.mlp.experts.137.up_proj",
|
| 745 |
+
"model.layers.47.mlp.experts.137.down_proj",
|
| 746 |
+
"model.layers.47.mlp.experts.138.gate_proj",
|
| 747 |
+
"model.layers.47.mlp.experts.138.up_proj",
|
| 748 |
+
"model.layers.47.mlp.experts.138.down_proj",
|
| 749 |
+
"model.layers.47.mlp.experts.139.gate_proj",
|
| 750 |
+
"model.layers.47.mlp.experts.139.up_proj",
|
| 751 |
+
"model.layers.47.mlp.experts.139.down_proj",
|
| 752 |
+
"model.layers.47.mlp.experts.140.gate_proj",
|
| 753 |
+
"model.layers.47.mlp.experts.140.up_proj",
|
| 754 |
+
"model.layers.47.mlp.experts.140.down_proj",
|
| 755 |
+
"model.layers.47.mlp.experts.141.gate_proj",
|
| 756 |
+
"model.layers.47.mlp.experts.141.up_proj",
|
| 757 |
+
"model.layers.47.mlp.experts.141.down_proj",
|
| 758 |
+
"model.layers.47.mlp.experts.142.gate_proj",
|
| 759 |
+
"model.layers.47.mlp.experts.142.up_proj",
|
| 760 |
+
"model.layers.47.mlp.experts.142.down_proj",
|
| 761 |
+
"model.layers.47.mlp.experts.143.gate_proj",
|
| 762 |
+
"model.layers.47.mlp.experts.143.up_proj",
|
| 763 |
+
"model.layers.47.mlp.experts.143.down_proj",
|
| 764 |
+
"model.layers.47.mlp.experts.144.gate_proj",
|
| 765 |
+
"model.layers.47.mlp.experts.144.up_proj",
|
| 766 |
+
"model.layers.47.mlp.experts.144.down_proj",
|
| 767 |
+
"model.layers.47.mlp.experts.145.gate_proj",
|
| 768 |
+
"model.layers.47.mlp.experts.145.up_proj",
|
| 769 |
+
"model.layers.47.mlp.experts.145.down_proj",
|
| 770 |
+
"model.layers.47.mlp.experts.146.gate_proj",
|
| 771 |
+
"model.layers.47.mlp.experts.146.up_proj",
|
| 772 |
+
"model.layers.47.mlp.experts.146.down_proj",
|
| 773 |
+
"model.layers.47.mlp.experts.147.gate_proj",
|
| 774 |
+
"model.layers.47.mlp.experts.147.up_proj",
|
| 775 |
+
"model.layers.47.mlp.experts.147.down_proj",
|
| 776 |
+
"model.layers.47.mlp.experts.148.gate_proj",
|
| 777 |
+
"model.layers.47.mlp.experts.148.up_proj",
|
| 778 |
+
"model.layers.47.mlp.experts.148.down_proj",
|
| 779 |
+
"model.layers.47.mlp.experts.149.gate_proj",
|
| 780 |
+
"model.layers.47.mlp.experts.149.up_proj",
|
| 781 |
+
"model.layers.47.mlp.experts.149.down_proj",
|
| 782 |
+
"model.layers.47.mlp.experts.150.gate_proj",
|
| 783 |
+
"model.layers.47.mlp.experts.150.up_proj",
|
| 784 |
+
"model.layers.47.mlp.experts.150.down_proj",
|
| 785 |
+
"model.layers.47.mlp.experts.151.gate_proj",
|
| 786 |
+
"model.layers.47.mlp.experts.151.up_proj",
|
| 787 |
+
"model.layers.47.mlp.experts.151.down_proj",
|
| 788 |
+
"model.layers.47.mlp.experts.152.gate_proj",
|
| 789 |
+
"model.layers.47.mlp.experts.152.up_proj",
|
| 790 |
+
"model.layers.47.mlp.experts.152.down_proj",
|
| 791 |
+
"model.layers.47.mlp.experts.153.gate_proj",
|
| 792 |
+
"model.layers.47.mlp.experts.153.up_proj",
|
| 793 |
+
"model.layers.47.mlp.experts.153.down_proj",
|
| 794 |
+
"model.layers.47.mlp.experts.154.gate_proj",
|
| 795 |
+
"model.layers.47.mlp.experts.154.up_proj",
|
| 796 |
+
"model.layers.47.mlp.experts.154.down_proj",
|
| 797 |
+
"model.layers.47.mlp.experts.155.gate_proj",
|
| 798 |
+
"model.layers.47.mlp.experts.155.up_proj",
|
| 799 |
+
"model.layers.47.mlp.experts.155.down_proj",
|
| 800 |
+
"model.layers.47.mlp.experts.156.gate_proj",
|
| 801 |
+
"model.layers.47.mlp.experts.156.up_proj",
|
| 802 |
+
"model.layers.47.mlp.experts.156.down_proj",
|
| 803 |
+
"model.layers.47.mlp.experts.157.gate_proj",
|
| 804 |
+
"model.layers.47.mlp.experts.157.up_proj",
|
| 805 |
+
"model.layers.47.mlp.experts.157.down_proj",
|
| 806 |
+
"model.layers.47.mlp.experts.158.gate_proj",
|
| 807 |
+
"model.layers.47.mlp.experts.158.up_proj",
|
| 808 |
+
"model.layers.47.mlp.experts.158.down_proj",
|
| 809 |
+
"model.layers.47.mlp.experts.159.gate_proj",
|
| 810 |
+
"model.layers.47.mlp.experts.159.up_proj",
|
| 811 |
+
"model.layers.47.mlp.experts.159.down_proj",
|
| 812 |
+
"model.layers.47.mlp.experts.160.gate_proj",
|
| 813 |
+
"model.layers.47.mlp.experts.160.up_proj",
|
| 814 |
+
"model.layers.47.mlp.experts.160.down_proj",
|
| 815 |
+
"model.layers.47.mlp.experts.161.gate_proj",
|
| 816 |
+
"model.layers.47.mlp.experts.161.up_proj",
|
| 817 |
+
"model.layers.47.mlp.experts.161.down_proj",
|
| 818 |
+
"model.layers.47.mlp.experts.162.gate_proj",
|
| 819 |
+
"model.layers.47.mlp.experts.162.up_proj",
|
| 820 |
+
"model.layers.47.mlp.experts.162.down_proj",
|
| 821 |
+
"model.layers.47.mlp.experts.163.gate_proj",
|
| 822 |
+
"model.layers.47.mlp.experts.163.up_proj",
|
| 823 |
+
"model.layers.47.mlp.experts.163.down_proj",
|
| 824 |
+
"model.layers.47.mlp.experts.164.gate_proj",
|
| 825 |
+
"model.layers.47.mlp.experts.164.up_proj",
|
| 826 |
+
"model.layers.47.mlp.experts.164.down_proj",
|
| 827 |
+
"model.layers.47.mlp.experts.165.gate_proj",
|
| 828 |
+
"model.layers.47.mlp.experts.165.up_proj",
|
| 829 |
+
"model.layers.47.mlp.experts.165.down_proj",
|
| 830 |
+
"model.layers.47.mlp.experts.166.gate_proj",
|
| 831 |
+
"model.layers.47.mlp.experts.166.up_proj",
|
| 832 |
+
"model.layers.47.mlp.experts.166.down_proj",
|
| 833 |
+
"model.layers.47.mlp.experts.167.gate_proj",
|
| 834 |
+
"model.layers.47.mlp.experts.167.up_proj",
|
| 835 |
+
"model.layers.47.mlp.experts.167.down_proj",
|
| 836 |
+
"model.layers.47.mlp.experts.168.gate_proj",
|
| 837 |
+
"model.layers.47.mlp.experts.168.up_proj",
|
| 838 |
+
"model.layers.47.mlp.experts.168.down_proj",
|
| 839 |
+
"model.layers.47.mlp.experts.169.gate_proj",
|
| 840 |
+
"model.layers.47.mlp.experts.169.up_proj",
|
| 841 |
+
"model.layers.47.mlp.experts.169.down_proj",
|
| 842 |
+
"model.layers.47.mlp.experts.170.gate_proj",
|
| 843 |
+
"model.layers.47.mlp.experts.170.up_proj",
|
| 844 |
+
"model.layers.47.mlp.experts.170.down_proj",
|
| 845 |
+
"model.layers.47.mlp.experts.171.gate_proj",
|
| 846 |
+
"model.layers.47.mlp.experts.171.up_proj",
|
| 847 |
+
"model.layers.47.mlp.experts.171.down_proj",
|
| 848 |
+
"model.layers.47.mlp.experts.172.gate_proj",
|
| 849 |
+
"model.layers.47.mlp.experts.172.up_proj",
|
| 850 |
+
"model.layers.47.mlp.experts.172.down_proj",
|
| 851 |
+
"model.layers.47.mlp.experts.173.gate_proj",
|
| 852 |
+
"model.layers.47.mlp.experts.173.up_proj",
|
| 853 |
+
"model.layers.47.mlp.experts.173.down_proj",
|
| 854 |
+
"model.layers.47.mlp.experts.174.gate_proj",
|
| 855 |
+
"model.layers.47.mlp.experts.174.up_proj",
|
| 856 |
+
"model.layers.47.mlp.experts.174.down_proj",
|
| 857 |
+
"model.layers.47.mlp.experts.175.gate_proj",
|
| 858 |
+
"model.layers.47.mlp.experts.175.up_proj",
|
| 859 |
+
"model.layers.47.mlp.experts.175.down_proj",
|
| 860 |
+
"model.layers.47.mlp.experts.176.gate_proj",
|
| 861 |
+
"model.layers.47.mlp.experts.176.up_proj",
|
| 862 |
+
"model.layers.47.mlp.experts.176.down_proj",
|
| 863 |
+
"model.layers.47.mlp.experts.177.gate_proj",
|
| 864 |
+
"model.layers.47.mlp.experts.177.up_proj",
|
| 865 |
+
"model.layers.47.mlp.experts.177.down_proj",
|
| 866 |
+
"model.layers.47.mlp.experts.178.gate_proj",
|
| 867 |
+
"model.layers.47.mlp.experts.178.up_proj",
|
| 868 |
+
"model.layers.47.mlp.experts.178.down_proj",
|
| 869 |
+
"model.layers.47.mlp.experts.179.gate_proj",
|
| 870 |
+
"model.layers.47.mlp.experts.179.up_proj",
|
| 871 |
+
"model.layers.47.mlp.experts.179.down_proj",
|
| 872 |
+
"model.layers.47.mlp.experts.180.gate_proj",
|
| 873 |
+
"model.layers.47.mlp.experts.180.up_proj",
|
| 874 |
+
"model.layers.47.mlp.experts.180.down_proj",
|
| 875 |
+
"model.layers.47.mlp.experts.181.gate_proj",
|
| 876 |
+
"model.layers.47.mlp.experts.181.up_proj",
|
| 877 |
+
"model.layers.47.mlp.experts.181.down_proj",
|
| 878 |
+
"model.layers.47.mlp.experts.182.gate_proj",
|
| 879 |
+
"model.layers.47.mlp.experts.182.up_proj",
|
| 880 |
+
"model.layers.47.mlp.experts.182.down_proj",
|
| 881 |
+
"model.layers.47.mlp.experts.183.gate_proj",
|
| 882 |
+
"model.layers.47.mlp.experts.183.up_proj",
|
| 883 |
+
"model.layers.47.mlp.experts.183.down_proj",
|
| 884 |
+
"model.layers.47.mlp.experts.184.gate_proj",
|
| 885 |
+
"model.layers.47.mlp.experts.184.up_proj",
|
| 886 |
+
"model.layers.47.mlp.experts.184.down_proj",
|
| 887 |
+
"model.layers.47.mlp.experts.185.gate_proj",
|
| 888 |
+
"model.layers.47.mlp.experts.185.up_proj",
|
| 889 |
+
"model.layers.47.mlp.experts.185.down_proj",
|
| 890 |
+
"model.layers.47.mlp.experts.186.gate_proj",
|
| 891 |
+
"model.layers.47.mlp.experts.186.up_proj",
|
| 892 |
+
"model.layers.47.mlp.experts.186.down_proj",
|
| 893 |
+
"model.layers.47.mlp.experts.187.gate_proj",
|
| 894 |
+
"model.layers.47.mlp.experts.187.up_proj",
|
| 895 |
+
"model.layers.47.mlp.experts.187.down_proj",
|
| 896 |
+
"model.layers.47.mlp.experts.188.gate_proj",
|
| 897 |
+
"model.layers.47.mlp.experts.188.up_proj",
|
| 898 |
+
"model.layers.47.mlp.experts.188.down_proj",
|
| 899 |
+
"model.layers.47.mlp.experts.189.gate_proj",
|
| 900 |
+
"model.layers.47.mlp.experts.189.up_proj",
|
| 901 |
+
"model.layers.47.mlp.experts.189.down_proj",
|
| 902 |
+
"model.layers.47.mlp.experts.190.gate_proj",
|
| 903 |
+
"model.layers.47.mlp.experts.190.up_proj",
|
| 904 |
+
"model.layers.47.mlp.experts.190.down_proj",
|
| 905 |
+
"model.layers.47.mlp.experts.191.gate_proj",
|
| 906 |
+
"model.layers.47.mlp.experts.191.up_proj",
|
| 907 |
+
"model.layers.47.mlp.experts.191.down_proj",
|
| 908 |
+
"model.layers.47.mlp.experts.192.gate_proj",
|
| 909 |
+
"model.layers.47.mlp.experts.192.up_proj",
|
| 910 |
+
"model.layers.47.mlp.experts.192.down_proj",
|
| 911 |
+
"model.layers.47.mlp.experts.193.gate_proj",
|
| 912 |
+
"model.layers.47.mlp.experts.193.up_proj",
|
| 913 |
+
"model.layers.47.mlp.experts.193.down_proj",
|
| 914 |
+
"model.layers.47.mlp.experts.194.gate_proj",
|
| 915 |
+
"model.layers.47.mlp.experts.194.up_proj",
|
| 916 |
+
"model.layers.47.mlp.experts.194.down_proj",
|
| 917 |
+
"model.layers.47.mlp.experts.195.gate_proj",
|
| 918 |
+
"model.layers.47.mlp.experts.195.up_proj",
|
| 919 |
+
"model.layers.47.mlp.experts.195.down_proj",
|
| 920 |
+
"model.layers.47.mlp.experts.196.gate_proj",
|
| 921 |
+
"model.layers.47.mlp.experts.196.up_proj",
|
| 922 |
+
"model.layers.47.mlp.experts.196.down_proj",
|
| 923 |
+
"model.layers.47.mlp.experts.197.gate_proj",
|
| 924 |
+
"model.layers.47.mlp.experts.197.up_proj",
|
| 925 |
+
"model.layers.47.mlp.experts.197.down_proj",
|
| 926 |
+
"model.layers.47.mlp.experts.198.gate_proj",
|
| 927 |
+
"model.layers.47.mlp.experts.198.up_proj",
|
| 928 |
+
"model.layers.47.mlp.experts.198.down_proj",
|
| 929 |
+
"model.layers.47.mlp.experts.199.gate_proj",
|
| 930 |
+
"model.layers.47.mlp.experts.199.up_proj",
|
| 931 |
+
"model.layers.47.mlp.experts.199.down_proj",
|
| 932 |
+
"model.layers.47.mlp.experts.200.gate_proj",
|
| 933 |
+
"model.layers.47.mlp.experts.200.up_proj",
|
| 934 |
+
"model.layers.47.mlp.experts.200.down_proj",
|
| 935 |
+
"model.layers.47.mlp.experts.201.gate_proj",
|
| 936 |
+
"model.layers.47.mlp.experts.201.up_proj",
|
| 937 |
+
"model.layers.47.mlp.experts.201.down_proj",
|
| 938 |
+
"model.layers.47.mlp.experts.202.gate_proj",
|
| 939 |
+
"model.layers.47.mlp.experts.202.up_proj",
|
| 940 |
+
"model.layers.47.mlp.experts.202.down_proj",
|
| 941 |
+
"model.layers.47.mlp.experts.203.gate_proj",
|
| 942 |
+
"model.layers.47.mlp.experts.203.up_proj",
|
| 943 |
+
"model.layers.47.mlp.experts.203.down_proj",
|
| 944 |
+
"model.layers.47.mlp.experts.204.gate_proj",
|
| 945 |
+
"model.layers.47.mlp.experts.204.up_proj",
|
| 946 |
+
"model.layers.47.mlp.experts.204.down_proj",
|
| 947 |
+
"model.layers.47.mlp.experts.205.gate_proj",
|
| 948 |
+
"model.layers.47.mlp.experts.205.up_proj",
|
| 949 |
+
"model.layers.47.mlp.experts.205.down_proj",
|
| 950 |
+
"model.layers.47.mlp.experts.206.gate_proj",
|
| 951 |
+
"model.layers.47.mlp.experts.206.up_proj",
|
| 952 |
+
"model.layers.47.mlp.experts.206.down_proj",
|
| 953 |
+
"model.layers.47.mlp.experts.207.gate_proj",
|
| 954 |
+
"model.layers.47.mlp.experts.207.up_proj",
|
| 955 |
+
"model.layers.47.mlp.experts.207.down_proj",
|
| 956 |
+
"model.layers.47.mlp.experts.208.gate_proj",
|
| 957 |
+
"model.layers.47.mlp.experts.208.up_proj",
|
| 958 |
+
"model.layers.47.mlp.experts.208.down_proj",
|
| 959 |
+
"model.layers.47.mlp.experts.209.gate_proj",
|
| 960 |
+
"model.layers.47.mlp.experts.209.up_proj",
|
| 961 |
+
"model.layers.47.mlp.experts.209.down_proj",
|
| 962 |
+
"model.layers.47.mlp.experts.210.gate_proj",
|
| 963 |
+
"model.layers.47.mlp.experts.210.up_proj",
|
| 964 |
+
"model.layers.47.mlp.experts.210.down_proj",
|
| 965 |
+
"model.layers.47.mlp.experts.211.gate_proj",
|
| 966 |
+
"model.layers.47.mlp.experts.211.up_proj",
|
| 967 |
+
"model.layers.47.mlp.experts.211.down_proj",
|
| 968 |
+
"model.layers.47.mlp.experts.212.gate_proj",
|
| 969 |
+
"model.layers.47.mlp.experts.212.up_proj",
|
| 970 |
+
"model.layers.47.mlp.experts.212.down_proj",
|
| 971 |
+
"model.layers.47.mlp.experts.213.gate_proj",
|
| 972 |
+
"model.layers.47.mlp.experts.213.up_proj",
|
| 973 |
+
"model.layers.47.mlp.experts.213.down_proj",
|
| 974 |
+
"model.layers.47.mlp.experts.214.gate_proj",
|
| 975 |
+
"model.layers.47.mlp.experts.214.up_proj",
|
| 976 |
+
"model.layers.47.mlp.experts.214.down_proj",
|
| 977 |
+
"model.layers.47.mlp.experts.215.gate_proj",
|
| 978 |
+
"model.layers.47.mlp.experts.215.up_proj",
|
| 979 |
+
"model.layers.47.mlp.experts.215.down_proj",
|
| 980 |
+
"model.layers.47.mlp.experts.216.gate_proj",
|
| 981 |
+
"model.layers.47.mlp.experts.216.up_proj",
|
| 982 |
+
"model.layers.47.mlp.experts.216.down_proj",
|
| 983 |
+
"model.layers.47.mlp.experts.217.gate_proj",
|
| 984 |
+
"model.layers.47.mlp.experts.217.up_proj",
|
| 985 |
+
"model.layers.47.mlp.experts.217.down_proj",
|
| 986 |
+
"model.layers.47.mlp.experts.218.gate_proj",
|
| 987 |
+
"model.layers.47.mlp.experts.218.up_proj",
|
| 988 |
+
"model.layers.47.mlp.experts.218.down_proj",
|
| 989 |
+
"model.layers.47.mlp.experts.219.gate_proj",
|
| 990 |
+
"model.layers.47.mlp.experts.219.up_proj",
|
| 991 |
+
"model.layers.47.mlp.experts.219.down_proj",
|
| 992 |
+
"model.layers.47.mlp.experts.220.gate_proj",
|
| 993 |
+
"model.layers.47.mlp.experts.220.up_proj",
|
| 994 |
+
"model.layers.47.mlp.experts.220.down_proj",
|
| 995 |
+
"model.layers.47.mlp.experts.221.gate_proj",
|
| 996 |
+
"model.layers.47.mlp.experts.221.up_proj",
|
| 997 |
+
"model.layers.47.mlp.experts.221.down_proj",
|
| 998 |
+
"model.layers.47.mlp.experts.222.gate_proj",
|
| 999 |
+
"model.layers.47.mlp.experts.222.up_proj",
|
| 1000 |
+
"model.layers.47.mlp.experts.222.down_proj",
|
| 1001 |
+
"model.layers.47.mlp.experts.223.gate_proj",
|
| 1002 |
+
"model.layers.47.mlp.experts.223.up_proj",
|
| 1003 |
+
"model.layers.47.mlp.experts.223.down_proj",
|
| 1004 |
+
"model.layers.47.mlp.experts.224.gate_proj",
|
| 1005 |
+
"model.layers.47.mlp.experts.224.up_proj",
|
| 1006 |
+
"model.layers.47.mlp.experts.224.down_proj",
|
| 1007 |
+
"model.layers.47.mlp.experts.225.gate_proj",
|
| 1008 |
+
"model.layers.47.mlp.experts.225.up_proj",
|
| 1009 |
+
"model.layers.47.mlp.experts.225.down_proj",
|
| 1010 |
+
"model.layers.47.mlp.experts.226.gate_proj",
|
| 1011 |
+
"model.layers.47.mlp.experts.226.up_proj",
|
| 1012 |
+
"model.layers.47.mlp.experts.226.down_proj",
|
| 1013 |
+
"model.layers.47.mlp.experts.227.gate_proj",
|
| 1014 |
+
"model.layers.47.mlp.experts.227.up_proj",
|
| 1015 |
+
"model.layers.47.mlp.experts.227.down_proj",
|
| 1016 |
+
"model.layers.47.mlp.experts.228.gate_proj",
|
| 1017 |
+
"model.layers.47.mlp.experts.228.up_proj",
|
| 1018 |
+
"model.layers.47.mlp.experts.228.down_proj",
|
| 1019 |
+
"model.layers.47.mlp.experts.229.gate_proj",
|
| 1020 |
+
"model.layers.47.mlp.experts.229.up_proj",
|
| 1021 |
+
"model.layers.47.mlp.experts.229.down_proj",
|
| 1022 |
+
"model.layers.47.mlp.experts.230.gate_proj",
|
| 1023 |
+
"model.layers.47.mlp.experts.230.up_proj",
|
| 1024 |
+
"model.layers.47.mlp.experts.230.down_proj",
|
| 1025 |
+
"model.layers.47.mlp.experts.231.gate_proj",
|
| 1026 |
+
"model.layers.47.mlp.experts.231.up_proj",
|
| 1027 |
+
"model.layers.47.mlp.experts.231.down_proj",
|
| 1028 |
+
"model.layers.47.mlp.experts.232.gate_proj",
|
| 1029 |
+
"model.layers.47.mlp.experts.232.up_proj",
|
| 1030 |
+
"model.layers.47.mlp.experts.232.down_proj",
|
| 1031 |
+
"model.layers.47.mlp.experts.233.gate_proj",
|
| 1032 |
+
"model.layers.47.mlp.experts.233.up_proj",
|
| 1033 |
+
"model.layers.47.mlp.experts.233.down_proj",
|
| 1034 |
+
"model.layers.47.mlp.experts.234.gate_proj",
|
| 1035 |
+
"model.layers.47.mlp.experts.234.up_proj",
|
| 1036 |
+
"model.layers.47.mlp.experts.234.down_proj",
|
| 1037 |
+
"model.layers.47.mlp.experts.235.gate_proj",
|
| 1038 |
+
"model.layers.47.mlp.experts.235.up_proj",
|
| 1039 |
+
"model.layers.47.mlp.experts.235.down_proj",
|
| 1040 |
+
"model.layers.47.mlp.experts.236.gate_proj",
|
| 1041 |
+
"model.layers.47.mlp.experts.236.up_proj",
|
| 1042 |
+
"model.layers.47.mlp.experts.236.down_proj",
|
| 1043 |
+
"model.layers.47.mlp.experts.237.gate_proj",
|
| 1044 |
+
"model.layers.47.mlp.experts.237.up_proj",
|
| 1045 |
+
"model.layers.47.mlp.experts.237.down_proj",
|
| 1046 |
+
"model.layers.47.mlp.experts.238.gate_proj",
|
| 1047 |
+
"model.layers.47.mlp.experts.238.up_proj",
|
| 1048 |
+
"model.layers.47.mlp.experts.238.down_proj",
|
| 1049 |
+
"model.layers.47.mlp.experts.239.gate_proj",
|
| 1050 |
+
"model.layers.47.mlp.experts.239.up_proj",
|
| 1051 |
+
"model.layers.47.mlp.experts.239.down_proj",
|
| 1052 |
+
"model.layers.47.mlp.experts.240.gate_proj",
|
| 1053 |
+
"model.layers.47.mlp.experts.240.up_proj",
|
| 1054 |
+
"model.layers.47.mlp.experts.240.down_proj",
|
| 1055 |
+
"model.layers.47.mlp.experts.241.gate_proj",
|
| 1056 |
+
"model.layers.47.mlp.experts.241.up_proj",
|
| 1057 |
+
"model.layers.47.mlp.experts.241.down_proj",
|
| 1058 |
+
"model.layers.47.mlp.experts.242.gate_proj",
|
| 1059 |
+
"model.layers.47.mlp.experts.242.up_proj",
|
| 1060 |
+
"model.layers.47.mlp.experts.242.down_proj",
|
| 1061 |
+
"model.layers.47.mlp.experts.243.gate_proj",
|
| 1062 |
+
"model.layers.47.mlp.experts.243.up_proj",
|
| 1063 |
+
"model.layers.47.mlp.experts.243.down_proj",
|
| 1064 |
+
"model.layers.47.mlp.experts.244.gate_proj",
|
| 1065 |
+
"model.layers.47.mlp.experts.244.up_proj",
|
| 1066 |
+
"model.layers.47.mlp.experts.244.down_proj",
|
| 1067 |
+
"model.layers.47.mlp.experts.245.gate_proj",
|
| 1068 |
+
"model.layers.47.mlp.experts.245.up_proj",
|
| 1069 |
+
"model.layers.47.mlp.experts.245.down_proj",
|
| 1070 |
+
"model.layers.47.mlp.experts.246.gate_proj",
|
| 1071 |
+
"model.layers.47.mlp.experts.246.up_proj",
|
| 1072 |
+
"model.layers.47.mlp.experts.246.down_proj",
|
| 1073 |
+
"model.layers.47.mlp.experts.247.gate_proj",
|
| 1074 |
+
"model.layers.47.mlp.experts.247.up_proj",
|
| 1075 |
+
"model.layers.47.mlp.experts.247.down_proj",
|
| 1076 |
+
"model.layers.47.mlp.experts.248.gate_proj",
|
| 1077 |
+
"model.layers.47.mlp.experts.248.up_proj",
|
| 1078 |
+
"model.layers.47.mlp.experts.248.down_proj",
|
| 1079 |
+
"model.layers.47.mlp.experts.249.gate_proj",
|
| 1080 |
+
"model.layers.47.mlp.experts.249.up_proj",
|
| 1081 |
+
"model.layers.47.mlp.experts.249.down_proj",
|
| 1082 |
+
"model.layers.47.mlp.experts.250.gate_proj",
|
| 1083 |
+
"model.layers.47.mlp.experts.250.up_proj",
|
| 1084 |
+
"model.layers.47.mlp.experts.250.down_proj",
|
| 1085 |
+
"model.layers.47.mlp.experts.251.gate_proj",
|
| 1086 |
+
"model.layers.47.mlp.experts.251.up_proj",
|
| 1087 |
+
"model.layers.47.mlp.experts.251.down_proj",
|
| 1088 |
+
"model.layers.47.mlp.experts.252.gate_proj",
|
| 1089 |
+
"model.layers.47.mlp.experts.252.up_proj",
|
| 1090 |
+
"model.layers.47.mlp.experts.252.down_proj",
|
| 1091 |
+
"model.layers.47.mlp.experts.253.gate_proj",
|
| 1092 |
+
"model.layers.47.mlp.experts.253.up_proj",
|
| 1093 |
+
"model.layers.47.mlp.experts.253.down_proj",
|
| 1094 |
+
"model.layers.47.mlp.experts.254.gate_proj",
|
| 1095 |
+
"model.layers.47.mlp.experts.254.up_proj",
|
| 1096 |
+
"model.layers.47.mlp.experts.254.down_proj",
|
| 1097 |
+
"model.layers.47.mlp.experts.255.gate_proj",
|
| 1098 |
+
"model.layers.47.mlp.experts.255.up_proj",
|
| 1099 |
+
"model.layers.47.mlp.experts.255.down_proj",
|
| 1100 |
+
"model.layers.47.mlp.experts.256.gate_proj",
|
| 1101 |
+
"model.layers.47.mlp.experts.256.up_proj",
|
| 1102 |
+
"model.layers.47.mlp.experts.256.down_proj",
|
| 1103 |
+
"model.layers.47.mlp.experts.257.gate_proj",
|
| 1104 |
+
"model.layers.47.mlp.experts.257.up_proj",
|
| 1105 |
+
"model.layers.47.mlp.experts.257.down_proj",
|
| 1106 |
+
"model.layers.47.mlp.experts.258.gate_proj",
|
| 1107 |
+
"model.layers.47.mlp.experts.258.up_proj",
|
| 1108 |
+
"model.layers.47.mlp.experts.258.down_proj",
|
| 1109 |
+
"model.layers.47.mlp.experts.259.gate_proj",
|
| 1110 |
+
"model.layers.47.mlp.experts.259.up_proj",
|
| 1111 |
+
"model.layers.47.mlp.experts.259.down_proj",
|
| 1112 |
+
"model.layers.47.mlp.experts.260.gate_proj",
|
| 1113 |
+
"model.layers.47.mlp.experts.260.up_proj",
|
| 1114 |
+
"model.layers.47.mlp.experts.260.down_proj",
|
| 1115 |
+
"model.layers.47.mlp.experts.261.gate_proj",
|
| 1116 |
+
"model.layers.47.mlp.experts.261.up_proj",
|
| 1117 |
+
"model.layers.47.mlp.experts.261.down_proj",
|
| 1118 |
+
"model.layers.47.mlp.experts.262.gate_proj",
|
| 1119 |
+
"model.layers.47.mlp.experts.262.up_proj",
|
| 1120 |
+
"model.layers.47.mlp.experts.262.down_proj",
|
| 1121 |
+
"model.layers.47.mlp.experts.263.gate_proj",
|
| 1122 |
+
"model.layers.47.mlp.experts.263.up_proj",
|
| 1123 |
+
"model.layers.47.mlp.experts.263.down_proj",
|
| 1124 |
+
"model.layers.47.mlp.experts.264.gate_proj",
|
| 1125 |
+
"model.layers.47.mlp.experts.264.up_proj",
|
| 1126 |
+
"model.layers.47.mlp.experts.264.down_proj",
|
| 1127 |
+
"model.layers.47.mlp.experts.265.gate_proj",
|
| 1128 |
+
"model.layers.47.mlp.experts.265.up_proj",
|
| 1129 |
+
"model.layers.47.mlp.experts.265.down_proj",
|
| 1130 |
+
"model.layers.47.mlp.experts.266.gate_proj",
|
| 1131 |
+
"model.layers.47.mlp.experts.266.up_proj",
|
| 1132 |
+
"model.layers.47.mlp.experts.266.down_proj",
|
| 1133 |
+
"model.layers.47.mlp.experts.267.gate_proj",
|
| 1134 |
+
"model.layers.47.mlp.experts.267.up_proj",
|
| 1135 |
+
"model.layers.47.mlp.experts.267.down_proj",
|
| 1136 |
+
"model.layers.47.mlp.experts.268.gate_proj",
|
| 1137 |
+
"model.layers.47.mlp.experts.268.up_proj",
|
| 1138 |
+
"model.layers.47.mlp.experts.268.down_proj",
|
| 1139 |
+
"model.layers.47.mlp.experts.269.gate_proj",
|
| 1140 |
+
"model.layers.47.mlp.experts.269.up_proj",
|
| 1141 |
+
"model.layers.47.mlp.experts.269.down_proj",
|
| 1142 |
+
"model.layers.47.mlp.experts.270.gate_proj",
|
| 1143 |
+
"model.layers.47.mlp.experts.270.up_proj",
|
| 1144 |
+
"model.layers.47.mlp.experts.270.down_proj",
|
| 1145 |
+
"model.layers.47.mlp.experts.271.gate_proj",
|
| 1146 |
+
"model.layers.47.mlp.experts.271.up_proj",
|
| 1147 |
+
"model.layers.47.mlp.experts.271.down_proj",
|
| 1148 |
+
"model.layers.47.mlp.experts.272.gate_proj",
|
| 1149 |
+
"model.layers.47.mlp.experts.272.up_proj",
|
| 1150 |
+
"model.layers.47.mlp.experts.272.down_proj",
|
| 1151 |
+
"model.layers.47.mlp.experts.273.gate_proj",
|
| 1152 |
+
"model.layers.47.mlp.experts.273.up_proj",
|
| 1153 |
+
"model.layers.47.mlp.experts.273.down_proj",
|
| 1154 |
+
"model.layers.47.mlp.experts.274.gate_proj",
|
| 1155 |
+
"model.layers.47.mlp.experts.274.up_proj",
|
| 1156 |
+
"model.layers.47.mlp.experts.274.down_proj",
|
| 1157 |
+
"model.layers.47.mlp.experts.275.gate_proj",
|
| 1158 |
+
"model.layers.47.mlp.experts.275.up_proj",
|
| 1159 |
+
"model.layers.47.mlp.experts.275.down_proj",
|
| 1160 |
+
"model.layers.47.mlp.experts.276.gate_proj",
|
| 1161 |
+
"model.layers.47.mlp.experts.276.up_proj",
|
| 1162 |
+
"model.layers.47.mlp.experts.276.down_proj",
|
| 1163 |
+
"model.layers.47.mlp.experts.277.gate_proj",
|
| 1164 |
+
"model.layers.47.mlp.experts.277.up_proj",
|
| 1165 |
+
"model.layers.47.mlp.experts.277.down_proj",
|
| 1166 |
+
"model.layers.47.mlp.experts.278.gate_proj",
|
| 1167 |
+
"model.layers.47.mlp.experts.278.up_proj",
|
| 1168 |
+
"model.layers.47.mlp.experts.278.down_proj",
|
| 1169 |
+
"model.layers.47.mlp.experts.279.gate_proj",
|
| 1170 |
+
"model.layers.47.mlp.experts.279.up_proj",
|
| 1171 |
+
"model.layers.47.mlp.experts.279.down_proj",
|
| 1172 |
+
"model.layers.47.mlp.experts.280.gate_proj",
|
| 1173 |
+
"model.layers.47.mlp.experts.280.up_proj",
|
| 1174 |
+
"model.layers.47.mlp.experts.280.down_proj",
|
| 1175 |
+
"model.layers.47.mlp.experts.281.gate_proj",
|
| 1176 |
+
"model.layers.47.mlp.experts.281.up_proj",
|
| 1177 |
+
"model.layers.47.mlp.experts.281.down_proj",
|
| 1178 |
+
"model.layers.47.mlp.experts.282.gate_proj",
|
| 1179 |
+
"model.layers.47.mlp.experts.282.up_proj",
|
| 1180 |
+
"model.layers.47.mlp.experts.282.down_proj",
|
| 1181 |
+
"model.layers.47.mlp.experts.283.gate_proj",
|
| 1182 |
+
"model.layers.47.mlp.experts.283.up_proj",
|
| 1183 |
+
"model.layers.47.mlp.experts.283.down_proj",
|
| 1184 |
+
"model.layers.47.mlp.experts.284.gate_proj",
|
| 1185 |
+
"model.layers.47.mlp.experts.284.up_proj",
|
| 1186 |
+
"model.layers.47.mlp.experts.284.down_proj",
|
| 1187 |
+
"model.layers.47.mlp.experts.285.gate_proj",
|
| 1188 |
+
"model.layers.47.mlp.experts.285.up_proj",
|
| 1189 |
+
"model.layers.47.mlp.experts.285.down_proj",
|
| 1190 |
+
"model.layers.47.mlp.experts.286.gate_proj",
|
| 1191 |
+
"model.layers.47.mlp.experts.286.up_proj",
|
| 1192 |
+
"model.layers.47.mlp.experts.286.down_proj",
|
| 1193 |
+
"model.layers.47.mlp.experts.287.gate_proj",
|
| 1194 |
+
"model.layers.47.mlp.experts.287.up_proj",
|
| 1195 |
+
"model.layers.47.mlp.experts.287.down_proj",
|
| 1196 |
+
"model.layers.47.mlp.experts.288.gate_proj",
|
| 1197 |
+
"model.layers.47.mlp.experts.288.up_proj",
|
| 1198 |
+
"model.layers.47.mlp.experts.288.down_proj",
|
| 1199 |
+
"model.layers.47.mlp.experts.289.gate_proj",
|
| 1200 |
+
"model.layers.47.mlp.experts.289.up_proj",
|
| 1201 |
+
"model.layers.47.mlp.experts.289.down_proj",
|
| 1202 |
+
"model.layers.47.mlp.experts.290.gate_proj",
|
| 1203 |
+
"model.layers.47.mlp.experts.290.up_proj",
|
| 1204 |
+
"model.layers.47.mlp.experts.290.down_proj",
|
| 1205 |
+
"model.layers.47.mlp.experts.291.gate_proj",
|
| 1206 |
+
"model.layers.47.mlp.experts.291.up_proj",
|
| 1207 |
+
"model.layers.47.mlp.experts.291.down_proj",
|
| 1208 |
+
"model.layers.47.mlp.experts.292.gate_proj",
|
| 1209 |
+
"model.layers.47.mlp.experts.292.up_proj",
|
| 1210 |
+
"model.layers.47.mlp.experts.292.down_proj",
|
| 1211 |
+
"model.layers.47.mlp.experts.293.gate_proj",
|
| 1212 |
+
"model.layers.47.mlp.experts.293.up_proj",
|
| 1213 |
+
"model.layers.47.mlp.experts.293.down_proj",
|
| 1214 |
+
"model.layers.47.mlp.experts.294.gate_proj",
|
| 1215 |
+
"model.layers.47.mlp.experts.294.up_proj",
|
| 1216 |
+
"model.layers.47.mlp.experts.294.down_proj",
|
| 1217 |
+
"model.layers.47.mlp.experts.295.gate_proj",
|
| 1218 |
+
"model.layers.47.mlp.experts.295.up_proj",
|
| 1219 |
+
"model.layers.47.mlp.experts.295.down_proj",
|
| 1220 |
+
"model.layers.47.mlp.experts.296.gate_proj",
|
| 1221 |
+
"model.layers.47.mlp.experts.296.up_proj",
|
| 1222 |
+
"model.layers.47.mlp.experts.296.down_proj",
|
| 1223 |
+
"model.layers.47.mlp.experts.297.gate_proj",
|
| 1224 |
+
"model.layers.47.mlp.experts.297.up_proj",
|
| 1225 |
+
"model.layers.47.mlp.experts.297.down_proj",
|
| 1226 |
+
"model.layers.47.mlp.experts.298.gate_proj",
|
| 1227 |
+
"model.layers.47.mlp.experts.298.up_proj",
|
| 1228 |
+
"model.layers.47.mlp.experts.298.down_proj",
|
| 1229 |
+
"model.layers.47.mlp.experts.299.gate_proj",
|
| 1230 |
+
"model.layers.47.mlp.experts.299.up_proj",
|
| 1231 |
+
"model.layers.47.mlp.experts.299.down_proj",
|
| 1232 |
+
"model.layers.47.mlp.experts.300.gate_proj",
|
| 1233 |
+
"model.layers.47.mlp.experts.300.up_proj",
|
| 1234 |
+
"model.layers.47.mlp.experts.300.down_proj",
|
| 1235 |
+
"model.layers.47.mlp.experts.301.gate_proj",
|
| 1236 |
+
"model.layers.47.mlp.experts.301.up_proj",
|
| 1237 |
+
"model.layers.47.mlp.experts.301.down_proj",
|
| 1238 |
+
"model.layers.47.mlp.experts.302.gate_proj",
|
| 1239 |
+
"model.layers.47.mlp.experts.302.up_proj",
|
| 1240 |
+
"model.layers.47.mlp.experts.302.down_proj",
|
| 1241 |
+
"model.layers.47.mlp.experts.303.gate_proj",
|
| 1242 |
+
"model.layers.47.mlp.experts.303.up_proj",
|
| 1243 |
+
"model.layers.47.mlp.experts.303.down_proj",
|
| 1244 |
+
"model.layers.47.mlp.experts.304.gate_proj",
|
| 1245 |
+
"model.layers.47.mlp.experts.304.up_proj",
|
| 1246 |
+
"model.layers.47.mlp.experts.304.down_proj",
|
| 1247 |
+
"model.layers.47.mlp.experts.305.gate_proj",
|
| 1248 |
+
"model.layers.47.mlp.experts.305.up_proj",
|
| 1249 |
+
"model.layers.47.mlp.experts.305.down_proj",
|
| 1250 |
+
"model.layers.47.mlp.experts.306.gate_proj",
|
| 1251 |
+
"model.layers.47.mlp.experts.306.up_proj",
|
| 1252 |
+
"model.layers.47.mlp.experts.306.down_proj",
|
| 1253 |
+
"model.layers.47.mlp.experts.307.gate_proj",
|
| 1254 |
+
"model.layers.47.mlp.experts.307.up_proj",
|
| 1255 |
+
"model.layers.47.mlp.experts.307.down_proj",
|
| 1256 |
+
"model.layers.47.mlp.experts.308.gate_proj",
|
| 1257 |
+
"model.layers.47.mlp.experts.308.up_proj",
|
| 1258 |
+
"model.layers.47.mlp.experts.308.down_proj",
|
| 1259 |
+
"model.layers.47.mlp.experts.309.gate_proj",
|
| 1260 |
+
"model.layers.47.mlp.experts.309.up_proj",
|
| 1261 |
+
"model.layers.47.mlp.experts.309.down_proj",
|
| 1262 |
+
"model.layers.47.mlp.experts.310.gate_proj",
|
| 1263 |
+
"model.layers.47.mlp.experts.310.up_proj",
|
| 1264 |
+
"model.layers.47.mlp.experts.310.down_proj",
|
| 1265 |
+
"model.layers.47.mlp.experts.311.gate_proj",
|
| 1266 |
+
"model.layers.47.mlp.experts.311.up_proj",
|
| 1267 |
+
"model.layers.47.mlp.experts.311.down_proj",
|
| 1268 |
+
"model.layers.47.mlp.experts.312.gate_proj",
|
| 1269 |
+
"model.layers.47.mlp.experts.312.up_proj",
|
| 1270 |
+
"model.layers.47.mlp.experts.312.down_proj",
|
| 1271 |
+
"model.layers.47.mlp.experts.313.gate_proj",
|
| 1272 |
+
"model.layers.47.mlp.experts.313.up_proj",
|
| 1273 |
+
"model.layers.47.mlp.experts.313.down_proj",
|
| 1274 |
+
"model.layers.47.mlp.experts.314.gate_proj",
|
| 1275 |
+
"model.layers.47.mlp.experts.314.up_proj",
|
| 1276 |
+
"model.layers.47.mlp.experts.314.down_proj",
|
| 1277 |
+
"model.layers.47.mlp.experts.315.gate_proj",
|
| 1278 |
+
"model.layers.47.mlp.experts.315.up_proj",
|
| 1279 |
+
"model.layers.47.mlp.experts.315.down_proj",
|
| 1280 |
+
"model.layers.47.mlp.experts.316.gate_proj",
|
| 1281 |
+
"model.layers.47.mlp.experts.316.up_proj",
|
| 1282 |
+
"model.layers.47.mlp.experts.316.down_proj",
|
| 1283 |
+
"model.layers.47.mlp.experts.317.gate_proj",
|
| 1284 |
+
"model.layers.47.mlp.experts.317.up_proj",
|
| 1285 |
+
"model.layers.47.mlp.experts.317.down_proj",
|
| 1286 |
+
"model.layers.47.mlp.experts.318.gate_proj",
|
| 1287 |
+
"model.layers.47.mlp.experts.318.up_proj",
|
| 1288 |
+
"model.layers.47.mlp.experts.318.down_proj",
|
| 1289 |
+
"model.layers.47.mlp.experts.319.gate_proj",
|
| 1290 |
+
"model.layers.47.mlp.experts.319.up_proj",
|
| 1291 |
+
"model.layers.47.mlp.experts.319.down_proj",
|
| 1292 |
+
"model.layers.47.mlp.experts.320.gate_proj",
|
| 1293 |
+
"model.layers.47.mlp.experts.320.up_proj",
|
| 1294 |
+
"model.layers.47.mlp.experts.320.down_proj",
|
| 1295 |
+
"model.layers.47.mlp.experts.321.gate_proj",
|
| 1296 |
+
"model.layers.47.mlp.experts.321.up_proj",
|
| 1297 |
+
"model.layers.47.mlp.experts.321.down_proj",
|
| 1298 |
+
"model.layers.47.mlp.experts.322.gate_proj",
|
| 1299 |
+
"model.layers.47.mlp.experts.322.up_proj",
|
| 1300 |
+
"model.layers.47.mlp.experts.322.down_proj",
|
| 1301 |
+
"model.layers.47.mlp.experts.323.gate_proj",
|
| 1302 |
+
"model.layers.47.mlp.experts.323.up_proj",
|
| 1303 |
+
"model.layers.47.mlp.experts.323.down_proj",
|
| 1304 |
+
"model.layers.47.mlp.experts.324.gate_proj",
|
| 1305 |
+
"model.layers.47.mlp.experts.324.up_proj",
|
| 1306 |
+
"model.layers.47.mlp.experts.324.down_proj",
|
| 1307 |
+
"model.layers.47.mlp.experts.325.gate_proj",
|
| 1308 |
+
"model.layers.47.mlp.experts.325.up_proj",
|
| 1309 |
+
"model.layers.47.mlp.experts.325.down_proj",
|
| 1310 |
+
"model.layers.47.mlp.experts.326.gate_proj",
|
| 1311 |
+
"model.layers.47.mlp.experts.326.up_proj",
|
| 1312 |
+
"model.layers.47.mlp.experts.326.down_proj",
|
| 1313 |
+
"model.layers.47.mlp.experts.327.gate_proj",
|
| 1314 |
+
"model.layers.47.mlp.experts.327.up_proj",
|
| 1315 |
+
"model.layers.47.mlp.experts.327.down_proj",
|
| 1316 |
+
"model.layers.47.mlp.experts.328.gate_proj",
|
| 1317 |
+
"model.layers.47.mlp.experts.328.up_proj",
|
| 1318 |
+
"model.layers.47.mlp.experts.328.down_proj",
|
| 1319 |
+
"model.layers.47.mlp.experts.329.gate_proj",
|
| 1320 |
+
"model.layers.47.mlp.experts.329.up_proj",
|
| 1321 |
+
"model.layers.47.mlp.experts.329.down_proj",
|
| 1322 |
+
"model.layers.47.mlp.experts.330.gate_proj",
|
| 1323 |
+
"model.layers.47.mlp.experts.330.up_proj",
|
| 1324 |
+
"model.layers.47.mlp.experts.330.down_proj",
|
| 1325 |
+
"model.layers.47.mlp.experts.331.gate_proj",
|
| 1326 |
+
"model.layers.47.mlp.experts.331.up_proj",
|
| 1327 |
+
"model.layers.47.mlp.experts.331.down_proj",
|
| 1328 |
+
"model.layers.47.mlp.experts.332.gate_proj",
|
| 1329 |
+
"model.layers.47.mlp.experts.332.up_proj",
|
| 1330 |
+
"model.layers.47.mlp.experts.332.down_proj",
|
| 1331 |
+
"model.layers.47.mlp.experts.333.gate_proj",
|
| 1332 |
+
"model.layers.47.mlp.experts.333.up_proj",
|
| 1333 |
+
"model.layers.47.mlp.experts.333.down_proj",
|
| 1334 |
+
"model.layers.47.mlp.experts.334.gate_proj",
|
| 1335 |
+
"model.layers.47.mlp.experts.334.up_proj",
|
| 1336 |
+
"model.layers.47.mlp.experts.334.down_proj",
|
| 1337 |
+
"model.layers.47.mlp.experts.335.gate_proj",
|
| 1338 |
+
"model.layers.47.mlp.experts.335.up_proj",
|
| 1339 |
+
"model.layers.47.mlp.experts.335.down_proj",
|
| 1340 |
+
"model.layers.47.mlp.experts.336.gate_proj",
|
| 1341 |
+
"model.layers.47.mlp.experts.336.up_proj",
|
| 1342 |
+
"model.layers.47.mlp.experts.336.down_proj",
|
| 1343 |
+
"model.layers.47.mlp.experts.337.gate_proj",
|
| 1344 |
+
"model.layers.47.mlp.experts.337.up_proj",
|
| 1345 |
+
"model.layers.47.mlp.experts.337.down_proj",
|
| 1346 |
+
"model.layers.47.mlp.experts.338.gate_proj",
|
| 1347 |
+
"model.layers.47.mlp.experts.338.up_proj",
|
| 1348 |
+
"model.layers.47.mlp.experts.338.down_proj",
|
| 1349 |
+
"model.layers.47.mlp.experts.339.gate_proj",
|
| 1350 |
+
"model.layers.47.mlp.experts.339.up_proj",
|
| 1351 |
+
"model.layers.47.mlp.experts.339.down_proj",
|
| 1352 |
+
"model.layers.47.mlp.experts.340.gate_proj",
|
| 1353 |
+
"model.layers.47.mlp.experts.340.up_proj",
|
| 1354 |
+
"model.layers.47.mlp.experts.340.down_proj",
|
| 1355 |
+
"model.layers.47.mlp.experts.341.gate_proj",
|
| 1356 |
+
"model.layers.47.mlp.experts.341.up_proj",
|
| 1357 |
+
"model.layers.47.mlp.experts.341.down_proj",
|
| 1358 |
+
"model.layers.47.mlp.experts.342.gate_proj",
|
| 1359 |
+
"model.layers.47.mlp.experts.342.up_proj",
|
| 1360 |
+
"model.layers.47.mlp.experts.342.down_proj",
|
| 1361 |
+
"model.layers.47.mlp.experts.343.gate_proj",
|
| 1362 |
+
"model.layers.47.mlp.experts.343.up_proj",
|
| 1363 |
+
"model.layers.47.mlp.experts.343.down_proj",
|
| 1364 |
+
"model.layers.47.mlp.experts.344.gate_proj",
|
| 1365 |
+
"model.layers.47.mlp.experts.344.up_proj",
|
| 1366 |
+
"model.layers.47.mlp.experts.344.down_proj",
|
| 1367 |
+
"model.layers.47.mlp.experts.345.gate_proj",
|
| 1368 |
+
"model.layers.47.mlp.experts.345.up_proj",
|
| 1369 |
+
"model.layers.47.mlp.experts.345.down_proj",
|
| 1370 |
+
"model.layers.47.mlp.experts.346.gate_proj",
|
| 1371 |
+
"model.layers.47.mlp.experts.346.up_proj",
|
| 1372 |
+
"model.layers.47.mlp.experts.346.down_proj",
|
| 1373 |
+
"model.layers.47.mlp.experts.347.gate_proj",
|
| 1374 |
+
"model.layers.47.mlp.experts.347.up_proj",
|
| 1375 |
+
"model.layers.47.mlp.experts.347.down_proj",
|
| 1376 |
+
"model.layers.47.mlp.experts.348.gate_proj",
|
| 1377 |
+
"model.layers.47.mlp.experts.348.up_proj",
|
| 1378 |
+
"model.layers.47.mlp.experts.348.down_proj",
|
| 1379 |
+
"model.layers.47.mlp.experts.349.gate_proj",
|
| 1380 |
+
"model.layers.47.mlp.experts.349.up_proj",
|
| 1381 |
+
"model.layers.47.mlp.experts.349.down_proj",
|
| 1382 |
+
"model.layers.47.mlp.experts.350.gate_proj",
|
| 1383 |
+
"model.layers.47.mlp.experts.350.up_proj",
|
| 1384 |
+
"model.layers.47.mlp.experts.350.down_proj",
|
| 1385 |
+
"model.layers.47.mlp.experts.351.gate_proj",
|
| 1386 |
+
"model.layers.47.mlp.experts.351.up_proj",
|
| 1387 |
+
"model.layers.47.mlp.experts.351.down_proj",
|
| 1388 |
+
"model.layers.47.mlp.experts.352.gate_proj",
|
| 1389 |
+
"model.layers.47.mlp.experts.352.up_proj",
|
| 1390 |
+
"model.layers.47.mlp.experts.352.down_proj",
|
| 1391 |
+
"model.layers.47.mlp.experts.353.gate_proj",
|
| 1392 |
+
"model.layers.47.mlp.experts.353.up_proj",
|
| 1393 |
+
"model.layers.47.mlp.experts.353.down_proj",
|
| 1394 |
+
"model.layers.47.mlp.experts.354.gate_proj",
|
| 1395 |
+
"model.layers.47.mlp.experts.354.up_proj",
|
| 1396 |
+
"model.layers.47.mlp.experts.354.down_proj",
|
| 1397 |
+
"model.layers.47.mlp.experts.355.gate_proj",
|
| 1398 |
+
"model.layers.47.mlp.experts.355.up_proj",
|
| 1399 |
+
"model.layers.47.mlp.experts.355.down_proj",
|
| 1400 |
+
"model.layers.47.mlp.experts.356.gate_proj",
|
| 1401 |
+
"model.layers.47.mlp.experts.356.up_proj",
|
| 1402 |
+
"model.layers.47.mlp.experts.356.down_proj",
|
| 1403 |
+
"model.layers.47.mlp.experts.357.gate_proj",
|
| 1404 |
+
"model.layers.47.mlp.experts.357.up_proj",
|
| 1405 |
+
"model.layers.47.mlp.experts.357.down_proj",
|
| 1406 |
+
"model.layers.47.mlp.experts.358.gate_proj",
|
| 1407 |
+
"model.layers.47.mlp.experts.358.up_proj",
|
| 1408 |
+
"model.layers.47.mlp.experts.358.down_proj",
|
| 1409 |
+
"model.layers.47.mlp.experts.359.gate_proj",
|
| 1410 |
+
"model.layers.47.mlp.experts.359.up_proj",
|
| 1411 |
+
"model.layers.47.mlp.experts.359.down_proj",
|
| 1412 |
+
"model.layers.47.mlp.experts.360.gate_proj",
|
| 1413 |
+
"model.layers.47.mlp.experts.360.up_proj",
|
| 1414 |
+
"model.layers.47.mlp.experts.360.down_proj",
|
| 1415 |
+
"model.layers.47.mlp.experts.361.gate_proj",
|
| 1416 |
+
"model.layers.47.mlp.experts.361.up_proj",
|
| 1417 |
+
"model.layers.47.mlp.experts.361.down_proj",
|
| 1418 |
+
"model.layers.47.mlp.experts.362.gate_proj",
|
| 1419 |
+
"model.layers.47.mlp.experts.362.up_proj",
|
| 1420 |
+
"model.layers.47.mlp.experts.362.down_proj",
|
| 1421 |
+
"model.layers.47.mlp.experts.363.gate_proj",
|
| 1422 |
+
"model.layers.47.mlp.experts.363.up_proj",
|
| 1423 |
+
"model.layers.47.mlp.experts.363.down_proj",
|
| 1424 |
+
"model.layers.47.mlp.experts.364.gate_proj",
|
| 1425 |
+
"model.layers.47.mlp.experts.364.up_proj",
|
| 1426 |
+
"model.layers.47.mlp.experts.364.down_proj",
|
| 1427 |
+
"model.layers.47.mlp.experts.365.gate_proj",
|
| 1428 |
+
"model.layers.47.mlp.experts.365.up_proj",
|
| 1429 |
+
"model.layers.47.mlp.experts.365.down_proj",
|
| 1430 |
+
"model.layers.47.mlp.experts.366.gate_proj",
|
| 1431 |
+
"model.layers.47.mlp.experts.366.up_proj",
|
| 1432 |
+
"model.layers.47.mlp.experts.366.down_proj",
|
| 1433 |
+
"model.layers.47.mlp.experts.367.gate_proj",
|
| 1434 |
+
"model.layers.47.mlp.experts.367.up_proj",
|
| 1435 |
+
"model.layers.47.mlp.experts.367.down_proj",
|
| 1436 |
+
"model.layers.47.mlp.experts.368.gate_proj",
|
| 1437 |
+
"model.layers.47.mlp.experts.368.up_proj",
|
| 1438 |
+
"model.layers.47.mlp.experts.368.down_proj",
|
| 1439 |
+
"model.layers.47.mlp.experts.369.gate_proj",
|
| 1440 |
+
"model.layers.47.mlp.experts.369.up_proj",
|
| 1441 |
+
"model.layers.47.mlp.experts.369.down_proj",
|
| 1442 |
+
"model.layers.47.mlp.experts.370.gate_proj",
|
| 1443 |
+
"model.layers.47.mlp.experts.370.up_proj",
|
| 1444 |
+
"model.layers.47.mlp.experts.370.down_proj",
|
| 1445 |
+
"model.layers.47.mlp.experts.371.gate_proj",
|
| 1446 |
+
"model.layers.47.mlp.experts.371.up_proj",
|
| 1447 |
+
"model.layers.47.mlp.experts.371.down_proj",
|
| 1448 |
+
"model.layers.47.mlp.experts.372.gate_proj",
|
| 1449 |
+
"model.layers.47.mlp.experts.372.up_proj",
|
| 1450 |
+
"model.layers.47.mlp.experts.372.down_proj",
|
| 1451 |
+
"model.layers.47.mlp.experts.373.gate_proj",
|
| 1452 |
+
"model.layers.47.mlp.experts.373.up_proj",
|
| 1453 |
+
"model.layers.47.mlp.experts.373.down_proj",
|
| 1454 |
+
"model.layers.47.mlp.experts.374.gate_proj",
|
| 1455 |
+
"model.layers.47.mlp.experts.374.up_proj",
|
| 1456 |
+
"model.layers.47.mlp.experts.374.down_proj",
|
| 1457 |
+
"model.layers.47.mlp.experts.375.gate_proj",
|
| 1458 |
+
"model.layers.47.mlp.experts.375.up_proj",
|
| 1459 |
+
"model.layers.47.mlp.experts.375.down_proj",
|
| 1460 |
+
"model.layers.47.mlp.experts.376.gate_proj",
|
| 1461 |
+
"model.layers.47.mlp.experts.376.up_proj",
|
| 1462 |
+
"model.layers.47.mlp.experts.376.down_proj",
|
| 1463 |
+
"model.layers.47.mlp.experts.377.gate_proj",
|
| 1464 |
+
"model.layers.47.mlp.experts.377.up_proj",
|
| 1465 |
+
"model.layers.47.mlp.experts.377.down_proj",
|
| 1466 |
+
"model.layers.47.mlp.experts.378.gate_proj",
|
| 1467 |
+
"model.layers.47.mlp.experts.378.up_proj",
|
| 1468 |
+
"model.layers.47.mlp.experts.378.down_proj",
|
| 1469 |
+
"model.layers.47.mlp.experts.379.gate_proj",
|
| 1470 |
+
"model.layers.47.mlp.experts.379.up_proj",
|
| 1471 |
+
"model.layers.47.mlp.experts.379.down_proj",
|
| 1472 |
+
"model.layers.47.mlp.experts.380.gate_proj",
|
| 1473 |
+
"model.layers.47.mlp.experts.380.up_proj",
|
| 1474 |
+
"model.layers.47.mlp.experts.380.down_proj",
|
| 1475 |
+
"model.layers.47.mlp.experts.381.gate_proj",
|
| 1476 |
+
"model.layers.47.mlp.experts.381.up_proj",
|
| 1477 |
+
"model.layers.47.mlp.experts.381.down_proj",
|
| 1478 |
+
"model.layers.47.mlp.experts.382.gate_proj",
|
| 1479 |
+
"model.layers.47.mlp.experts.382.up_proj",
|
| 1480 |
+
"model.layers.47.mlp.experts.382.down_proj",
|
| 1481 |
+
"model.layers.47.mlp.experts.383.gate_proj",
|
| 1482 |
+
"model.layers.47.mlp.experts.383.up_proj",
|
| 1483 |
+
"model.layers.47.mlp.experts.383.down_proj",
|
| 1484 |
+
"model.layers.47.mlp.experts.384.gate_proj",
|
| 1485 |
+
"model.layers.47.mlp.experts.384.up_proj",
|
| 1486 |
+
"model.layers.47.mlp.experts.384.down_proj",
|
| 1487 |
+
"model.layers.47.mlp.experts.385.gate_proj",
|
| 1488 |
+
"model.layers.47.mlp.experts.385.up_proj",
|
| 1489 |
+
"model.layers.47.mlp.experts.385.down_proj",
|
| 1490 |
+
"model.layers.47.mlp.experts.386.gate_proj",
|
| 1491 |
+
"model.layers.47.mlp.experts.386.up_proj",
|
| 1492 |
+
"model.layers.47.mlp.experts.386.down_proj",
|
| 1493 |
+
"model.layers.47.mlp.experts.387.gate_proj",
|
| 1494 |
+
"model.layers.47.mlp.experts.387.up_proj",
|
| 1495 |
+
"model.layers.47.mlp.experts.387.down_proj",
|
| 1496 |
+
"model.layers.47.mlp.experts.388.gate_proj",
|
| 1497 |
+
"model.layers.47.mlp.experts.388.up_proj",
|
| 1498 |
+
"model.layers.47.mlp.experts.388.down_proj",
|
| 1499 |
+
"model.layers.47.mlp.experts.389.gate_proj",
|
| 1500 |
+
"model.layers.47.mlp.experts.389.up_proj",
|
| 1501 |
+
"model.layers.47.mlp.experts.389.down_proj",
|
| 1502 |
+
"model.layers.47.mlp.experts.390.gate_proj",
|
| 1503 |
+
"model.layers.47.mlp.experts.390.up_proj",
|
| 1504 |
+
"model.layers.47.mlp.experts.390.down_proj",
|
| 1505 |
+
"model.layers.47.mlp.experts.391.gate_proj",
|
| 1506 |
+
"model.layers.47.mlp.experts.391.up_proj",
|
| 1507 |
+
"model.layers.47.mlp.experts.391.down_proj",
|
| 1508 |
+
"model.layers.47.mlp.experts.392.gate_proj",
|
| 1509 |
+
"model.layers.47.mlp.experts.392.up_proj",
|
| 1510 |
+
"model.layers.47.mlp.experts.392.down_proj",
|
| 1511 |
+
"model.layers.47.mlp.experts.393.gate_proj",
|
| 1512 |
+
"model.layers.47.mlp.experts.393.up_proj",
|
| 1513 |
+
"model.layers.47.mlp.experts.393.down_proj",
|
| 1514 |
+
"model.layers.47.mlp.experts.394.gate_proj",
|
| 1515 |
+
"model.layers.47.mlp.experts.394.up_proj",
|
| 1516 |
+
"model.layers.47.mlp.experts.394.down_proj",
|
| 1517 |
+
"model.layers.47.mlp.experts.395.gate_proj",
|
| 1518 |
+
"model.layers.47.mlp.experts.395.up_proj",
|
| 1519 |
+
"model.layers.47.mlp.experts.395.down_proj",
|
| 1520 |
+
"model.layers.47.mlp.experts.396.gate_proj",
|
| 1521 |
+
"model.layers.47.mlp.experts.396.up_proj",
|
| 1522 |
+
"model.layers.47.mlp.experts.396.down_proj",
|
| 1523 |
+
"model.layers.47.mlp.experts.397.gate_proj",
|
| 1524 |
+
"model.layers.47.mlp.experts.397.up_proj",
|
| 1525 |
+
"model.layers.47.mlp.experts.397.down_proj",
|
| 1526 |
+
"model.layers.47.mlp.experts.398.gate_proj",
|
| 1527 |
+
"model.layers.47.mlp.experts.398.up_proj",
|
| 1528 |
+
"model.layers.47.mlp.experts.398.down_proj",
|
| 1529 |
+
"model.layers.47.mlp.experts.399.gate_proj",
|
| 1530 |
+
"model.layers.47.mlp.experts.399.up_proj",
|
| 1531 |
+
"model.layers.47.mlp.experts.399.down_proj",
|
| 1532 |
+
"model.layers.47.mlp.experts.400.gate_proj",
|
| 1533 |
+
"model.layers.47.mlp.experts.400.up_proj",
|
| 1534 |
+
"model.layers.47.mlp.experts.400.down_proj",
|
| 1535 |
+
"model.layers.47.mlp.experts.401.gate_proj",
|
| 1536 |
+
"model.layers.47.mlp.experts.401.up_proj",
|
| 1537 |
+
"model.layers.47.mlp.experts.401.down_proj",
|
| 1538 |
+
"model.layers.47.mlp.experts.402.gate_proj",
|
| 1539 |
+
"model.layers.47.mlp.experts.402.up_proj",
|
| 1540 |
+
"model.layers.47.mlp.experts.402.down_proj",
|
| 1541 |
+
"model.layers.47.mlp.experts.403.gate_proj",
|
| 1542 |
+
"model.layers.47.mlp.experts.403.up_proj",
|
| 1543 |
+
"model.layers.47.mlp.experts.403.down_proj",
|
| 1544 |
+
"model.layers.47.mlp.experts.404.gate_proj",
|
| 1545 |
+
"model.layers.47.mlp.experts.404.up_proj",
|
| 1546 |
+
"model.layers.47.mlp.experts.404.down_proj",
|
| 1547 |
+
"model.layers.47.mlp.experts.405.gate_proj",
|
| 1548 |
+
"model.layers.47.mlp.experts.405.up_proj",
|
| 1549 |
+
"model.layers.47.mlp.experts.405.down_proj",
|
| 1550 |
+
"model.layers.47.mlp.experts.406.gate_proj",
|
| 1551 |
+
"model.layers.47.mlp.experts.406.up_proj",
|
| 1552 |
+
"model.layers.47.mlp.experts.406.down_proj",
|
| 1553 |
+
"model.layers.47.mlp.experts.407.gate_proj",
|
| 1554 |
+
"model.layers.47.mlp.experts.407.up_proj",
|
| 1555 |
+
"model.layers.47.mlp.experts.407.down_proj",
|
| 1556 |
+
"model.layers.47.mlp.experts.408.gate_proj",
|
| 1557 |
+
"model.layers.47.mlp.experts.408.up_proj",
|
| 1558 |
+
"model.layers.47.mlp.experts.408.down_proj",
|
| 1559 |
+
"model.layers.47.mlp.experts.409.gate_proj",
|
| 1560 |
+
"model.layers.47.mlp.experts.409.up_proj",
|
| 1561 |
+
"model.layers.47.mlp.experts.409.down_proj",
|
| 1562 |
+
"model.layers.47.mlp.experts.410.gate_proj",
|
| 1563 |
+
"model.layers.47.mlp.experts.410.up_proj",
|
| 1564 |
+
"model.layers.47.mlp.experts.410.down_proj",
|
| 1565 |
+
"model.layers.47.mlp.experts.411.gate_proj",
|
| 1566 |
+
"model.layers.47.mlp.experts.411.up_proj",
|
| 1567 |
+
"model.layers.47.mlp.experts.411.down_proj",
|
| 1568 |
+
"model.layers.47.mlp.experts.412.gate_proj",
|
| 1569 |
+
"model.layers.47.mlp.experts.412.up_proj",
|
| 1570 |
+
"model.layers.47.mlp.experts.412.down_proj",
|
| 1571 |
+
"model.layers.47.mlp.experts.413.gate_proj",
|
| 1572 |
+
"model.layers.47.mlp.experts.413.up_proj",
|
| 1573 |
+
"model.layers.47.mlp.experts.413.down_proj",
|
| 1574 |
+
"model.layers.47.mlp.experts.414.gate_proj",
|
| 1575 |
+
"model.layers.47.mlp.experts.414.up_proj",
|
| 1576 |
+
"model.layers.47.mlp.experts.414.down_proj",
|
| 1577 |
+
"model.layers.47.mlp.experts.415.gate_proj",
|
| 1578 |
+
"model.layers.47.mlp.experts.415.up_proj",
|
| 1579 |
+
"model.layers.47.mlp.experts.415.down_proj",
|
| 1580 |
+
"model.layers.47.mlp.experts.416.gate_proj",
|
| 1581 |
+
"model.layers.47.mlp.experts.416.up_proj",
|
| 1582 |
+
"model.layers.47.mlp.experts.416.down_proj",
|
| 1583 |
+
"model.layers.47.mlp.experts.417.gate_proj",
|
| 1584 |
+
"model.layers.47.mlp.experts.417.up_proj",
|
| 1585 |
+
"model.layers.47.mlp.experts.417.down_proj",
|
| 1586 |
+
"model.layers.47.mlp.experts.418.gate_proj",
|
| 1587 |
+
"model.layers.47.mlp.experts.418.up_proj",
|
| 1588 |
+
"model.layers.47.mlp.experts.418.down_proj",
|
| 1589 |
+
"model.layers.47.mlp.experts.419.gate_proj",
|
| 1590 |
+
"model.layers.47.mlp.experts.419.up_proj",
|
| 1591 |
+
"model.layers.47.mlp.experts.419.down_proj",
|
| 1592 |
+
"model.layers.47.mlp.experts.420.gate_proj",
|
| 1593 |
+
"model.layers.47.mlp.experts.420.up_proj",
|
| 1594 |
+
"model.layers.47.mlp.experts.420.down_proj",
|
| 1595 |
+
"model.layers.47.mlp.experts.421.gate_proj",
|
| 1596 |
+
"model.layers.47.mlp.experts.421.up_proj",
|
| 1597 |
+
"model.layers.47.mlp.experts.421.down_proj",
|
| 1598 |
+
"model.layers.47.mlp.experts.422.gate_proj",
|
| 1599 |
+
"model.layers.47.mlp.experts.422.up_proj",
|
| 1600 |
+
"model.layers.47.mlp.experts.422.down_proj",
|
| 1601 |
+
"model.layers.47.mlp.experts.423.gate_proj",
|
| 1602 |
+
"model.layers.47.mlp.experts.423.up_proj",
|
| 1603 |
+
"model.layers.47.mlp.experts.423.down_proj",
|
| 1604 |
+
"model.layers.47.mlp.experts.424.gate_proj",
|
| 1605 |
+
"model.layers.47.mlp.experts.424.up_proj",
|
| 1606 |
+
"model.layers.47.mlp.experts.424.down_proj",
|
| 1607 |
+
"model.layers.47.mlp.experts.425.gate_proj",
|
| 1608 |
+
"model.layers.47.mlp.experts.425.up_proj",
|
| 1609 |
+
"model.layers.47.mlp.experts.425.down_proj",
|
| 1610 |
+
"model.layers.47.mlp.experts.426.gate_proj",
|
| 1611 |
+
"model.layers.47.mlp.experts.426.up_proj",
|
| 1612 |
+
"model.layers.47.mlp.experts.426.down_proj",
|
| 1613 |
+
"model.layers.47.mlp.experts.427.gate_proj",
|
| 1614 |
+
"model.layers.47.mlp.experts.427.up_proj",
|
| 1615 |
+
"model.layers.47.mlp.experts.427.down_proj",
|
| 1616 |
+
"model.layers.47.mlp.experts.428.gate_proj",
|
| 1617 |
+
"model.layers.47.mlp.experts.428.up_proj",
|
| 1618 |
+
"model.layers.47.mlp.experts.428.down_proj",
|
| 1619 |
+
"model.layers.47.mlp.experts.429.gate_proj",
|
| 1620 |
+
"model.layers.47.mlp.experts.429.up_proj",
|
| 1621 |
+
"model.layers.47.mlp.experts.429.down_proj",
|
| 1622 |
+
"model.layers.47.mlp.experts.430.gate_proj",
|
| 1623 |
+
"model.layers.47.mlp.experts.430.up_proj",
|
| 1624 |
+
"model.layers.47.mlp.experts.430.down_proj",
|
| 1625 |
+
"model.layers.47.mlp.experts.431.gate_proj",
|
| 1626 |
+
"model.layers.47.mlp.experts.431.up_proj",
|
| 1627 |
+
"model.layers.47.mlp.experts.431.down_proj",
|
| 1628 |
+
"model.layers.47.mlp.experts.432.gate_proj",
|
| 1629 |
+
"model.layers.47.mlp.experts.432.up_proj",
|
| 1630 |
+
"model.layers.47.mlp.experts.432.down_proj",
|
| 1631 |
+
"model.layers.47.mlp.experts.433.gate_proj",
|
| 1632 |
+
"model.layers.47.mlp.experts.433.up_proj",
|
| 1633 |
+
"model.layers.47.mlp.experts.433.down_proj",
|
| 1634 |
+
"model.layers.47.mlp.experts.434.gate_proj",
|
| 1635 |
+
"model.layers.47.mlp.experts.434.up_proj",
|
| 1636 |
+
"model.layers.47.mlp.experts.434.down_proj",
|
| 1637 |
+
"model.layers.47.mlp.experts.435.gate_proj",
|
| 1638 |
+
"model.layers.47.mlp.experts.435.up_proj",
|
| 1639 |
+
"model.layers.47.mlp.experts.435.down_proj",
|
| 1640 |
+
"model.layers.47.mlp.experts.436.gate_proj",
|
| 1641 |
+
"model.layers.47.mlp.experts.436.up_proj",
|
| 1642 |
+
"model.layers.47.mlp.experts.436.down_proj",
|
| 1643 |
+
"model.layers.47.mlp.experts.437.gate_proj",
|
| 1644 |
+
"model.layers.47.mlp.experts.437.up_proj",
|
| 1645 |
+
"model.layers.47.mlp.experts.437.down_proj",
|
| 1646 |
+
"model.layers.47.mlp.experts.438.gate_proj",
|
| 1647 |
+
"model.layers.47.mlp.experts.438.up_proj",
|
| 1648 |
+
"model.layers.47.mlp.experts.438.down_proj",
|
| 1649 |
+
"model.layers.47.mlp.experts.439.gate_proj",
|
| 1650 |
+
"model.layers.47.mlp.experts.439.up_proj",
|
| 1651 |
+
"model.layers.47.mlp.experts.439.down_proj",
|
| 1652 |
+
"model.layers.47.mlp.experts.440.gate_proj",
|
| 1653 |
+
"model.layers.47.mlp.experts.440.up_proj",
|
| 1654 |
+
"model.layers.47.mlp.experts.440.down_proj",
|
| 1655 |
+
"model.layers.47.mlp.experts.441.gate_proj",
|
| 1656 |
+
"model.layers.47.mlp.experts.441.up_proj",
|
| 1657 |
+
"model.layers.47.mlp.experts.441.down_proj",
|
| 1658 |
+
"model.layers.47.mlp.experts.442.gate_proj",
|
| 1659 |
+
"model.layers.47.mlp.experts.442.up_proj",
|
| 1660 |
+
"model.layers.47.mlp.experts.442.down_proj",
|
| 1661 |
+
"model.layers.47.mlp.experts.443.gate_proj",
|
| 1662 |
+
"model.layers.47.mlp.experts.443.up_proj",
|
| 1663 |
+
"model.layers.47.mlp.experts.443.down_proj",
|
| 1664 |
+
"model.layers.47.mlp.experts.444.gate_proj",
|
| 1665 |
+
"model.layers.47.mlp.experts.444.up_proj",
|
| 1666 |
+
"model.layers.47.mlp.experts.444.down_proj",
|
| 1667 |
+
"model.layers.47.mlp.experts.445.gate_proj",
|
| 1668 |
+
"model.layers.47.mlp.experts.445.up_proj",
|
| 1669 |
+
"model.layers.47.mlp.experts.445.down_proj",
|
| 1670 |
+
"model.layers.47.mlp.experts.446.gate_proj",
|
| 1671 |
+
"model.layers.47.mlp.experts.446.up_proj",
|
| 1672 |
+
"model.layers.47.mlp.experts.446.down_proj",
|
| 1673 |
+
"model.layers.47.mlp.experts.447.gate_proj",
|
| 1674 |
+
"model.layers.47.mlp.experts.447.up_proj",
|
| 1675 |
+
"model.layers.47.mlp.experts.447.down_proj",
|
| 1676 |
+
"model.layers.47.mlp.experts.448.gate_proj",
|
| 1677 |
+
"model.layers.47.mlp.experts.448.up_proj",
|
| 1678 |
+
"model.layers.47.mlp.experts.448.down_proj",
|
| 1679 |
+
"model.layers.47.mlp.experts.449.gate_proj",
|
| 1680 |
+
"model.layers.47.mlp.experts.449.up_proj",
|
| 1681 |
+
"model.layers.47.mlp.experts.449.down_proj",
|
| 1682 |
+
"model.layers.47.mlp.experts.450.gate_proj",
|
| 1683 |
+
"model.layers.47.mlp.experts.450.up_proj",
|
| 1684 |
+
"model.layers.47.mlp.experts.450.down_proj",
|
| 1685 |
+
"model.layers.47.mlp.experts.451.gate_proj",
|
| 1686 |
+
"model.layers.47.mlp.experts.451.up_proj",
|
| 1687 |
+
"model.layers.47.mlp.experts.451.down_proj",
|
| 1688 |
+
"model.layers.47.mlp.experts.452.gate_proj",
|
| 1689 |
+
"model.layers.47.mlp.experts.452.up_proj",
|
| 1690 |
+
"model.layers.47.mlp.experts.452.down_proj",
|
| 1691 |
+
"model.layers.47.mlp.experts.453.gate_proj",
|
| 1692 |
+
"model.layers.47.mlp.experts.453.up_proj",
|
| 1693 |
+
"model.layers.47.mlp.experts.453.down_proj",
|
| 1694 |
+
"model.layers.47.mlp.experts.454.gate_proj",
|
| 1695 |
+
"model.layers.47.mlp.experts.454.up_proj",
|
| 1696 |
+
"model.layers.47.mlp.experts.454.down_proj",
|
| 1697 |
+
"model.layers.47.mlp.experts.455.gate_proj",
|
| 1698 |
+
"model.layers.47.mlp.experts.455.up_proj",
|
| 1699 |
+
"model.layers.47.mlp.experts.455.down_proj",
|
| 1700 |
+
"model.layers.47.mlp.experts.456.gate_proj",
|
| 1701 |
+
"model.layers.47.mlp.experts.456.up_proj",
|
| 1702 |
+
"model.layers.47.mlp.experts.456.down_proj",
|
| 1703 |
+
"model.layers.47.mlp.experts.457.gate_proj",
|
| 1704 |
+
"model.layers.47.mlp.experts.457.up_proj",
|
| 1705 |
+
"model.layers.47.mlp.experts.457.down_proj",
|
| 1706 |
+
"model.layers.47.mlp.experts.458.gate_proj",
|
| 1707 |
+
"model.layers.47.mlp.experts.458.up_proj",
|
| 1708 |
+
"model.layers.47.mlp.experts.458.down_proj",
|
| 1709 |
+
"model.layers.47.mlp.experts.459.gate_proj",
|
| 1710 |
+
"model.layers.47.mlp.experts.459.up_proj",
|
| 1711 |
+
"model.layers.47.mlp.experts.459.down_proj",
|
| 1712 |
+
"model.layers.47.mlp.experts.460.gate_proj",
|
| 1713 |
+
"model.layers.47.mlp.experts.460.up_proj",
|
| 1714 |
+
"model.layers.47.mlp.experts.460.down_proj",
|
| 1715 |
+
"model.layers.47.mlp.experts.461.gate_proj",
|
| 1716 |
+
"model.layers.47.mlp.experts.461.up_proj",
|
| 1717 |
+
"model.layers.47.mlp.experts.461.down_proj",
|
| 1718 |
+
"model.layers.47.mlp.experts.462.gate_proj",
|
| 1719 |
+
"model.layers.47.mlp.experts.462.up_proj",
|
| 1720 |
+
"model.layers.47.mlp.experts.462.down_proj",
|
| 1721 |
+
"model.layers.47.mlp.experts.463.gate_proj",
|
| 1722 |
+
"model.layers.47.mlp.experts.463.up_proj",
|
| 1723 |
+
"model.layers.47.mlp.experts.463.down_proj",
|
| 1724 |
+
"model.layers.47.mlp.experts.464.gate_proj",
|
| 1725 |
+
"model.layers.47.mlp.experts.464.up_proj",
|
| 1726 |
+
"model.layers.47.mlp.experts.464.down_proj",
|
| 1727 |
+
"model.layers.47.mlp.experts.465.gate_proj",
|
| 1728 |
+
"model.layers.47.mlp.experts.465.up_proj",
|
| 1729 |
+
"model.layers.47.mlp.experts.465.down_proj",
|
| 1730 |
+
"model.layers.47.mlp.experts.466.gate_proj",
|
| 1731 |
+
"model.layers.47.mlp.experts.466.up_proj",
|
| 1732 |
+
"model.layers.47.mlp.experts.466.down_proj",
|
| 1733 |
+
"model.layers.47.mlp.experts.467.gate_proj",
|
| 1734 |
+
"model.layers.47.mlp.experts.467.up_proj",
|
| 1735 |
+
"model.layers.47.mlp.experts.467.down_proj",
|
| 1736 |
+
"model.layers.47.mlp.experts.468.gate_proj",
|
| 1737 |
+
"model.layers.47.mlp.experts.468.up_proj",
|
| 1738 |
+
"model.layers.47.mlp.experts.468.down_proj",
|
| 1739 |
+
"model.layers.47.mlp.experts.469.gate_proj",
|
| 1740 |
+
"model.layers.47.mlp.experts.469.up_proj",
|
| 1741 |
+
"model.layers.47.mlp.experts.469.down_proj",
|
| 1742 |
+
"model.layers.47.mlp.experts.470.gate_proj",
|
| 1743 |
+
"model.layers.47.mlp.experts.470.up_proj",
|
| 1744 |
+
"model.layers.47.mlp.experts.470.down_proj",
|
| 1745 |
+
"model.layers.47.mlp.experts.471.gate_proj",
|
| 1746 |
+
"model.layers.47.mlp.experts.471.up_proj",
|
| 1747 |
+
"model.layers.47.mlp.experts.471.down_proj",
|
| 1748 |
+
"model.layers.47.mlp.experts.472.gate_proj",
|
| 1749 |
+
"model.layers.47.mlp.experts.472.up_proj",
|
| 1750 |
+
"model.layers.47.mlp.experts.472.down_proj",
|
| 1751 |
+
"model.layers.47.mlp.experts.473.gate_proj",
|
| 1752 |
+
"model.layers.47.mlp.experts.473.up_proj",
|
| 1753 |
+
"model.layers.47.mlp.experts.473.down_proj",
|
| 1754 |
+
"model.layers.47.mlp.experts.474.gate_proj",
|
| 1755 |
+
"model.layers.47.mlp.experts.474.up_proj",
|
| 1756 |
+
"model.layers.47.mlp.experts.474.down_proj",
|
| 1757 |
+
"model.layers.47.mlp.experts.475.gate_proj",
|
| 1758 |
+
"model.layers.47.mlp.experts.475.up_proj",
|
| 1759 |
+
"model.layers.47.mlp.experts.475.down_proj",
|
| 1760 |
+
"model.layers.47.mlp.experts.476.gate_proj",
|
| 1761 |
+
"model.layers.47.mlp.experts.476.up_proj",
|
| 1762 |
+
"model.layers.47.mlp.experts.476.down_proj",
|
| 1763 |
+
"model.layers.47.mlp.experts.477.gate_proj",
|
| 1764 |
+
"model.layers.47.mlp.experts.477.up_proj",
|
| 1765 |
+
"model.layers.47.mlp.experts.477.down_proj",
|
| 1766 |
+
"model.layers.47.mlp.experts.478.gate_proj",
|
| 1767 |
+
"model.layers.47.mlp.experts.478.up_proj",
|
| 1768 |
+
"model.layers.47.mlp.experts.478.down_proj",
|
| 1769 |
+
"model.layers.47.mlp.experts.479.gate_proj",
|
| 1770 |
+
"model.layers.47.mlp.experts.479.up_proj",
|
| 1771 |
+
"model.layers.47.mlp.experts.479.down_proj",
|
| 1772 |
+
"model.layers.47.mlp.experts.480.gate_proj",
|
| 1773 |
+
"model.layers.47.mlp.experts.480.up_proj",
|
| 1774 |
+
"model.layers.47.mlp.experts.480.down_proj",
|
| 1775 |
+
"model.layers.47.mlp.experts.481.gate_proj",
|
| 1776 |
+
"model.layers.47.mlp.experts.481.up_proj",
|
| 1777 |
+
"model.layers.47.mlp.experts.481.down_proj",
|
| 1778 |
+
"model.layers.47.mlp.experts.482.gate_proj",
|
| 1779 |
+
"model.layers.47.mlp.experts.482.up_proj",
|
| 1780 |
+
"model.layers.47.mlp.experts.482.down_proj",
|
| 1781 |
+
"model.layers.47.mlp.experts.483.gate_proj",
|
| 1782 |
+
"model.layers.47.mlp.experts.483.up_proj",
|
| 1783 |
+
"model.layers.47.mlp.experts.483.down_proj",
|
| 1784 |
+
"model.layers.47.mlp.experts.484.gate_proj",
|
| 1785 |
+
"model.layers.47.mlp.experts.484.up_proj",
|
| 1786 |
+
"model.layers.47.mlp.experts.484.down_proj",
|
| 1787 |
+
"model.layers.47.mlp.experts.485.gate_proj",
|
| 1788 |
+
"model.layers.47.mlp.experts.485.up_proj",
|
| 1789 |
+
"model.layers.47.mlp.experts.485.down_proj",
|
| 1790 |
+
"model.layers.47.mlp.experts.486.gate_proj",
|
| 1791 |
+
"model.layers.47.mlp.experts.486.up_proj",
|
| 1792 |
+
"model.layers.47.mlp.experts.486.down_proj",
|
| 1793 |
+
"model.layers.47.mlp.experts.487.gate_proj",
|
| 1794 |
+
"model.layers.47.mlp.experts.487.up_proj",
|
| 1795 |
+
"model.layers.47.mlp.experts.487.down_proj",
|
| 1796 |
+
"model.layers.47.mlp.experts.488.gate_proj",
|
| 1797 |
+
"model.layers.47.mlp.experts.488.up_proj",
|
| 1798 |
+
"model.layers.47.mlp.experts.488.down_proj",
|
| 1799 |
+
"model.layers.47.mlp.experts.489.gate_proj",
|
| 1800 |
+
"model.layers.47.mlp.experts.489.up_proj",
|
| 1801 |
+
"model.layers.47.mlp.experts.489.down_proj",
|
| 1802 |
+
"model.layers.47.mlp.experts.490.gate_proj",
|
| 1803 |
+
"model.layers.47.mlp.experts.490.up_proj",
|
| 1804 |
+
"model.layers.47.mlp.experts.490.down_proj",
|
| 1805 |
+
"model.layers.47.mlp.experts.491.gate_proj",
|
| 1806 |
+
"model.layers.47.mlp.experts.491.up_proj",
|
| 1807 |
+
"model.layers.47.mlp.experts.491.down_proj",
|
| 1808 |
+
"model.layers.47.mlp.experts.492.gate_proj",
|
| 1809 |
+
"model.layers.47.mlp.experts.492.up_proj",
|
| 1810 |
+
"model.layers.47.mlp.experts.492.down_proj",
|
| 1811 |
+
"model.layers.47.mlp.experts.493.gate_proj",
|
| 1812 |
+
"model.layers.47.mlp.experts.493.up_proj",
|
| 1813 |
+
"model.layers.47.mlp.experts.493.down_proj",
|
| 1814 |
+
"model.layers.47.mlp.experts.494.gate_proj",
|
| 1815 |
+
"model.layers.47.mlp.experts.494.up_proj",
|
| 1816 |
+
"model.layers.47.mlp.experts.494.down_proj",
|
| 1817 |
+
"model.layers.47.mlp.experts.495.gate_proj",
|
| 1818 |
+
"model.layers.47.mlp.experts.495.up_proj",
|
| 1819 |
+
"model.layers.47.mlp.experts.495.down_proj",
|
| 1820 |
+
"model.layers.47.mlp.experts.496.gate_proj",
|
| 1821 |
+
"model.layers.47.mlp.experts.496.up_proj",
|
| 1822 |
+
"model.layers.47.mlp.experts.496.down_proj",
|
| 1823 |
+
"model.layers.47.mlp.experts.497.gate_proj",
|
| 1824 |
+
"model.layers.47.mlp.experts.497.up_proj",
|
| 1825 |
+
"model.layers.47.mlp.experts.497.down_proj",
|
| 1826 |
+
"model.layers.47.mlp.experts.498.gate_proj",
|
| 1827 |
+
"model.layers.47.mlp.experts.498.up_proj",
|
| 1828 |
+
"model.layers.47.mlp.experts.498.down_proj",
|
| 1829 |
+
"model.layers.47.mlp.experts.499.gate_proj",
|
| 1830 |
+
"model.layers.47.mlp.experts.499.up_proj",
|
| 1831 |
+
"model.layers.47.mlp.experts.499.down_proj",
|
| 1832 |
+
"model.layers.47.mlp.experts.500.gate_proj",
|
| 1833 |
+
"model.layers.47.mlp.experts.500.up_proj",
|
| 1834 |
+
"model.layers.47.mlp.experts.500.down_proj",
|
| 1835 |
+
"model.layers.47.mlp.experts.501.gate_proj",
|
| 1836 |
+
"model.layers.47.mlp.experts.501.up_proj",
|
| 1837 |
+
"model.layers.47.mlp.experts.501.down_proj",
|
| 1838 |
+
"model.layers.47.mlp.experts.502.gate_proj",
|
| 1839 |
+
"model.layers.47.mlp.experts.502.up_proj",
|
| 1840 |
+
"model.layers.47.mlp.experts.502.down_proj",
|
| 1841 |
+
"model.layers.47.mlp.experts.503.gate_proj",
|
| 1842 |
+
"model.layers.47.mlp.experts.503.up_proj",
|
| 1843 |
+
"model.layers.47.mlp.experts.503.down_proj",
|
| 1844 |
+
"model.layers.47.mlp.experts.504.gate_proj",
|
| 1845 |
+
"model.layers.47.mlp.experts.504.up_proj",
|
| 1846 |
+
"model.layers.47.mlp.experts.504.down_proj",
|
| 1847 |
+
"model.layers.47.mlp.experts.505.gate_proj",
|
| 1848 |
+
"model.layers.47.mlp.experts.505.up_proj",
|
| 1849 |
+
"model.layers.47.mlp.experts.505.down_proj",
|
| 1850 |
+
"model.layers.47.mlp.experts.506.gate_proj",
|
| 1851 |
+
"model.layers.47.mlp.experts.506.up_proj",
|
| 1852 |
+
"model.layers.47.mlp.experts.506.down_proj",
|
| 1853 |
+
"model.layers.47.mlp.experts.507.gate_proj",
|
| 1854 |
+
"model.layers.47.mlp.experts.507.up_proj",
|
| 1855 |
+
"model.layers.47.mlp.experts.507.down_proj",
|
| 1856 |
+
"model.layers.47.mlp.experts.508.gate_proj",
|
| 1857 |
+
"model.layers.47.mlp.experts.508.up_proj",
|
| 1858 |
+
"model.layers.47.mlp.experts.508.down_proj",
|
| 1859 |
+
"model.layers.47.mlp.experts.509.gate_proj",
|
| 1860 |
+
"model.layers.47.mlp.experts.509.up_proj",
|
| 1861 |
+
"model.layers.47.mlp.experts.509.down_proj",
|
| 1862 |
+
"model.layers.47.mlp.experts.510.gate_proj",
|
| 1863 |
+
"model.layers.47.mlp.experts.510.up_proj",
|
| 1864 |
+
"model.layers.47.mlp.experts.510.down_proj",
|
| 1865 |
+
"model.layers.47.mlp.experts.511.gate_proj",
|
| 1866 |
+
"model.layers.47.mlp.experts.511.up_proj",
|
| 1867 |
+
"model.layers.47.mlp.experts.511.down_proj",
|
| 1868 |
+
"model.layers.47.mlp.shared_expert.gate_proj",
|
| 1869 |
+
"model.layers.47.mlp.shared_expert.up_proj",
|
| 1870 |
+
"model.layers.47.mlp.shared_expert.down_proj",
|
| 1871 |
+
"model.layers.47.mlp.shared_expert_gate",
|
| 1872 |
+
"lm_head"
|
| 1873 |
+
],
|
| 1874 |
+
"kv_cache_scheme": null,
|
| 1875 |
+
"quant_method": "compressed-tensors",
|
| 1876 |
+
"quantization_status": "compressed",
|
| 1877 |
+
"sparsity_config": {},
|
| 1878 |
+
"transform_config": {},
|
| 1879 |
+
"version": "0.13.1.dev26+g46dd0c7"
|
| 1880 |
+
},
|
| 1881 |
+
"rms_norm_eps": 1e-06,
|
| 1882 |
+
"rope_scaling": null,
|
| 1883 |
+
"rope_theta": 5000000,
|
| 1884 |
+
"router_aux_loss_coef": 0.001,
|
| 1885 |
+
"shared_expert_intermediate_size": 512,
|
| 1886 |
+
"tie_word_embeddings": false,
|
| 1887 |
+
"transformers_version": "4.57.6",
|
| 1888 |
+
"unsloth_fixed": true,
|
| 1889 |
+
"use_cache": true,
|
| 1890 |
+
"use_sliding_window": false,
|
| 1891 |
+
"vocab_size": 151936
|
| 1892 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"top_k": 40,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.6"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a121fc32fbe88c932dda9130dbb334272e34ad6ec58cf35d34c04bd8dd5ead87
|
| 3 |
+
size 5000835824
|
model-00002-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed33183e3d78782381c531fdd853f5953c9b8682e08d77e2454b0f92c3e95793
|
| 3 |
+
size 5000409768
|
model-00003-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaeef1ff2d0ae996f212d57679f307834a06bf70ef9eff9288a353b86b5594db
|
| 3 |
+
size 5000412776
|
model-00004-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:350d765553430224a58c548869b0ce55e186ec6089d0046178b90c8cbdd0be9c
|
| 3 |
+
size 5000418240
|
model-00005-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb993418e06b66ecb1d525d538922337b834b688263f8ed2a34eaa80be476e67
|
| 3 |
+
size 5000640688
|
model-00006-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95afad8a9c7be0f77ebdaa1b9a6a6095366362267bafe72b94488b0790dc8763
|
| 3 |
+
size 5000418544
|
model-00007-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b7e8fc40f1eabfc486be35e01f5b0265ba771e8b8852c8b618ba0687f8f747c
|
| 3 |
+
size 5000421552
|
model-00008-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06a7cf4a7f85396e31872f7f34467b5ce0ccb9bc843325897bd93cb427c1cc84
|
| 3 |
+
size 5000421496
|
model-00009-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:497f4c5377b07551db8dec1affa6dcaf45863ab8bd786a92d05dc93958beff2b
|
| 3 |
+
size 5000640232
|
model-00010-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69dd65622346a3ca696af9421cf1f7698ea98ae785a3aee4850d368c9577c76
|
| 3 |
+
size 5000418088
|
model-00011-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c237cc196a3636b2b1609c21fe749e7b70799304803948f3a34318d2f41c1cb0
|
| 3 |
+
size 5000421096
|
model-00012-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5598423e16e5139c53b4c3b8d6020d72e197788cd827ea5334f4faf0205b953
|
| 3 |
+
size 5000421040
|
model-00013-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee44b4066282c7be68c2b27af79af91c454909397a5a6c8bcb45cf56a9d9abba
|
| 3 |
+
size 5000639776
|
model-00014-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c34e4881fac7e869f0587330cadcdcd4d567d4f0f0153d4e039e07eecb8d0e
|
| 3 |
+
size 5000417632
|
model-00015-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07175cee89a26dba73476b71375f07750fd6ad0ba95a604b59ee47ed41f87269
|
| 3 |
+
size 5000420640
|
model-00016-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc60e33ac1d6deb0efdb7e1795c0fce11cd08db956fd06e389ca782e9fdae381
|
| 3 |
+
size 5000347584
|
model-00017-of-00017.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5824a2a14357a60f0071f82d9085440f2d38a9fa960653489add6e8d8443ddc
|
| 3 |
+
size 3361390584
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74ef913cd3437a2b1ded9abec5165fd0f9f528295c40211f680b93044b168065
|
| 3 |
+
size 13773357
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|vision_pad|>",
|
| 236 |
+
"padding_side": "left",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|