Upload folder using huggingface_hub
Browse files- .msc +0 -0
- .mv +1 -1
- README.md +20 -339
- config.json +6 -4
- model-00001-of-00005.safetensors +2 -2
- model-00002-of-00005.safetensors +2 -2
- model-00003-of-00005.safetensors +2 -2
- model-00004-of-00005.safetensors +2 -2
- model-00005-of-00005.safetensors +2 -2
- model.safetensors.index.json +397 -253
- quantize_config.json +6 -4
.msc
CHANGED
|
Binary files a/.msc and b/.msc differ
|
|
|
.mv
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
Revision:master,CreatedAt:
|
|
|
|
| 1 |
+
Revision:master,CreatedAt:1746673573
|
README.md
CHANGED
|
@@ -1,354 +1,35 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: transformers
|
| 3 |
license: apache-2.0
|
| 4 |
-
license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE
|
| 5 |
-
pipeline_tag: text-generation
|
| 6 |
-
base_model:
|
| 7 |
-
- Qwen/Qwen3-4B-Base
|
| 8 |
-
---
|
| 9 |
|
| 10 |
-
# Qwen3-
|
| 11 |
-
|
| 12 |
-
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
| 13 |
-
</a>
|
| 14 |
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
|
| 20 |
-
- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
|
| 21 |
-
- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
|
| 22 |
-
- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
|
| 23 |
-
- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
|
| 24 |
-
|
| 25 |
-
## Model Overview
|
| 26 |
-
|
| 27 |
-
**Qwen3-4B** has the following features:
|
| 28 |
-
- Type: Causal Language Models
|
| 29 |
-
- Training Stage: Pretraining & Post-training
|
| 30 |
-
- Number of Parameters: 4.0B
|
| 31 |
-
- Number of Paramaters (Non-Embedding): 3.6B
|
| 32 |
-
- Number of Layers: 36
|
| 33 |
-
- Number of Attention Heads (GQA): 32 for Q and 8 for KV
|
| 34 |
-
- Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts).
|
| 35 |
-
|
| 36 |
-
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
| 37 |
-
|
| 38 |
-
> [!TIP]
|
| 39 |
-
> If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5.
|
| 40 |
-
|
| 41 |
-
## Quickstart
|
| 42 |
-
|
| 43 |
-
The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
|
| 44 |
-
|
| 45 |
-
With `transformers<4.51.0`, you will encounter the following error:
|
| 46 |
-
```
|
| 47 |
-
KeyError: 'qwen3'
|
| 48 |
```
|
| 49 |
|
| 50 |
-
|
| 51 |
-
```python
|
| 52 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 53 |
-
|
| 54 |
-
model_name = "Qwen/Qwen3-4B"
|
| 55 |
-
|
| 56 |
-
# load the tokenizer and the model
|
| 57 |
-
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 58 |
-
model = AutoModelForCausalLM.from_pretrained(
|
| 59 |
-
model_name,
|
| 60 |
-
torch_dtype="auto",
|
| 61 |
-
device_map="auto"
|
| 62 |
-
)
|
| 63 |
-
|
| 64 |
-
# prepare the model input
|
| 65 |
-
prompt = "Give me a short introduction to large language model."
|
| 66 |
-
messages = [
|
| 67 |
-
{"role": "user", "content": prompt}
|
| 68 |
-
]
|
| 69 |
-
text = tokenizer.apply_chat_template(
|
| 70 |
-
messages,
|
| 71 |
-
tokenize=False,
|
| 72 |
-
add_generation_prompt=True,
|
| 73 |
-
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
|
| 74 |
-
)
|
| 75 |
-
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
| 76 |
-
|
| 77 |
-
# conduct text completion
|
| 78 |
-
generated_ids = model.generate(
|
| 79 |
-
**model_inputs,
|
| 80 |
-
max_new_tokens=32768
|
| 81 |
-
)
|
| 82 |
-
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
|
| 83 |
|
| 84 |
-
# parsing thinking content
|
| 85 |
-
try:
|
| 86 |
-
# rindex finding 151668 (</think>)
|
| 87 |
-
index = len(output_ids) - output_ids[::-1].index(151668)
|
| 88 |
-
except ValueError:
|
| 89 |
-
index = 0
|
| 90 |
-
|
| 91 |
-
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
|
| 92 |
-
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
|
| 93 |
-
|
| 94 |
-
print("thinking content:", thinking_content)
|
| 95 |
-
print("content:", content)
|
| 96 |
```
|
| 97 |
-
|
| 98 |
-
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
|
| 99 |
-
- SGLang:
|
| 100 |
-
```shell
|
| 101 |
-
python -m sglang.launch_server --model-path Qwen/Qwen3-4B --reasoning-parser qwen3
|
| 102 |
-
```
|
| 103 |
-
- vLLM:
|
| 104 |
-
```shell
|
| 105 |
-
vllm serve Qwen/Qwen3-4B --enable-reasoning --reasoning-parser deepseek_r1
|
| 106 |
-
```
|
| 107 |
-
|
| 108 |
-
For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3.
|
| 109 |
-
|
| 110 |
-
## Switching Between Thinking and Non-Thinking Mode
|
| 111 |
-
|
| 112 |
-
> [!TIP]
|
| 113 |
-
> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM.
|
| 114 |
-
> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users.
|
| 115 |
-
|
| 116 |
-
### `enable_thinking=True`
|
| 117 |
-
|
| 118 |
-
By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
|
| 119 |
-
|
| 120 |
-
```python
|
| 121 |
-
text = tokenizer.apply_chat_template(
|
| 122 |
-
messages,
|
| 123 |
-
tokenize=False,
|
| 124 |
-
add_generation_prompt=True,
|
| 125 |
-
enable_thinking=True # True is the default value for enable_thinking
|
| 126 |
-
)
|
| 127 |
```
|
| 128 |
|
| 129 |
-
In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
|
| 130 |
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
### `enable_thinking=False`
|
| 136 |
-
|
| 137 |
-
We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
|
| 138 |
-
|
| 139 |
-
```python
|
| 140 |
-
text = tokenizer.apply_chat_template(
|
| 141 |
-
messages,
|
| 142 |
-
tokenize=False,
|
| 143 |
-
add_generation_prompt=True,
|
| 144 |
-
enable_thinking=False # Setting enable_thinking=False disables thinking mode
|
| 145 |
-
)
|
| 146 |
```
|
| 147 |
-
|
| 148 |
-
In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
|
| 149 |
-
|
| 150 |
-
> [!NOTE]
|
| 151 |
-
> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
|
| 152 |
-
|
| 153 |
-
### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
|
| 154 |
-
|
| 155 |
-
We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
|
| 156 |
-
|
| 157 |
-
Here is an example of a multi-turn conversation:
|
| 158 |
-
|
| 159 |
```python
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
def __init__(self, model_name="Qwen/Qwen3-4B"):
|
| 164 |
-
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 165 |
-
self.model = AutoModelForCausalLM.from_pretrained(model_name)
|
| 166 |
-
self.history = []
|
| 167 |
-
|
| 168 |
-
def generate_response(self, user_input):
|
| 169 |
-
messages = self.history + [{"role": "user", "content": user_input}]
|
| 170 |
-
|
| 171 |
-
text = self.tokenizer.apply_chat_template(
|
| 172 |
-
messages,
|
| 173 |
-
tokenize=False,
|
| 174 |
-
add_generation_prompt=True
|
| 175 |
-
)
|
| 176 |
-
|
| 177 |
-
inputs = self.tokenizer(text, return_tensors="pt")
|
| 178 |
-
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
|
| 179 |
-
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
|
| 180 |
-
|
| 181 |
-
# Update history
|
| 182 |
-
self.history.append({"role": "user", "content": user_input})
|
| 183 |
-
self.history.append({"role": "assistant", "content": response})
|
| 184 |
-
|
| 185 |
-
return response
|
| 186 |
-
|
| 187 |
-
# Example Usage
|
| 188 |
-
if __name__ == "__main__":
|
| 189 |
-
chatbot = QwenChatbot()
|
| 190 |
-
|
| 191 |
-
# First input (without /think or /no_think tags, thinking mode is enabled by default)
|
| 192 |
-
user_input_1 = "How many r's in strawberries?"
|
| 193 |
-
print(f"User: {user_input_1}")
|
| 194 |
-
response_1 = chatbot.generate_response(user_input_1)
|
| 195 |
-
print(f"Bot: {response_1}")
|
| 196 |
-
print("----------------------")
|
| 197 |
-
|
| 198 |
-
# Second input with /no_think
|
| 199 |
-
user_input_2 = "Then, how many r's in blueberries? /no_think"
|
| 200 |
-
print(f"User: {user_input_2}")
|
| 201 |
-
response_2 = chatbot.generate_response(user_input_2)
|
| 202 |
-
print(f"Bot: {response_2}")
|
| 203 |
-
print("----------------------")
|
| 204 |
-
|
| 205 |
-
# Third input with /think
|
| 206 |
-
user_input_3 = "Really? /think"
|
| 207 |
-
print(f"User: {user_input_3}")
|
| 208 |
-
response_3 = chatbot.generate_response(user_input_3)
|
| 209 |
-
print(f"Bot: {response_3}")
|
| 210 |
```
|
| 211 |
-
|
| 212 |
-
> [!NOTE]
|
| 213 |
-
> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
|
| 214 |
-
> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
|
| 215 |
-
|
| 216 |
-
## Agentic Use
|
| 217 |
-
|
| 218 |
-
Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
|
| 219 |
-
|
| 220 |
-
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
|
| 221 |
-
```python
|
| 222 |
-
from qwen_agent.agents import Assistant
|
| 223 |
-
|
| 224 |
-
# Define LLM
|
| 225 |
-
llm_cfg = {
|
| 226 |
-
'model': 'Qwen3-4B',
|
| 227 |
-
|
| 228 |
-
# Use the endpoint provided by Alibaba Model Studio:
|
| 229 |
-
# 'model_type': 'qwen_dashscope',
|
| 230 |
-
# 'api_key': os.getenv('DASHSCOPE_API_KEY'),
|
| 231 |
-
|
| 232 |
-
# Use a custom endpoint compatible with OpenAI API:
|
| 233 |
-
'model_server': 'http://localhost:8000/v1', # api_base
|
| 234 |
-
'api_key': 'EMPTY',
|
| 235 |
-
|
| 236 |
-
# Other parameters:
|
| 237 |
-
# 'generate_cfg': {
|
| 238 |
-
# # Add: When the response content is `<think>this is the thought</think>this is the answer;
|
| 239 |
-
# # Do not add: When the response has been separated by reasoning_content and content.
|
| 240 |
-
# 'thought_in_content': True,
|
| 241 |
-
# },
|
| 242 |
-
}
|
| 243 |
-
|
| 244 |
-
# Define Tools
|
| 245 |
-
tools = [
|
| 246 |
-
{'mcpServers': { # You can specify the MCP configuration file
|
| 247 |
-
'time': {
|
| 248 |
-
'command': 'uvx',
|
| 249 |
-
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
|
| 250 |
-
},
|
| 251 |
-
"fetch": {
|
| 252 |
-
"command": "uvx",
|
| 253 |
-
"args": ["mcp-server-fetch"]
|
| 254 |
-
}
|
| 255 |
-
}
|
| 256 |
-
},
|
| 257 |
-
'code_interpreter', # Built-in tools
|
| 258 |
-
]
|
| 259 |
-
|
| 260 |
-
# Define Agent
|
| 261 |
-
bot = Assistant(llm=llm_cfg, function_list=tools)
|
| 262 |
-
|
| 263 |
-
# Streaming generation
|
| 264 |
-
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
|
| 265 |
-
for responses in bot.run(messages=messages):
|
| 266 |
-
pass
|
| 267 |
-
print(responses)
|
| 268 |
```
|
| 269 |
-
|
| 270 |
-
|
| 271 |
-
|
| 272 |
-
Qwen3 natively supports context lengths of up to 32,768 tokens. For conversations where the total length (including both input and output) significantly exceeds this limit, we recommend using RoPE scaling techniques to handle long texts effectively. We have validated the model's performance on context lengths of up to 131,072 tokens using the [YaRN](https://arxiv.org/abs/2309.00071) method.
|
| 273 |
-
|
| 274 |
-
YaRN is currently supported by several inference frameworks, e.g., `transformers` and `llama.cpp` for local use, `vllm` and `sglang` for deployment. In general, there are two approaches to enabling YaRN for supported frameworks:
|
| 275 |
-
|
| 276 |
-
- Modifying the model files:
|
| 277 |
-
In the `config.json` file, add the `rope_scaling` fields:
|
| 278 |
-
```json
|
| 279 |
-
{
|
| 280 |
-
...,
|
| 281 |
-
"rope_scaling": {
|
| 282 |
-
"rope_type": "yarn",
|
| 283 |
-
"factor": 4.0,
|
| 284 |
-
"original_max_position_embeddings": 32768
|
| 285 |
-
}
|
| 286 |
-
}
|
| 287 |
-
```
|
| 288 |
-
For `llama.cpp`, you need to regenerate the GGUF file after the modification.
|
| 289 |
-
|
| 290 |
-
- Passing command line arguments:
|
| 291 |
-
|
| 292 |
-
For `vllm`, you can use
|
| 293 |
-
```shell
|
| 294 |
-
vllm serve ... --rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' --max-model-len 131072
|
| 295 |
-
```
|
| 296 |
-
|
| 297 |
-
For `sglang`, you can use
|
| 298 |
-
```shell
|
| 299 |
-
python -m sglang.launch_server ... --json-model-override-args '{"rope_scaling":{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}}'
|
| 300 |
-
```
|
| 301 |
-
|
| 302 |
-
For `llama-server` from `llama.cpp`, you can use
|
| 303 |
-
```shell
|
| 304 |
-
llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768
|
| 305 |
-
```
|
| 306 |
-
|
| 307 |
-
> [!IMPORTANT]
|
| 308 |
-
> If you encounter the following warning
|
| 309 |
-
> ```
|
| 310 |
-
> Unrecognized keys in `rope_scaling` for 'rope_type'='yarn': {'original_max_position_embeddings'}
|
| 311 |
-
> ```
|
| 312 |
-
> please upgrade `transformers>=4.51.0`.
|
| 313 |
-
|
| 314 |
-
> [!NOTE]
|
| 315 |
-
> All the notable open-source frameworks implement static YaRN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts.**
|
| 316 |
-
> We advise adding the `rope_scaling` configuration only when processing long contexts is required.
|
| 317 |
-
> It is also recommended to modify the `factor` as needed. For example, if the typical context length for your application is 65,536 tokens, it would be better to set `factor` as 2.0.
|
| 318 |
-
|
| 319 |
-
> [!NOTE]
|
| 320 |
-
> The default `max_position_embeddings` in `config.json` is set to 40,960. This allocation includes reserving 32,768 tokens for outputs and 8,192 tokens for typical prompts, which is sufficient for most scenarios involving short text processing. If the average context length does not exceed 32,768 tokens, we do not recommend enabling YaRN in this scenario, as it may potentially degrade model performance.
|
| 321 |
-
|
| 322 |
-
> [!TIP]
|
| 323 |
-
> The endpoint provided by Alibaba Model Studio supports dynamic YaRN by default and no extra configuration is needed.
|
| 324 |
-
|
| 325 |
-
## Best Practices
|
| 326 |
-
|
| 327 |
-
To achieve optimal performance, we recommend the following settings:
|
| 328 |
-
|
| 329 |
-
1. **Sampling Parameters**:
|
| 330 |
-
- For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
|
| 331 |
-
- For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
|
| 332 |
-
- For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
|
| 333 |
-
|
| 334 |
-
2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
|
| 335 |
-
|
| 336 |
-
3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
|
| 337 |
-
- **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
|
| 338 |
-
- **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
|
| 339 |
-
|
| 340 |
-
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
|
| 341 |
-
|
| 342 |
-
### Citation
|
| 343 |
-
|
| 344 |
-
If you find our work helpful, feel free to give us a cite.
|
| 345 |
-
|
| 346 |
```
|
| 347 |
-
|
| 348 |
-
|
| 349 |
-
url = {https://qwenlm.github.io/blog/qwen3/},
|
| 350 |
-
author = {Qwen Team},
|
| 351 |
-
month = {April},
|
| 352 |
-
year = {2025}
|
| 353 |
-
}
|
| 354 |
-
```
|
|
|
|
|
|
|
|
|
|
| 1 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
+
# 通义千问Qwen3-30B-A3B-GPTQ-Int4量化
|
| 4 |
+
基础模型 [通义千问3-30B-A3B](https://modelscope.cn/models/Qwen/Qwen3-30B-A3B)
|
|
|
|
|
|
|
| 5 |
|
| 6 |
+
### 最近更新
|
| 7 |
+
```
|
| 8 |
+
2025-05-08
|
| 9 |
+
fix (model.layers.*.mlp.gate) are not quantized
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
```
|
| 11 |
|
| 12 |
+
### 依赖
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
```
|
| 15 |
+
vllm==0.8.5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
```
|
| 17 |
|
|
|
|
| 18 |
|
| 19 |
+
SDK下载
|
| 20 |
+
```bash
|
| 21 |
+
#安装ModelScope
|
| 22 |
+
pip install modelscope
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
```python
|
| 25 |
+
#SDK模型下载
|
| 26 |
+
from modelscope import snapshot_download
|
| 27 |
+
model_dir = snapshot_download('JunHowie/Qwen3-30B-A3B-GPTQ-Int4')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
```
|
| 29 |
+
Git下载
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
```
|
| 31 |
+
#Git模型下载
|
| 32 |
+
git clone https://www.modelscope.cn/JunHowie/Qwen3-30B-A3B-GPTQ-Int4.git
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
```
|
| 34 |
+
|
| 35 |
+
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
|
@@ -31,15 +31,17 @@
|
|
| 31 |
"group_size": 128,
|
| 32 |
"lm_head": false,
|
| 33 |
"meta": {
|
| 34 |
-
"damp_auto_increment": 0.
|
| 35 |
-
"damp_percent": 0.
|
| 36 |
"mse": 0.0,
|
| 37 |
"quantizer": [
|
| 38 |
-
"gptqmodel:
|
| 39 |
],
|
| 40 |
"static_groups": false,
|
| 41 |
"true_sequential": true,
|
| 42 |
-
"uri": "https://github.com/modelcloud/gptqmodel"
|
|
|
|
|
|
|
| 43 |
},
|
| 44 |
"pack_dtype": "int32",
|
| 45 |
"quant_method": "gptq",
|
|
|
|
| 31 |
"group_size": 128,
|
| 32 |
"lm_head": false,
|
| 33 |
"meta": {
|
| 34 |
+
"damp_auto_increment": 0.01,
|
| 35 |
+
"damp_percent": 0.05,
|
| 36 |
"mse": 0.0,
|
| 37 |
"quantizer": [
|
| 38 |
+
"gptqmodel:4.0.0-dev"
|
| 39 |
],
|
| 40 |
"static_groups": false,
|
| 41 |
"true_sequential": true,
|
| 42 |
+
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 43 |
+
"v2": false,
|
| 44 |
+
"v2_alpha": 0.25
|
| 45 |
},
|
| 46 |
"pack_dtype": "int32",
|
| 47 |
"quant_method": "gptq",
|
model-00001-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e5be8644a3e4c3ad1f05b48d6caf6c57d09772085dc9142a5560c4d2b7b242
|
| 3 |
+
size 4001615168
|
model-00002-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:621653d6bc683384afa8df31474c531a31012df22f9b33ebcb5cc1335dd9d070
|
| 3 |
+
size 4001632008
|
model-00003-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84eaf9be046f6dd2a8c73b8d806e3cb7c3b0f7f1eac788f9c7922aa8ef31a0bb
|
| 3 |
+
size 4001632136
|
model-00004-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9103e328ced3707a04fd14fdacf59c12d58e512f8a1004310b342787ca52ae55
|
| 3 |
+
size 4001745272
|
model-00005-of-00005.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:504462bea741d0e85d5cfc85989bb2f20eac5671caca96d5fa537d39bbc94de3
|
| 3 |
+
size 908307360
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
|
@@ -1542,7 +1542,10 @@
|
|
| 1542 |
"model.layers.0.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 1543 |
"model.layers.0.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 1544 |
"model.layers.0.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 1545 |
-
"model.layers.0.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 1546 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 1547 |
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 1548 |
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -3099,7 +3102,10 @@
|
|
| 3099 |
"model.layers.1.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3100 |
"model.layers.1.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3101 |
"model.layers.1.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3102 |
-
"model.layers.1.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 3103 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 3104 |
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 3105 |
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -3876,10 +3882,10 @@
|
|
| 3876 |
"model.layers.10.mlp.experts.4.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3877 |
"model.layers.10.mlp.experts.4.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3878 |
"model.layers.10.mlp.experts.4.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3879 |
-
"model.layers.10.mlp.experts.40.down_proj.g_idx": "model-
|
| 3880 |
-
"model.layers.10.mlp.experts.40.down_proj.qweight": "model-
|
| 3881 |
-
"model.layers.10.mlp.experts.40.down_proj.qzeros": "model-
|
| 3882 |
-
"model.layers.10.mlp.experts.40.down_proj.scales": "model-
|
| 3883 |
"model.layers.10.mlp.experts.40.gate_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3884 |
"model.layers.10.mlp.experts.40.gate_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3885 |
"model.layers.10.mlp.experts.40.gate_proj.qzeros": "model-00001-of-00005.safetensors",
|
|
@@ -3888,26 +3894,26 @@
|
|
| 3888 |
"model.layers.10.mlp.experts.40.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3889 |
"model.layers.10.mlp.experts.40.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3890 |
"model.layers.10.mlp.experts.40.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3891 |
-
"model.layers.10.mlp.experts.41.down_proj.g_idx": "model-
|
| 3892 |
-
"model.layers.10.mlp.experts.41.down_proj.qweight": "model-
|
| 3893 |
-
"model.layers.10.mlp.experts.41.down_proj.qzeros": "model-
|
| 3894 |
-
"model.layers.10.mlp.experts.41.down_proj.scales": "model-
|
| 3895 |
-
"model.layers.10.mlp.experts.41.gate_proj.g_idx": "model-
|
| 3896 |
-
"model.layers.10.mlp.experts.41.gate_proj.qweight": "model-
|
| 3897 |
-
"model.layers.10.mlp.experts.41.gate_proj.qzeros": "model-
|
| 3898 |
-
"model.layers.10.mlp.experts.41.gate_proj.scales": "model-
|
| 3899 |
-
"model.layers.10.mlp.experts.41.up_proj.g_idx": "model-
|
| 3900 |
-
"model.layers.10.mlp.experts.41.up_proj.qweight": "model-
|
| 3901 |
-
"model.layers.10.mlp.experts.41.up_proj.qzeros": "model-
|
| 3902 |
-
"model.layers.10.mlp.experts.41.up_proj.scales": "model-
|
| 3903 |
"model.layers.10.mlp.experts.42.down_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 3904 |
"model.layers.10.mlp.experts.42.down_proj.qweight": "model-00002-of-00005.safetensors",
|
| 3905 |
"model.layers.10.mlp.experts.42.down_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 3906 |
"model.layers.10.mlp.experts.42.down_proj.scales": "model-00002-of-00005.safetensors",
|
| 3907 |
-
"model.layers.10.mlp.experts.42.gate_proj.g_idx": "model-
|
| 3908 |
-
"model.layers.10.mlp.experts.42.gate_proj.qweight": "model-
|
| 3909 |
-
"model.layers.10.mlp.experts.42.gate_proj.qzeros": "model-
|
| 3910 |
-
"model.layers.10.mlp.experts.42.gate_proj.scales": "model-
|
| 3911 |
"model.layers.10.mlp.experts.42.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 3912 |
"model.layers.10.mlp.experts.42.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 3913 |
"model.layers.10.mlp.experts.42.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
|
@@ -4656,7 +4662,10 @@
|
|
| 4656 |
"model.layers.10.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 4657 |
"model.layers.10.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 4658 |
"model.layers.10.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 4659 |
-
"model.layers.10.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 4660 |
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 4661 |
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 4662 |
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -6213,7 +6222,10 @@
|
|
| 6213 |
"model.layers.11.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 6214 |
"model.layers.11.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 6215 |
"model.layers.11.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 6216 |
-
"model.layers.11.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 6217 |
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 6218 |
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 6219 |
"model.layers.11.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -7770,7 +7782,10 @@
|
|
| 7770 |
"model.layers.12.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 7771 |
"model.layers.12.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 7772 |
"model.layers.12.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 7773 |
-
"model.layers.12.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 7774 |
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 7775 |
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 7776 |
"model.layers.12.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -9327,7 +9342,10 @@
|
|
| 9327 |
"model.layers.13.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 9328 |
"model.layers.13.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 9329 |
"model.layers.13.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 9330 |
-
"model.layers.13.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 9331 |
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 9332 |
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 9333 |
"model.layers.13.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -10884,7 +10902,10 @@
|
|
| 10884 |
"model.layers.14.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 10885 |
"model.layers.14.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 10886 |
"model.layers.14.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 10887 |
-
"model.layers.14.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 10888 |
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 10889 |
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 10890 |
"model.layers.14.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -12441,7 +12462,10 @@
|
|
| 12441 |
"model.layers.15.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 12442 |
"model.layers.15.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 12443 |
"model.layers.15.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 12444 |
-
"model.layers.15.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 12445 |
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 12446 |
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 12447 |
"model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -13998,7 +14022,10 @@
|
|
| 13998 |
"model.layers.16.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 13999 |
"model.layers.16.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 14000 |
"model.layers.16.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 14001 |
-
"model.layers.16.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 14002 |
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 14003 |
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 14004 |
"model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -15555,7 +15582,10 @@
|
|
| 15555 |
"model.layers.17.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 15556 |
"model.layers.17.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 15557 |
"model.layers.17.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 15558 |
-
"model.layers.17.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 15559 |
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 15560 |
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 15561 |
"model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -17112,7 +17142,10 @@
|
|
| 17112 |
"model.layers.18.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 17113 |
"model.layers.18.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 17114 |
"model.layers.18.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 17115 |
-
"model.layers.18.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 17116 |
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 17117 |
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 17118 |
"model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -18669,7 +18702,10 @@
|
|
| 18669 |
"model.layers.19.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 18670 |
"model.layers.19.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 18671 |
"model.layers.19.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 18672 |
-
"model.layers.19.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 18673 |
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 18674 |
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 18675 |
"model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -20226,7 +20262,10 @@
|
|
| 20226 |
"model.layers.2.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 20227 |
"model.layers.2.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 20228 |
"model.layers.2.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 20229 |
-
"model.layers.2.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 20230 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 20231 |
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 20232 |
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -21783,7 +21822,10 @@
|
|
| 21783 |
"model.layers.20.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 21784 |
"model.layers.20.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 21785 |
"model.layers.20.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 21786 |
-
"model.layers.20.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 21787 |
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 21788 |
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 21789 |
"model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -23340,7 +23382,10 @@
|
|
| 23340 |
"model.layers.21.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 23341 |
"model.layers.21.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 23342 |
"model.layers.21.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 23343 |
-
"model.layers.21.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 23344 |
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 23345 |
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 23346 |
"model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -24549,50 +24594,50 @@
|
|
| 24549 |
"model.layers.22.mlp.experts.72.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24550 |
"model.layers.22.mlp.experts.72.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24551 |
"model.layers.22.mlp.experts.72.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 24552 |
-
"model.layers.22.mlp.experts.73.down_proj.g_idx": "model-
|
| 24553 |
-
"model.layers.22.mlp.experts.73.down_proj.qweight": "model-
|
| 24554 |
-
"model.layers.22.mlp.experts.73.down_proj.qzeros": "model-
|
| 24555 |
-
"model.layers.22.mlp.experts.73.down_proj.scales": "model-
|
| 24556 |
-
"model.layers.22.mlp.experts.73.gate_proj.g_idx": "model-
|
| 24557 |
-
"model.layers.22.mlp.experts.73.gate_proj.qweight": "model-
|
| 24558 |
-
"model.layers.22.mlp.experts.73.gate_proj.qzeros": "model-
|
| 24559 |
-
"model.layers.22.mlp.experts.73.gate_proj.scales": "model-
|
| 24560 |
-
"model.layers.22.mlp.experts.73.up_proj.g_idx": "model-
|
| 24561 |
-
"model.layers.22.mlp.experts.73.up_proj.qweight": "model-
|
| 24562 |
-
"model.layers.22.mlp.experts.73.up_proj.qzeros": "model-
|
| 24563 |
-
"model.layers.22.mlp.experts.73.up_proj.scales": "model-
|
| 24564 |
-
"model.layers.22.mlp.experts.74.down_proj.g_idx": "model-
|
| 24565 |
-
"model.layers.22.mlp.experts.74.down_proj.qweight": "model-
|
| 24566 |
-
"model.layers.22.mlp.experts.74.down_proj.qzeros": "model-
|
| 24567 |
-
"model.layers.22.mlp.experts.74.down_proj.scales": "model-
|
| 24568 |
-
"model.layers.22.mlp.experts.74.gate_proj.g_idx": "model-
|
| 24569 |
-
"model.layers.22.mlp.experts.74.gate_proj.qweight": "model-
|
| 24570 |
-
"model.layers.22.mlp.experts.74.gate_proj.qzeros": "model-
|
| 24571 |
-
"model.layers.22.mlp.experts.74.gate_proj.scales": "model-
|
| 24572 |
-
"model.layers.22.mlp.experts.74.up_proj.g_idx": "model-
|
| 24573 |
-
"model.layers.22.mlp.experts.74.up_proj.qweight": "model-
|
| 24574 |
-
"model.layers.22.mlp.experts.74.up_proj.qzeros": "model-
|
| 24575 |
-
"model.layers.22.mlp.experts.74.up_proj.scales": "model-
|
| 24576 |
-
"model.layers.22.mlp.experts.75.down_proj.g_idx": "model-
|
| 24577 |
-
"model.layers.22.mlp.experts.75.down_proj.qweight": "model-
|
| 24578 |
-
"model.layers.22.mlp.experts.75.down_proj.qzeros": "model-
|
| 24579 |
-
"model.layers.22.mlp.experts.75.down_proj.scales": "model-
|
| 24580 |
-
"model.layers.22.mlp.experts.75.gate_proj.g_idx": "model-
|
| 24581 |
-
"model.layers.22.mlp.experts.75.gate_proj.qweight": "model-
|
| 24582 |
-
"model.layers.22.mlp.experts.75.gate_proj.qzeros": "model-
|
| 24583 |
-
"model.layers.22.mlp.experts.75.gate_proj.scales": "model-
|
| 24584 |
-
"model.layers.22.mlp.experts.75.up_proj.g_idx": "model-
|
| 24585 |
-
"model.layers.22.mlp.experts.75.up_proj.qweight": "model-
|
| 24586 |
-
"model.layers.22.mlp.experts.75.up_proj.qzeros": "model-
|
| 24587 |
-
"model.layers.22.mlp.experts.75.up_proj.scales": "model-
|
| 24588 |
"model.layers.22.mlp.experts.76.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 24589 |
"model.layers.22.mlp.experts.76.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24590 |
"model.layers.22.mlp.experts.76.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 24591 |
"model.layers.22.mlp.experts.76.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 24592 |
-
"model.layers.22.mlp.experts.76.gate_proj.g_idx": "model-
|
| 24593 |
-
"model.layers.22.mlp.experts.76.gate_proj.qweight": "model-
|
| 24594 |
-
"model.layers.22.mlp.experts.76.gate_proj.qzeros": "model-
|
| 24595 |
-
"model.layers.22.mlp.experts.76.gate_proj.scales": "model-
|
| 24596 |
"model.layers.22.mlp.experts.76.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 24597 |
"model.layers.22.mlp.experts.76.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24598 |
"model.layers.22.mlp.experts.76.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
|
@@ -24897,7 +24942,10 @@
|
|
| 24897 |
"model.layers.22.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24898 |
"model.layers.22.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 24899 |
"model.layers.22.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 24900 |
-
"model.layers.22.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 24901 |
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 24902 |
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 24903 |
"model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
@@ -26454,7 +26502,10 @@
|
|
| 26454 |
"model.layers.23.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 26455 |
"model.layers.23.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 26456 |
"model.layers.23.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 26457 |
-
"model.layers.23.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 26458 |
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 26459 |
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 26460 |
"model.layers.23.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -28011,7 +28062,10 @@
|
|
| 28011 |
"model.layers.24.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 28012 |
"model.layers.24.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 28013 |
"model.layers.24.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 28014 |
-
"model.layers.24.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 28015 |
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 28016 |
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 28017 |
"model.layers.24.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -29568,7 +29622,10 @@
|
|
| 29568 |
"model.layers.25.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 29569 |
"model.layers.25.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 29570 |
"model.layers.25.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 29571 |
-
"model.layers.25.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 29572 |
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 29573 |
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 29574 |
"model.layers.25.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -31125,7 +31182,10 @@
|
|
| 31125 |
"model.layers.26.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 31126 |
"model.layers.26.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 31127 |
"model.layers.26.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 31128 |
-
"model.layers.26.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 31129 |
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 31130 |
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 31131 |
"model.layers.26.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -32682,7 +32742,10 @@
|
|
| 32682 |
"model.layers.27.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 32683 |
"model.layers.27.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 32684 |
"model.layers.27.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 32685 |
-
"model.layers.27.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 32686 |
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 32687 |
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 32688 |
"model.layers.27.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -34239,7 +34302,10 @@
|
|
| 34239 |
"model.layers.28.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 34240 |
"model.layers.28.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 34241 |
"model.layers.28.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 34242 |
-
"model.layers.28.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 34243 |
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 34244 |
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 34245 |
"model.layers.28.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -35796,7 +35862,10 @@
|
|
| 35796 |
"model.layers.29.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 35797 |
"model.layers.29.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 35798 |
"model.layers.29.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 35799 |
-
"model.layers.29.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 35800 |
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 35801 |
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 35802 |
"model.layers.29.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -37353,7 +37422,10 @@
|
|
| 37353 |
"model.layers.3.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 37354 |
"model.layers.3.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 37355 |
"model.layers.3.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 37356 |
-
"model.layers.3.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 37357 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 37358 |
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 37359 |
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -38910,7 +38982,10 @@
|
|
| 38910 |
"model.layers.30.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 38911 |
"model.layers.30.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 38912 |
"model.layers.30.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 38913 |
-
"model.layers.30.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 38914 |
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 38915 |
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 38916 |
"model.layers.30.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -40467,7 +40542,10 @@
|
|
| 40467 |
"model.layers.31.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 40468 |
"model.layers.31.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 40469 |
"model.layers.31.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 40470 |
-
"model.layers.31.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 40471 |
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 40472 |
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 40473 |
"model.layers.31.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -42024,7 +42102,10 @@
|
|
| 42024 |
"model.layers.32.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 42025 |
"model.layers.32.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 42026 |
"model.layers.32.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 42027 |
-
"model.layers.32.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 42028 |
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 42029 |
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 42030 |
"model.layers.32.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -43581,7 +43662,10 @@
|
|
| 43581 |
"model.layers.33.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43582 |
"model.layers.33.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43583 |
"model.layers.33.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43584 |
-
"model.layers.33.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 43585 |
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 43586 |
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 43587 |
"model.layers.33.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -43698,66 +43782,66 @@
|
|
| 43698 |
"model.layers.34.mlp.experts.104.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43699 |
"model.layers.34.mlp.experts.104.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43700 |
"model.layers.34.mlp.experts.104.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43701 |
-
"model.layers.34.mlp.experts.105.down_proj.g_idx": "model-
|
| 43702 |
-
"model.layers.34.mlp.experts.105.down_proj.qweight": "model-
|
| 43703 |
-
"model.layers.34.mlp.experts.105.down_proj.qzeros": "model-
|
| 43704 |
-
"model.layers.34.mlp.experts.105.down_proj.scales": "model-
|
| 43705 |
"model.layers.34.mlp.experts.105.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43706 |
"model.layers.34.mlp.experts.105.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43707 |
"model.layers.34.mlp.experts.105.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43708 |
"model.layers.34.mlp.experts.105.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43709 |
-
"model.layers.34.mlp.experts.105.up_proj.g_idx": "model-
|
| 43710 |
-
"model.layers.34.mlp.experts.105.up_proj.qweight": "model-
|
| 43711 |
-
"model.layers.34.mlp.experts.105.up_proj.qzeros": "model-
|
| 43712 |
-
"model.layers.34.mlp.experts.105.up_proj.scales": "model-
|
| 43713 |
-
"model.layers.34.mlp.experts.106.down_proj.g_idx": "model-
|
| 43714 |
-
"model.layers.34.mlp.experts.106.down_proj.qweight": "model-
|
| 43715 |
-
"model.layers.34.mlp.experts.106.down_proj.qzeros": "model-
|
| 43716 |
-
"model.layers.34.mlp.experts.106.down_proj.scales": "model-
|
| 43717 |
-
"model.layers.34.mlp.experts.106.gate_proj.g_idx": "model-
|
| 43718 |
-
"model.layers.34.mlp.experts.106.gate_proj.qweight": "model-
|
| 43719 |
-
"model.layers.34.mlp.experts.106.gate_proj.qzeros": "model-
|
| 43720 |
-
"model.layers.34.mlp.experts.106.gate_proj.scales": "model-
|
| 43721 |
-
"model.layers.34.mlp.experts.106.up_proj.g_idx": "model-
|
| 43722 |
-
"model.layers.34.mlp.experts.106.up_proj.qweight": "model-
|
| 43723 |
-
"model.layers.34.mlp.experts.106.up_proj.qzeros": "model-
|
| 43724 |
-
"model.layers.34.mlp.experts.106.up_proj.scales": "model-
|
| 43725 |
-
"model.layers.34.mlp.experts.107.down_proj.g_idx": "model-
|
| 43726 |
-
"model.layers.34.mlp.experts.107.down_proj.qweight": "model-
|
| 43727 |
-
"model.layers.34.mlp.experts.107.down_proj.qzeros": "model-
|
| 43728 |
-
"model.layers.34.mlp.experts.107.down_proj.scales": "model-
|
| 43729 |
-
"model.layers.34.mlp.experts.107.gate_proj.g_idx": "model-
|
| 43730 |
-
"model.layers.34.mlp.experts.107.gate_proj.qweight": "model-
|
| 43731 |
-
"model.layers.34.mlp.experts.107.gate_proj.qzeros": "model-
|
| 43732 |
-
"model.layers.34.mlp.experts.107.gate_proj.scales": "model-
|
| 43733 |
-
"model.layers.34.mlp.experts.107.up_proj.g_idx": "model-
|
| 43734 |
-
"model.layers.34.mlp.experts.107.up_proj.qweight": "model-
|
| 43735 |
-
"model.layers.34.mlp.experts.107.up_proj.qzeros": "model-
|
| 43736 |
-
"model.layers.34.mlp.experts.107.up_proj.scales": "model-
|
| 43737 |
-
"model.layers.34.mlp.experts.108.down_proj.g_idx": "model-
|
| 43738 |
-
"model.layers.34.mlp.experts.108.down_proj.qweight": "model-
|
| 43739 |
-
"model.layers.34.mlp.experts.108.down_proj.qzeros": "model-
|
| 43740 |
-
"model.layers.34.mlp.experts.108.down_proj.scales": "model-
|
| 43741 |
-
"model.layers.34.mlp.experts.108.gate_proj.g_idx": "model-
|
| 43742 |
-
"model.layers.34.mlp.experts.108.gate_proj.qweight": "model-
|
| 43743 |
-
"model.layers.34.mlp.experts.108.gate_proj.qzeros": "model-
|
| 43744 |
-
"model.layers.34.mlp.experts.108.gate_proj.scales": "model-
|
| 43745 |
-
"model.layers.34.mlp.experts.108.up_proj.g_idx": "model-
|
| 43746 |
-
"model.layers.34.mlp.experts.108.up_proj.qweight": "model-
|
| 43747 |
-
"model.layers.34.mlp.experts.108.up_proj.qzeros": "model-
|
| 43748 |
-
"model.layers.34.mlp.experts.108.up_proj.scales": "model-
|
| 43749 |
-
"model.layers.34.mlp.experts.109.down_proj.g_idx": "model-
|
| 43750 |
-
"model.layers.34.mlp.experts.109.down_proj.qweight": "model-
|
| 43751 |
-
"model.layers.34.mlp.experts.109.down_proj.qzeros": "model-
|
| 43752 |
-
"model.layers.34.mlp.experts.109.down_proj.scales": "model-
|
| 43753 |
-
"model.layers.34.mlp.experts.109.gate_proj.g_idx": "model-
|
| 43754 |
-
"model.layers.34.mlp.experts.109.gate_proj.qweight": "model-
|
| 43755 |
-
"model.layers.34.mlp.experts.109.gate_proj.qzeros": "model-
|
| 43756 |
-
"model.layers.34.mlp.experts.109.gate_proj.scales": "model-
|
| 43757 |
-
"model.layers.34.mlp.experts.109.up_proj.g_idx": "model-
|
| 43758 |
-
"model.layers.34.mlp.experts.109.up_proj.qweight": "model-
|
| 43759 |
-
"model.layers.34.mlp.experts.109.up_proj.qzeros": "model-
|
| 43760 |
-
"model.layers.34.mlp.experts.109.up_proj.scales": "model-
|
| 43761 |
"model.layers.34.mlp.experts.11.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43762 |
"model.layers.34.mlp.experts.11.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43763 |
"model.layers.34.mlp.experts.11.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
|
@@ -43774,10 +43858,10 @@
|
|
| 43774 |
"model.layers.34.mlp.experts.110.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 43775 |
"model.layers.34.mlp.experts.110.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 43776 |
"model.layers.34.mlp.experts.110.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 43777 |
-
"model.layers.34.mlp.experts.110.gate_proj.g_idx": "model-
|
| 43778 |
-
"model.layers.34.mlp.experts.110.gate_proj.qweight": "model-
|
| 43779 |
-
"model.layers.34.mlp.experts.110.gate_proj.qzeros": "model-
|
| 43780 |
-
"model.layers.34.mlp.experts.110.gate_proj.scales": "model-
|
| 43781 |
"model.layers.34.mlp.experts.110.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 43782 |
"model.layers.34.mlp.experts.110.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 43783 |
"model.layers.34.mlp.experts.110.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
|
@@ -45138,7 +45222,10 @@
|
|
| 45138 |
"model.layers.34.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 45139 |
"model.layers.34.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 45140 |
"model.layers.34.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 45141 |
-
"model.layers.34.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 45142 |
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 45143 |
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 45144 |
"model.layers.34.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
@@ -46695,7 +46782,10 @@
|
|
| 46695 |
"model.layers.35.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 46696 |
"model.layers.35.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 46697 |
"model.layers.35.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 46698 |
-
"model.layers.35.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 46699 |
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 46700 |
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 46701 |
"model.layers.35.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -48252,7 +48342,10 @@
|
|
| 48252 |
"model.layers.36.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 48253 |
"model.layers.36.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 48254 |
"model.layers.36.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 48255 |
-
"model.layers.36.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 48256 |
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 48257 |
"model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 48258 |
"model.layers.36.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -49809,7 +49902,10 @@
|
|
| 49809 |
"model.layers.37.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 49810 |
"model.layers.37.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 49811 |
"model.layers.37.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 49812 |
-
"model.layers.37.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 49813 |
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 49814 |
"model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 49815 |
"model.layers.37.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -51366,7 +51462,10 @@
|
|
| 51366 |
"model.layers.38.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 51367 |
"model.layers.38.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 51368 |
"model.layers.38.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 51369 |
-
"model.layers.38.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 51370 |
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 51371 |
"model.layers.38.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 51372 |
"model.layers.38.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -52923,7 +53022,10 @@
|
|
| 52923 |
"model.layers.39.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 52924 |
"model.layers.39.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 52925 |
"model.layers.39.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 52926 |
-
"model.layers.39.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 52927 |
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 52928 |
"model.layers.39.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 52929 |
"model.layers.39.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -54480,7 +54582,10 @@
|
|
| 54480 |
"model.layers.4.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 54481 |
"model.layers.4.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 54482 |
"model.layers.4.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 54483 |
-
"model.layers.4.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 54484 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 54485 |
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 54486 |
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -56037,7 +56142,10 @@
|
|
| 56037 |
"model.layers.40.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 56038 |
"model.layers.40.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 56039 |
"model.layers.40.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 56040 |
-
"model.layers.40.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 56041 |
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 56042 |
"model.layers.40.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 56043 |
"model.layers.40.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -57594,7 +57702,10 @@
|
|
| 57594 |
"model.layers.41.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 57595 |
"model.layers.41.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 57596 |
"model.layers.41.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 57597 |
-
"model.layers.41.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 57598 |
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 57599 |
"model.layers.41.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 57600 |
"model.layers.41.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -59151,7 +59262,10 @@
|
|
| 59151 |
"model.layers.42.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 59152 |
"model.layers.42.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 59153 |
"model.layers.42.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 59154 |
-
"model.layers.42.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 59155 |
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 59156 |
"model.layers.42.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 59157 |
"model.layers.42.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -60708,7 +60822,10 @@
|
|
| 60708 |
"model.layers.43.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 60709 |
"model.layers.43.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 60710 |
"model.layers.43.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 60711 |
-
"model.layers.43.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 60712 |
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 60713 |
"model.layers.43.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 60714 |
"model.layers.43.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -62265,7 +62382,10 @@
|
|
| 62265 |
"model.layers.44.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 62266 |
"model.layers.44.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 62267 |
"model.layers.44.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 62268 |
-
"model.layers.44.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 62269 |
"model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 62270 |
"model.layers.44.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 62271 |
"model.layers.44.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -63822,7 +63942,10 @@
|
|
| 63822 |
"model.layers.45.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 63823 |
"model.layers.45.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 63824 |
"model.layers.45.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 63825 |
-
"model.layers.45.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 63826 |
"model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 63827 |
"model.layers.45.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 63828 |
"model.layers.45.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -65379,7 +65502,10 @@
|
|
| 65379 |
"model.layers.46.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65380 |
"model.layers.46.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65381 |
"model.layers.46.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65382 |
-
"model.layers.46.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 65383 |
"model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 65384 |
"model.layers.46.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 65385 |
"model.layers.46.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -65424,18 +65550,18 @@
|
|
| 65424 |
"model.layers.47.mlp.experts.1.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65425 |
"model.layers.47.mlp.experts.1.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65426 |
"model.layers.47.mlp.experts.1.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65427 |
-
"model.layers.47.mlp.experts.10.down_proj.g_idx": "model-
|
| 65428 |
-
"model.layers.47.mlp.experts.10.down_proj.qweight": "model-
|
| 65429 |
-
"model.layers.47.mlp.experts.10.down_proj.qzeros": "model-
|
| 65430 |
-
"model.layers.47.mlp.experts.10.down_proj.scales": "model-
|
| 65431 |
-
"model.layers.47.mlp.experts.10.gate_proj.g_idx": "model-
|
| 65432 |
-
"model.layers.47.mlp.experts.10.gate_proj.qweight": "model-
|
| 65433 |
-
"model.layers.47.mlp.experts.10.gate_proj.qzeros": "model-
|
| 65434 |
-
"model.layers.47.mlp.experts.10.gate_proj.scales": "model-
|
| 65435 |
-
"model.layers.47.mlp.experts.10.up_proj.g_idx": "model-
|
| 65436 |
-
"model.layers.47.mlp.experts.10.up_proj.qweight": "model-
|
| 65437 |
-
"model.layers.47.mlp.experts.10.up_proj.qzeros": "model-
|
| 65438 |
-
"model.layers.47.mlp.experts.10.up_proj.scales": "model-
|
| 65439 |
"model.layers.47.mlp.experts.100.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65440 |
"model.layers.47.mlp.experts.100.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65441 |
"model.layers.47.mlp.experts.100.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -65556,18 +65682,18 @@
|
|
| 65556 |
"model.layers.47.mlp.experts.109.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65557 |
"model.layers.47.mlp.experts.109.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 65558 |
"model.layers.47.mlp.experts.109.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 65559 |
-
"model.layers.47.mlp.experts.11.down_proj.g_idx": "model-
|
| 65560 |
-
"model.layers.47.mlp.experts.11.down_proj.qweight": "model-
|
| 65561 |
-
"model.layers.47.mlp.experts.11.down_proj.qzeros": "model-
|
| 65562 |
-
"model.layers.47.mlp.experts.11.down_proj.scales": "model-
|
| 65563 |
-
"model.layers.47.mlp.experts.11.gate_proj.g_idx": "model-
|
| 65564 |
-
"model.layers.47.mlp.experts.11.gate_proj.qweight": "model-
|
| 65565 |
-
"model.layers.47.mlp.experts.11.gate_proj.qzeros": "model-
|
| 65566 |
-
"model.layers.47.mlp.experts.11.gate_proj.scales": "model-
|
| 65567 |
-
"model.layers.47.mlp.experts.11.up_proj.g_idx": "model-
|
| 65568 |
-
"model.layers.47.mlp.experts.11.up_proj.qweight": "model-
|
| 65569 |
-
"model.layers.47.mlp.experts.11.up_proj.qzeros": "model-
|
| 65570 |
-
"model.layers.47.mlp.experts.11.up_proj.scales": "model-
|
| 65571 |
"model.layers.47.mlp.experts.110.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65572 |
"model.layers.47.mlp.experts.110.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65573 |
"model.layers.47.mlp.experts.110.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -65692,10 +65818,10 @@
|
|
| 65692 |
"model.layers.47.mlp.experts.12.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65693 |
"model.layers.47.mlp.experts.12.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 65694 |
"model.layers.47.mlp.experts.12.down_proj.scales": "model-00005-of-00005.safetensors",
|
| 65695 |
-
"model.layers.47.mlp.experts.12.gate_proj.g_idx": "model-
|
| 65696 |
-
"model.layers.47.mlp.experts.12.gate_proj.qweight": "model-
|
| 65697 |
-
"model.layers.47.mlp.experts.12.gate_proj.qzeros": "model-
|
| 65698 |
-
"model.layers.47.mlp.experts.12.gate_proj.scales": "model-
|
| 65699 |
"model.layers.47.mlp.experts.12.up_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65700 |
"model.layers.47.mlp.experts.12.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65701 |
"model.layers.47.mlp.experts.12.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66276,18 +66402,18 @@
|
|
| 66276 |
"model.layers.47.mlp.experts.49.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66277 |
"model.layers.47.mlp.experts.49.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66278 |
"model.layers.47.mlp.experts.49.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66279 |
-
"model.layers.47.mlp.experts.5.down_proj.g_idx": "model-
|
| 66280 |
-
"model.layers.47.mlp.experts.5.down_proj.qweight": "model-
|
| 66281 |
-
"model.layers.47.mlp.experts.5.down_proj.qzeros": "model-
|
| 66282 |
-
"model.layers.47.mlp.experts.5.down_proj.scales": "model-
|
| 66283 |
"model.layers.47.mlp.experts.5.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66284 |
"model.layers.47.mlp.experts.5.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66285 |
"model.layers.47.mlp.experts.5.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66286 |
"model.layers.47.mlp.experts.5.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66287 |
-
"model.layers.47.mlp.experts.5.up_proj.g_idx": "model-
|
| 66288 |
-
"model.layers.47.mlp.experts.5.up_proj.qweight": "model-
|
| 66289 |
-
"model.layers.47.mlp.experts.5.up_proj.qzeros": "model-
|
| 66290 |
-
"model.layers.47.mlp.experts.5.up_proj.scales": "model-
|
| 66291 |
"model.layers.47.mlp.experts.50.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66292 |
"model.layers.47.mlp.experts.50.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66293 |
"model.layers.47.mlp.experts.50.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66408,18 +66534,18 @@
|
|
| 66408 |
"model.layers.47.mlp.experts.59.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66409 |
"model.layers.47.mlp.experts.59.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66410 |
"model.layers.47.mlp.experts.59.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66411 |
-
"model.layers.47.mlp.experts.6.down_proj.g_idx": "model-
|
| 66412 |
-
"model.layers.47.mlp.experts.6.down_proj.qweight": "model-
|
| 66413 |
-
"model.layers.47.mlp.experts.6.down_proj.qzeros": "model-
|
| 66414 |
-
"model.layers.47.mlp.experts.6.down_proj.scales": "model-
|
| 66415 |
-
"model.layers.47.mlp.experts.6.gate_proj.g_idx": "model-
|
| 66416 |
-
"model.layers.47.mlp.experts.6.gate_proj.qweight": "model-
|
| 66417 |
-
"model.layers.47.mlp.experts.6.gate_proj.qzeros": "model-
|
| 66418 |
-
"model.layers.47.mlp.experts.6.gate_proj.scales": "model-
|
| 66419 |
-
"model.layers.47.mlp.experts.6.up_proj.g_idx": "model-
|
| 66420 |
-
"model.layers.47.mlp.experts.6.up_proj.qweight": "model-
|
| 66421 |
-
"model.layers.47.mlp.experts.6.up_proj.qzeros": "model-
|
| 66422 |
-
"model.layers.47.mlp.experts.6.up_proj.scales": "model-
|
| 66423 |
"model.layers.47.mlp.experts.60.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66424 |
"model.layers.47.mlp.experts.60.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66425 |
"model.layers.47.mlp.experts.60.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66540,18 +66666,18 @@
|
|
| 66540 |
"model.layers.47.mlp.experts.69.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66541 |
"model.layers.47.mlp.experts.69.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66542 |
"model.layers.47.mlp.experts.69.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66543 |
-
"model.layers.47.mlp.experts.7.down_proj.g_idx": "model-
|
| 66544 |
-
"model.layers.47.mlp.experts.7.down_proj.qweight": "model-
|
| 66545 |
-
"model.layers.47.mlp.experts.7.down_proj.qzeros": "model-
|
| 66546 |
-
"model.layers.47.mlp.experts.7.down_proj.scales": "model-
|
| 66547 |
-
"model.layers.47.mlp.experts.7.gate_proj.g_idx": "model-
|
| 66548 |
-
"model.layers.47.mlp.experts.7.gate_proj.qweight": "model-
|
| 66549 |
-
"model.layers.47.mlp.experts.7.gate_proj.qzeros": "model-
|
| 66550 |
-
"model.layers.47.mlp.experts.7.gate_proj.scales": "model-
|
| 66551 |
-
"model.layers.47.mlp.experts.7.up_proj.g_idx": "model-
|
| 66552 |
-
"model.layers.47.mlp.experts.7.up_proj.qweight": "model-
|
| 66553 |
-
"model.layers.47.mlp.experts.7.up_proj.qzeros": "model-
|
| 66554 |
-
"model.layers.47.mlp.experts.7.up_proj.scales": "model-
|
| 66555 |
"model.layers.47.mlp.experts.70.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66556 |
"model.layers.47.mlp.experts.70.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66557 |
"model.layers.47.mlp.experts.70.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66672,18 +66798,18 @@
|
|
| 66672 |
"model.layers.47.mlp.experts.79.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66673 |
"model.layers.47.mlp.experts.79.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66674 |
"model.layers.47.mlp.experts.79.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66675 |
-
"model.layers.47.mlp.experts.8.down_proj.g_idx": "model-
|
| 66676 |
-
"model.layers.47.mlp.experts.8.down_proj.qweight": "model-
|
| 66677 |
-
"model.layers.47.mlp.experts.8.down_proj.qzeros": "model-
|
| 66678 |
-
"model.layers.47.mlp.experts.8.down_proj.scales": "model-
|
| 66679 |
-
"model.layers.47.mlp.experts.8.gate_proj.g_idx": "model-
|
| 66680 |
-
"model.layers.47.mlp.experts.8.gate_proj.qweight": "model-
|
| 66681 |
-
"model.layers.47.mlp.experts.8.gate_proj.qzeros": "model-
|
| 66682 |
-
"model.layers.47.mlp.experts.8.gate_proj.scales": "model-
|
| 66683 |
-
"model.layers.47.mlp.experts.8.up_proj.g_idx": "model-
|
| 66684 |
-
"model.layers.47.mlp.experts.8.up_proj.qweight": "model-
|
| 66685 |
-
"model.layers.47.mlp.experts.8.up_proj.qzeros": "model-
|
| 66686 |
-
"model.layers.47.mlp.experts.8.up_proj.scales": "model-
|
| 66687 |
"model.layers.47.mlp.experts.80.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66688 |
"model.layers.47.mlp.experts.80.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66689 |
"model.layers.47.mlp.experts.80.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66804,18 +66930,18 @@
|
|
| 66804 |
"model.layers.47.mlp.experts.89.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66805 |
"model.layers.47.mlp.experts.89.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66806 |
"model.layers.47.mlp.experts.89.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66807 |
-
"model.layers.47.mlp.experts.9.down_proj.g_idx": "model-
|
| 66808 |
-
"model.layers.47.mlp.experts.9.down_proj.qweight": "model-
|
| 66809 |
-
"model.layers.47.mlp.experts.9.down_proj.qzeros": "model-
|
| 66810 |
-
"model.layers.47.mlp.experts.9.down_proj.scales": "model-
|
| 66811 |
-
"model.layers.47.mlp.experts.9.gate_proj.g_idx": "model-
|
| 66812 |
-
"model.layers.47.mlp.experts.9.gate_proj.qweight": "model-
|
| 66813 |
-
"model.layers.47.mlp.experts.9.gate_proj.qzeros": "model-
|
| 66814 |
-
"model.layers.47.mlp.experts.9.gate_proj.scales": "model-
|
| 66815 |
-
"model.layers.47.mlp.experts.9.up_proj.g_idx": "model-
|
| 66816 |
-
"model.layers.47.mlp.experts.9.up_proj.qweight": "model-
|
| 66817 |
-
"model.layers.47.mlp.experts.9.up_proj.qzeros": "model-
|
| 66818 |
-
"model.layers.47.mlp.experts.9.up_proj.scales": "model-
|
| 66819 |
"model.layers.47.mlp.experts.90.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66820 |
"model.layers.47.mlp.experts.90.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66821 |
"model.layers.47.mlp.experts.90.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
@@ -66936,7 +67062,10 @@
|
|
| 66936 |
"model.layers.47.mlp.experts.99.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66937 |
"model.layers.47.mlp.experts.99.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66938 |
"model.layers.47.mlp.experts.99.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66939 |
-
"model.layers.47.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 66940 |
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 66941 |
"model.layers.47.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 66942 |
"model.layers.47.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
@@ -68493,7 +68622,10 @@
|
|
| 68493 |
"model.layers.5.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 68494 |
"model.layers.5.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 68495 |
"model.layers.5.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 68496 |
-
"model.layers.5.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 68497 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 68498 |
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 68499 |
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -70050,7 +70182,10 @@
|
|
| 70050 |
"model.layers.6.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 70051 |
"model.layers.6.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 70052 |
"model.layers.6.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 70053 |
-
"model.layers.6.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 70054 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 70055 |
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 70056 |
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -71607,7 +71742,10 @@
|
|
| 71607 |
"model.layers.7.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 71608 |
"model.layers.7.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 71609 |
"model.layers.7.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 71610 |
-
"model.layers.7.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 71611 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 71612 |
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 71613 |
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -73164,7 +73302,10 @@
|
|
| 73164 |
"model.layers.8.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 73165 |
"model.layers.8.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 73166 |
"model.layers.8.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 73167 |
-
"model.layers.8.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 73168 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 73169 |
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 73170 |
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
@@ -74721,7 +74862,10 @@
|
|
| 74721 |
"model.layers.9.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 74722 |
"model.layers.9.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 74723 |
"model.layers.9.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 74724 |
-
"model.layers.9.mlp.gate.
|
|
|
|
|
|
|
|
|
|
| 74725 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 74726 |
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 74727 |
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 16905940992
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00005-of-00005.safetensors",
|
|
|
|
| 1542 |
"model.layers.0.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 1543 |
"model.layers.0.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 1544 |
"model.layers.0.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 1545 |
+
"model.layers.0.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 1546 |
+
"model.layers.0.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 1547 |
+
"model.layers.0.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 1548 |
+
"model.layers.0.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 1549 |
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 1550 |
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 1551 |
"model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 3102 |
"model.layers.1.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3103 |
"model.layers.1.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3104 |
"model.layers.1.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3105 |
+
"model.layers.1.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 3106 |
+
"model.layers.1.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 3107 |
+
"model.layers.1.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 3108 |
+
"model.layers.1.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 3109 |
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 3110 |
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 3111 |
"model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 3882 |
"model.layers.10.mlp.experts.4.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3883 |
"model.layers.10.mlp.experts.4.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3884 |
"model.layers.10.mlp.experts.4.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3885 |
+
"model.layers.10.mlp.experts.40.down_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3886 |
+
"model.layers.10.mlp.experts.40.down_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3887 |
+
"model.layers.10.mlp.experts.40.down_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3888 |
+
"model.layers.10.mlp.experts.40.down_proj.scales": "model-00001-of-00005.safetensors",
|
| 3889 |
"model.layers.10.mlp.experts.40.gate_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3890 |
"model.layers.10.mlp.experts.40.gate_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3891 |
"model.layers.10.mlp.experts.40.gate_proj.qzeros": "model-00001-of-00005.safetensors",
|
|
|
|
| 3894 |
"model.layers.10.mlp.experts.40.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3895 |
"model.layers.10.mlp.experts.40.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3896 |
"model.layers.10.mlp.experts.40.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3897 |
+
"model.layers.10.mlp.experts.41.down_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3898 |
+
"model.layers.10.mlp.experts.41.down_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3899 |
+
"model.layers.10.mlp.experts.41.down_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3900 |
+
"model.layers.10.mlp.experts.41.down_proj.scales": "model-00001-of-00005.safetensors",
|
| 3901 |
+
"model.layers.10.mlp.experts.41.gate_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3902 |
+
"model.layers.10.mlp.experts.41.gate_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3903 |
+
"model.layers.10.mlp.experts.41.gate_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3904 |
+
"model.layers.10.mlp.experts.41.gate_proj.scales": "model-00001-of-00005.safetensors",
|
| 3905 |
+
"model.layers.10.mlp.experts.41.up_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3906 |
+
"model.layers.10.mlp.experts.41.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3907 |
+
"model.layers.10.mlp.experts.41.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3908 |
+
"model.layers.10.mlp.experts.41.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 3909 |
"model.layers.10.mlp.experts.42.down_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 3910 |
"model.layers.10.mlp.experts.42.down_proj.qweight": "model-00002-of-00005.safetensors",
|
| 3911 |
"model.layers.10.mlp.experts.42.down_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 3912 |
"model.layers.10.mlp.experts.42.down_proj.scales": "model-00002-of-00005.safetensors",
|
| 3913 |
+
"model.layers.10.mlp.experts.42.gate_proj.g_idx": "model-00001-of-00005.safetensors",
|
| 3914 |
+
"model.layers.10.mlp.experts.42.gate_proj.qweight": "model-00001-of-00005.safetensors",
|
| 3915 |
+
"model.layers.10.mlp.experts.42.gate_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 3916 |
+
"model.layers.10.mlp.experts.42.gate_proj.scales": "model-00001-of-00005.safetensors",
|
| 3917 |
"model.layers.10.mlp.experts.42.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 3918 |
"model.layers.10.mlp.experts.42.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 3919 |
"model.layers.10.mlp.experts.42.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
|
|
|
| 4662 |
"model.layers.10.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 4663 |
"model.layers.10.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 4664 |
"model.layers.10.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 4665 |
+
"model.layers.10.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 4666 |
+
"model.layers.10.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 4667 |
+
"model.layers.10.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 4668 |
+
"model.layers.10.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 4669 |
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 4670 |
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 4671 |
"model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 6222 |
"model.layers.11.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 6223 |
"model.layers.11.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 6224 |
"model.layers.11.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 6225 |
+
"model.layers.11.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 6226 |
+
"model.layers.11.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 6227 |
+
"model.layers.11.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 6228 |
+
"model.layers.11.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 6229 |
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 6230 |
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 6231 |
"model.layers.11.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 7782 |
"model.layers.12.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 7783 |
"model.layers.12.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 7784 |
"model.layers.12.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 7785 |
+
"model.layers.12.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 7786 |
+
"model.layers.12.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 7787 |
+
"model.layers.12.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 7788 |
+
"model.layers.12.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 7789 |
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 7790 |
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 7791 |
"model.layers.12.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 9342 |
"model.layers.13.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 9343 |
"model.layers.13.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 9344 |
"model.layers.13.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 9345 |
+
"model.layers.13.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 9346 |
+
"model.layers.13.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 9347 |
+
"model.layers.13.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 9348 |
+
"model.layers.13.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 9349 |
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 9350 |
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 9351 |
"model.layers.13.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 10902 |
"model.layers.14.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 10903 |
"model.layers.14.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 10904 |
"model.layers.14.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 10905 |
+
"model.layers.14.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 10906 |
+
"model.layers.14.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 10907 |
+
"model.layers.14.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 10908 |
+
"model.layers.14.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 10909 |
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 10910 |
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 10911 |
"model.layers.14.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 12462 |
"model.layers.15.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 12463 |
"model.layers.15.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 12464 |
"model.layers.15.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 12465 |
+
"model.layers.15.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 12466 |
+
"model.layers.15.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 12467 |
+
"model.layers.15.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 12468 |
+
"model.layers.15.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 12469 |
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 12470 |
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 12471 |
"model.layers.15.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 14022 |
"model.layers.16.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 14023 |
"model.layers.16.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 14024 |
"model.layers.16.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 14025 |
+
"model.layers.16.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 14026 |
+
"model.layers.16.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 14027 |
+
"model.layers.16.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 14028 |
+
"model.layers.16.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 14029 |
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 14030 |
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 14031 |
"model.layers.16.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 15582 |
"model.layers.17.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 15583 |
"model.layers.17.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 15584 |
"model.layers.17.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 15585 |
+
"model.layers.17.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 15586 |
+
"model.layers.17.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 15587 |
+
"model.layers.17.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 15588 |
+
"model.layers.17.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 15589 |
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 15590 |
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 15591 |
"model.layers.17.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 17142 |
"model.layers.18.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 17143 |
"model.layers.18.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 17144 |
"model.layers.18.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 17145 |
+
"model.layers.18.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 17146 |
+
"model.layers.18.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 17147 |
+
"model.layers.18.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 17148 |
+
"model.layers.18.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 17149 |
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 17150 |
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 17151 |
"model.layers.18.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 18702 |
"model.layers.19.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 18703 |
"model.layers.19.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 18704 |
"model.layers.19.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 18705 |
+
"model.layers.19.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 18706 |
+
"model.layers.19.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 18707 |
+
"model.layers.19.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 18708 |
+
"model.layers.19.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 18709 |
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 18710 |
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 18711 |
"model.layers.19.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 20262 |
"model.layers.2.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 20263 |
"model.layers.2.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 20264 |
"model.layers.2.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 20265 |
+
"model.layers.2.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 20266 |
+
"model.layers.2.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 20267 |
+
"model.layers.2.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 20268 |
+
"model.layers.2.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 20269 |
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 20270 |
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 20271 |
"model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 21822 |
"model.layers.20.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 21823 |
"model.layers.20.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 21824 |
"model.layers.20.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 21825 |
+
"model.layers.20.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 21826 |
+
"model.layers.20.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 21827 |
+
"model.layers.20.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 21828 |
+
"model.layers.20.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 21829 |
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 21830 |
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 21831 |
"model.layers.20.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 23382 |
"model.layers.21.mlp.experts.99.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 23383 |
"model.layers.21.mlp.experts.99.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 23384 |
"model.layers.21.mlp.experts.99.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 23385 |
+
"model.layers.21.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 23386 |
+
"model.layers.21.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 23387 |
+
"model.layers.21.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 23388 |
+
"model.layers.21.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 23389 |
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 23390 |
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 23391 |
"model.layers.21.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 24594 |
"model.layers.22.mlp.experts.72.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24595 |
"model.layers.22.mlp.experts.72.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24596 |
"model.layers.22.mlp.experts.72.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 24597 |
+
"model.layers.22.mlp.experts.73.down_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24598 |
+
"model.layers.22.mlp.experts.73.down_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24599 |
+
"model.layers.22.mlp.experts.73.down_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24600 |
+
"model.layers.22.mlp.experts.73.down_proj.scales": "model-00002-of-00005.safetensors",
|
| 24601 |
+
"model.layers.22.mlp.experts.73.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24602 |
+
"model.layers.22.mlp.experts.73.gate_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24603 |
+
"model.layers.22.mlp.experts.73.gate_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24604 |
+
"model.layers.22.mlp.experts.73.gate_proj.scales": "model-00002-of-00005.safetensors",
|
| 24605 |
+
"model.layers.22.mlp.experts.73.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24606 |
+
"model.layers.22.mlp.experts.73.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24607 |
+
"model.layers.22.mlp.experts.73.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24608 |
+
"model.layers.22.mlp.experts.73.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 24609 |
+
"model.layers.22.mlp.experts.74.down_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24610 |
+
"model.layers.22.mlp.experts.74.down_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24611 |
+
"model.layers.22.mlp.experts.74.down_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24612 |
+
"model.layers.22.mlp.experts.74.down_proj.scales": "model-00002-of-00005.safetensors",
|
| 24613 |
+
"model.layers.22.mlp.experts.74.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24614 |
+
"model.layers.22.mlp.experts.74.gate_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24615 |
+
"model.layers.22.mlp.experts.74.gate_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24616 |
+
"model.layers.22.mlp.experts.74.gate_proj.scales": "model-00002-of-00005.safetensors",
|
| 24617 |
+
"model.layers.22.mlp.experts.74.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24618 |
+
"model.layers.22.mlp.experts.74.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24619 |
+
"model.layers.22.mlp.experts.74.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24620 |
+
"model.layers.22.mlp.experts.74.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 24621 |
+
"model.layers.22.mlp.experts.75.down_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24622 |
+
"model.layers.22.mlp.experts.75.down_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24623 |
+
"model.layers.22.mlp.experts.75.down_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24624 |
+
"model.layers.22.mlp.experts.75.down_proj.scales": "model-00002-of-00005.safetensors",
|
| 24625 |
+
"model.layers.22.mlp.experts.75.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24626 |
+
"model.layers.22.mlp.experts.75.gate_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24627 |
+
"model.layers.22.mlp.experts.75.gate_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24628 |
+
"model.layers.22.mlp.experts.75.gate_proj.scales": "model-00002-of-00005.safetensors",
|
| 24629 |
+
"model.layers.22.mlp.experts.75.up_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24630 |
+
"model.layers.22.mlp.experts.75.up_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24631 |
+
"model.layers.22.mlp.experts.75.up_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24632 |
+
"model.layers.22.mlp.experts.75.up_proj.scales": "model-00002-of-00005.safetensors",
|
| 24633 |
"model.layers.22.mlp.experts.76.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 24634 |
"model.layers.22.mlp.experts.76.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24635 |
"model.layers.22.mlp.experts.76.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 24636 |
"model.layers.22.mlp.experts.76.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 24637 |
+
"model.layers.22.mlp.experts.76.gate_proj.g_idx": "model-00002-of-00005.safetensors",
|
| 24638 |
+
"model.layers.22.mlp.experts.76.gate_proj.qweight": "model-00002-of-00005.safetensors",
|
| 24639 |
+
"model.layers.22.mlp.experts.76.gate_proj.qzeros": "model-00002-of-00005.safetensors",
|
| 24640 |
+
"model.layers.22.mlp.experts.76.gate_proj.scales": "model-00002-of-00005.safetensors",
|
| 24641 |
"model.layers.22.mlp.experts.76.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 24642 |
"model.layers.22.mlp.experts.76.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24643 |
"model.layers.22.mlp.experts.76.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
|
|
|
| 24942 |
"model.layers.22.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 24943 |
"model.layers.22.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 24944 |
"model.layers.22.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 24945 |
+
"model.layers.22.mlp.gate.g_idx": "model-00002-of-00005.safetensors",
|
| 24946 |
+
"model.layers.22.mlp.gate.qweight": "model-00002-of-00005.safetensors",
|
| 24947 |
+
"model.layers.22.mlp.gate.qzeros": "model-00002-of-00005.safetensors",
|
| 24948 |
+
"model.layers.22.mlp.gate.scales": "model-00002-of-00005.safetensors",
|
| 24949 |
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 24950 |
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00005.safetensors",
|
| 24951 |
"model.layers.22.self_attn.k_proj.g_idx": "model-00002-of-00005.safetensors",
|
|
|
|
| 26502 |
"model.layers.23.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 26503 |
"model.layers.23.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 26504 |
"model.layers.23.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 26505 |
+
"model.layers.23.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 26506 |
+
"model.layers.23.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 26507 |
+
"model.layers.23.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 26508 |
+
"model.layers.23.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 26509 |
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 26510 |
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 26511 |
"model.layers.23.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 28062 |
"model.layers.24.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 28063 |
"model.layers.24.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 28064 |
"model.layers.24.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 28065 |
+
"model.layers.24.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 28066 |
+
"model.layers.24.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 28067 |
+
"model.layers.24.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 28068 |
+
"model.layers.24.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 28069 |
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 28070 |
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 28071 |
"model.layers.24.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 29622 |
"model.layers.25.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 29623 |
"model.layers.25.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 29624 |
"model.layers.25.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 29625 |
+
"model.layers.25.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 29626 |
+
"model.layers.25.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 29627 |
+
"model.layers.25.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 29628 |
+
"model.layers.25.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 29629 |
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 29630 |
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 29631 |
"model.layers.25.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 31182 |
"model.layers.26.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 31183 |
"model.layers.26.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 31184 |
"model.layers.26.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 31185 |
+
"model.layers.26.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 31186 |
+
"model.layers.26.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 31187 |
+
"model.layers.26.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 31188 |
+
"model.layers.26.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 31189 |
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 31190 |
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 31191 |
"model.layers.26.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 32742 |
"model.layers.27.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 32743 |
"model.layers.27.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 32744 |
"model.layers.27.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 32745 |
+
"model.layers.27.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 32746 |
+
"model.layers.27.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 32747 |
+
"model.layers.27.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 32748 |
+
"model.layers.27.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 32749 |
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 32750 |
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 32751 |
"model.layers.27.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 34302 |
"model.layers.28.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 34303 |
"model.layers.28.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 34304 |
"model.layers.28.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 34305 |
+
"model.layers.28.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 34306 |
+
"model.layers.28.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 34307 |
+
"model.layers.28.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 34308 |
+
"model.layers.28.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 34309 |
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 34310 |
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 34311 |
"model.layers.28.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 35862 |
"model.layers.29.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 35863 |
"model.layers.29.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 35864 |
"model.layers.29.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 35865 |
+
"model.layers.29.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 35866 |
+
"model.layers.29.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 35867 |
+
"model.layers.29.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 35868 |
+
"model.layers.29.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 35869 |
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 35870 |
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 35871 |
"model.layers.29.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 37422 |
"model.layers.3.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 37423 |
"model.layers.3.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 37424 |
"model.layers.3.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 37425 |
+
"model.layers.3.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 37426 |
+
"model.layers.3.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 37427 |
+
"model.layers.3.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 37428 |
+
"model.layers.3.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 37429 |
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 37430 |
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 37431 |
"model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 38982 |
"model.layers.30.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 38983 |
"model.layers.30.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 38984 |
"model.layers.30.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 38985 |
+
"model.layers.30.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 38986 |
+
"model.layers.30.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 38987 |
+
"model.layers.30.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 38988 |
+
"model.layers.30.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 38989 |
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 38990 |
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 38991 |
"model.layers.30.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 40542 |
"model.layers.31.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 40543 |
"model.layers.31.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 40544 |
"model.layers.31.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 40545 |
+
"model.layers.31.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 40546 |
+
"model.layers.31.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 40547 |
+
"model.layers.31.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 40548 |
+
"model.layers.31.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 40549 |
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 40550 |
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 40551 |
"model.layers.31.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 42102 |
"model.layers.32.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 42103 |
"model.layers.32.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 42104 |
"model.layers.32.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 42105 |
+
"model.layers.32.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 42106 |
+
"model.layers.32.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 42107 |
+
"model.layers.32.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 42108 |
+
"model.layers.32.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 42109 |
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 42110 |
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 42111 |
"model.layers.32.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 43662 |
"model.layers.33.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43663 |
"model.layers.33.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43664 |
"model.layers.33.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43665 |
+
"model.layers.33.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 43666 |
+
"model.layers.33.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 43667 |
+
"model.layers.33.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 43668 |
+
"model.layers.33.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 43669 |
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 43670 |
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 43671 |
"model.layers.33.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 43782 |
"model.layers.34.mlp.experts.104.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43783 |
"model.layers.34.mlp.experts.104.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43784 |
"model.layers.34.mlp.experts.104.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43785 |
+
"model.layers.34.mlp.experts.105.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43786 |
+
"model.layers.34.mlp.experts.105.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43787 |
+
"model.layers.34.mlp.experts.105.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43788 |
+
"model.layers.34.mlp.experts.105.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 43789 |
"model.layers.34.mlp.experts.105.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43790 |
"model.layers.34.mlp.experts.105.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43791 |
"model.layers.34.mlp.experts.105.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43792 |
"model.layers.34.mlp.experts.105.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43793 |
+
"model.layers.34.mlp.experts.105.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43794 |
+
"model.layers.34.mlp.experts.105.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43795 |
+
"model.layers.34.mlp.experts.105.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43796 |
+
"model.layers.34.mlp.experts.105.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43797 |
+
"model.layers.34.mlp.experts.106.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43798 |
+
"model.layers.34.mlp.experts.106.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43799 |
+
"model.layers.34.mlp.experts.106.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43800 |
+
"model.layers.34.mlp.experts.106.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 43801 |
+
"model.layers.34.mlp.experts.106.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43802 |
+
"model.layers.34.mlp.experts.106.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43803 |
+
"model.layers.34.mlp.experts.106.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43804 |
+
"model.layers.34.mlp.experts.106.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43805 |
+
"model.layers.34.mlp.experts.106.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43806 |
+
"model.layers.34.mlp.experts.106.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43807 |
+
"model.layers.34.mlp.experts.106.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43808 |
+
"model.layers.34.mlp.experts.106.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43809 |
+
"model.layers.34.mlp.experts.107.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43810 |
+
"model.layers.34.mlp.experts.107.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43811 |
+
"model.layers.34.mlp.experts.107.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43812 |
+
"model.layers.34.mlp.experts.107.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 43813 |
+
"model.layers.34.mlp.experts.107.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43814 |
+
"model.layers.34.mlp.experts.107.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43815 |
+
"model.layers.34.mlp.experts.107.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43816 |
+
"model.layers.34.mlp.experts.107.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43817 |
+
"model.layers.34.mlp.experts.107.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43818 |
+
"model.layers.34.mlp.experts.107.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43819 |
+
"model.layers.34.mlp.experts.107.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43820 |
+
"model.layers.34.mlp.experts.107.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43821 |
+
"model.layers.34.mlp.experts.108.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43822 |
+
"model.layers.34.mlp.experts.108.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43823 |
+
"model.layers.34.mlp.experts.108.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43824 |
+
"model.layers.34.mlp.experts.108.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 43825 |
+
"model.layers.34.mlp.experts.108.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43826 |
+
"model.layers.34.mlp.experts.108.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43827 |
+
"model.layers.34.mlp.experts.108.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43828 |
+
"model.layers.34.mlp.experts.108.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43829 |
+
"model.layers.34.mlp.experts.108.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43830 |
+
"model.layers.34.mlp.experts.108.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43831 |
+
"model.layers.34.mlp.experts.108.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43832 |
+
"model.layers.34.mlp.experts.108.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43833 |
+
"model.layers.34.mlp.experts.109.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43834 |
+
"model.layers.34.mlp.experts.109.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43835 |
+
"model.layers.34.mlp.experts.109.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43836 |
+
"model.layers.34.mlp.experts.109.down_proj.scales": "model-00003-of-00005.safetensors",
|
| 43837 |
+
"model.layers.34.mlp.experts.109.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43838 |
+
"model.layers.34.mlp.experts.109.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43839 |
+
"model.layers.34.mlp.experts.109.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43840 |
+
"model.layers.34.mlp.experts.109.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43841 |
+
"model.layers.34.mlp.experts.109.up_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43842 |
+
"model.layers.34.mlp.experts.109.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43843 |
+
"model.layers.34.mlp.experts.109.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43844 |
+
"model.layers.34.mlp.experts.109.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 43845 |
"model.layers.34.mlp.experts.11.down_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43846 |
"model.layers.34.mlp.experts.11.down_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43847 |
"model.layers.34.mlp.experts.11.down_proj.qzeros": "model-00003-of-00005.safetensors",
|
|
|
|
| 43858 |
"model.layers.34.mlp.experts.110.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 43859 |
"model.layers.34.mlp.experts.110.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 43860 |
"model.layers.34.mlp.experts.110.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 43861 |
+
"model.layers.34.mlp.experts.110.gate_proj.g_idx": "model-00003-of-00005.safetensors",
|
| 43862 |
+
"model.layers.34.mlp.experts.110.gate_proj.qweight": "model-00003-of-00005.safetensors",
|
| 43863 |
+
"model.layers.34.mlp.experts.110.gate_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 43864 |
+
"model.layers.34.mlp.experts.110.gate_proj.scales": "model-00003-of-00005.safetensors",
|
| 43865 |
"model.layers.34.mlp.experts.110.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 43866 |
"model.layers.34.mlp.experts.110.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 43867 |
"model.layers.34.mlp.experts.110.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
|
|
|
| 45222 |
"model.layers.34.mlp.experts.99.up_proj.qweight": "model-00003-of-00005.safetensors",
|
| 45223 |
"model.layers.34.mlp.experts.99.up_proj.qzeros": "model-00003-of-00005.safetensors",
|
| 45224 |
"model.layers.34.mlp.experts.99.up_proj.scales": "model-00003-of-00005.safetensors",
|
| 45225 |
+
"model.layers.34.mlp.gate.g_idx": "model-00003-of-00005.safetensors",
|
| 45226 |
+
"model.layers.34.mlp.gate.qweight": "model-00003-of-00005.safetensors",
|
| 45227 |
+
"model.layers.34.mlp.gate.qzeros": "model-00003-of-00005.safetensors",
|
| 45228 |
+
"model.layers.34.mlp.gate.scales": "model-00003-of-00005.safetensors",
|
| 45229 |
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 45230 |
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00005.safetensors",
|
| 45231 |
"model.layers.34.self_attn.k_proj.g_idx": "model-00003-of-00005.safetensors",
|
|
|
|
| 46782 |
"model.layers.35.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 46783 |
"model.layers.35.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 46784 |
"model.layers.35.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 46785 |
+
"model.layers.35.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 46786 |
+
"model.layers.35.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 46787 |
+
"model.layers.35.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 46788 |
+
"model.layers.35.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 46789 |
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 46790 |
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 46791 |
"model.layers.35.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 48342 |
"model.layers.36.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 48343 |
"model.layers.36.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 48344 |
"model.layers.36.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 48345 |
+
"model.layers.36.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 48346 |
+
"model.layers.36.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 48347 |
+
"model.layers.36.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 48348 |
+
"model.layers.36.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 48349 |
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 48350 |
"model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 48351 |
"model.layers.36.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 49902 |
"model.layers.37.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 49903 |
"model.layers.37.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 49904 |
"model.layers.37.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 49905 |
+
"model.layers.37.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 49906 |
+
"model.layers.37.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 49907 |
+
"model.layers.37.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 49908 |
+
"model.layers.37.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 49909 |
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 49910 |
"model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 49911 |
"model.layers.37.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 51462 |
"model.layers.38.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 51463 |
"model.layers.38.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 51464 |
"model.layers.38.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 51465 |
+
"model.layers.38.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 51466 |
+
"model.layers.38.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 51467 |
+
"model.layers.38.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 51468 |
+
"model.layers.38.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 51469 |
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 51470 |
"model.layers.38.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 51471 |
"model.layers.38.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 53022 |
"model.layers.39.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 53023 |
"model.layers.39.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 53024 |
"model.layers.39.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 53025 |
+
"model.layers.39.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 53026 |
+
"model.layers.39.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 53027 |
+
"model.layers.39.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 53028 |
+
"model.layers.39.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 53029 |
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 53030 |
"model.layers.39.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 53031 |
"model.layers.39.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 54582 |
"model.layers.4.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 54583 |
"model.layers.4.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 54584 |
"model.layers.4.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 54585 |
+
"model.layers.4.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 54586 |
+
"model.layers.4.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 54587 |
+
"model.layers.4.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 54588 |
+
"model.layers.4.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 54589 |
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 54590 |
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 54591 |
"model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 56142 |
"model.layers.40.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 56143 |
"model.layers.40.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 56144 |
"model.layers.40.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 56145 |
+
"model.layers.40.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 56146 |
+
"model.layers.40.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 56147 |
+
"model.layers.40.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 56148 |
+
"model.layers.40.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 56149 |
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 56150 |
"model.layers.40.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 56151 |
"model.layers.40.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 57702 |
"model.layers.41.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 57703 |
"model.layers.41.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 57704 |
"model.layers.41.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 57705 |
+
"model.layers.41.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 57706 |
+
"model.layers.41.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 57707 |
+
"model.layers.41.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 57708 |
+
"model.layers.41.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 57709 |
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 57710 |
"model.layers.41.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 57711 |
"model.layers.41.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 59262 |
"model.layers.42.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 59263 |
"model.layers.42.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 59264 |
"model.layers.42.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 59265 |
+
"model.layers.42.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 59266 |
+
"model.layers.42.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 59267 |
+
"model.layers.42.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 59268 |
+
"model.layers.42.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 59269 |
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 59270 |
"model.layers.42.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 59271 |
"model.layers.42.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 60822 |
"model.layers.43.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 60823 |
"model.layers.43.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 60824 |
"model.layers.43.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 60825 |
+
"model.layers.43.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 60826 |
+
"model.layers.43.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 60827 |
+
"model.layers.43.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 60828 |
+
"model.layers.43.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 60829 |
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 60830 |
"model.layers.43.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 60831 |
"model.layers.43.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 62382 |
"model.layers.44.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 62383 |
"model.layers.44.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 62384 |
"model.layers.44.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 62385 |
+
"model.layers.44.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 62386 |
+
"model.layers.44.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 62387 |
+
"model.layers.44.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 62388 |
+
"model.layers.44.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 62389 |
"model.layers.44.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 62390 |
"model.layers.44.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 62391 |
"model.layers.44.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 63942 |
"model.layers.45.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 63943 |
"model.layers.45.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 63944 |
"model.layers.45.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 63945 |
+
"model.layers.45.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 63946 |
+
"model.layers.45.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 63947 |
+
"model.layers.45.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 63948 |
+
"model.layers.45.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 63949 |
"model.layers.45.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 63950 |
"model.layers.45.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 63951 |
"model.layers.45.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 65502 |
"model.layers.46.mlp.experts.99.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65503 |
"model.layers.46.mlp.experts.99.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65504 |
"model.layers.46.mlp.experts.99.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65505 |
+
"model.layers.46.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 65506 |
+
"model.layers.46.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 65507 |
+
"model.layers.46.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 65508 |
+
"model.layers.46.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 65509 |
"model.layers.46.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 65510 |
"model.layers.46.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 65511 |
"model.layers.46.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 65550 |
"model.layers.47.mlp.experts.1.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65551 |
"model.layers.47.mlp.experts.1.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65552 |
"model.layers.47.mlp.experts.1.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65553 |
+
"model.layers.47.mlp.experts.10.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65554 |
+
"model.layers.47.mlp.experts.10.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65555 |
+
"model.layers.47.mlp.experts.10.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65556 |
+
"model.layers.47.mlp.experts.10.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 65557 |
+
"model.layers.47.mlp.experts.10.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65558 |
+
"model.layers.47.mlp.experts.10.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65559 |
+
"model.layers.47.mlp.experts.10.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65560 |
+
"model.layers.47.mlp.experts.10.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 65561 |
+
"model.layers.47.mlp.experts.10.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65562 |
+
"model.layers.47.mlp.experts.10.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65563 |
+
"model.layers.47.mlp.experts.10.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65564 |
+
"model.layers.47.mlp.experts.10.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65565 |
"model.layers.47.mlp.experts.100.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65566 |
"model.layers.47.mlp.experts.100.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65567 |
"model.layers.47.mlp.experts.100.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 65682 |
"model.layers.47.mlp.experts.109.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65683 |
"model.layers.47.mlp.experts.109.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 65684 |
"model.layers.47.mlp.experts.109.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 65685 |
+
"model.layers.47.mlp.experts.11.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65686 |
+
"model.layers.47.mlp.experts.11.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65687 |
+
"model.layers.47.mlp.experts.11.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65688 |
+
"model.layers.47.mlp.experts.11.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 65689 |
+
"model.layers.47.mlp.experts.11.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65690 |
+
"model.layers.47.mlp.experts.11.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65691 |
+
"model.layers.47.mlp.experts.11.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65692 |
+
"model.layers.47.mlp.experts.11.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 65693 |
+
"model.layers.47.mlp.experts.11.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65694 |
+
"model.layers.47.mlp.experts.11.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65695 |
+
"model.layers.47.mlp.experts.11.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65696 |
+
"model.layers.47.mlp.experts.11.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 65697 |
"model.layers.47.mlp.experts.110.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65698 |
"model.layers.47.mlp.experts.110.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65699 |
"model.layers.47.mlp.experts.110.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 65818 |
"model.layers.47.mlp.experts.12.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65819 |
"model.layers.47.mlp.experts.12.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 65820 |
"model.layers.47.mlp.experts.12.down_proj.scales": "model-00005-of-00005.safetensors",
|
| 65821 |
+
"model.layers.47.mlp.experts.12.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 65822 |
+
"model.layers.47.mlp.experts.12.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 65823 |
+
"model.layers.47.mlp.experts.12.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 65824 |
+
"model.layers.47.mlp.experts.12.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 65825 |
"model.layers.47.mlp.experts.12.up_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 65826 |
"model.layers.47.mlp.experts.12.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 65827 |
"model.layers.47.mlp.experts.12.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 66402 |
"model.layers.47.mlp.experts.49.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66403 |
"model.layers.47.mlp.experts.49.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66404 |
"model.layers.47.mlp.experts.49.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66405 |
+
"model.layers.47.mlp.experts.5.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66406 |
+
"model.layers.47.mlp.experts.5.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66407 |
+
"model.layers.47.mlp.experts.5.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66408 |
+
"model.layers.47.mlp.experts.5.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 66409 |
"model.layers.47.mlp.experts.5.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66410 |
"model.layers.47.mlp.experts.5.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66411 |
"model.layers.47.mlp.experts.5.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66412 |
"model.layers.47.mlp.experts.5.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66413 |
+
"model.layers.47.mlp.experts.5.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66414 |
+
"model.layers.47.mlp.experts.5.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66415 |
+
"model.layers.47.mlp.experts.5.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66416 |
+
"model.layers.47.mlp.experts.5.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 66417 |
"model.layers.47.mlp.experts.50.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66418 |
"model.layers.47.mlp.experts.50.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66419 |
"model.layers.47.mlp.experts.50.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 66534 |
"model.layers.47.mlp.experts.59.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66535 |
"model.layers.47.mlp.experts.59.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66536 |
"model.layers.47.mlp.experts.59.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66537 |
+
"model.layers.47.mlp.experts.6.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66538 |
+
"model.layers.47.mlp.experts.6.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66539 |
+
"model.layers.47.mlp.experts.6.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66540 |
+
"model.layers.47.mlp.experts.6.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 66541 |
+
"model.layers.47.mlp.experts.6.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66542 |
+
"model.layers.47.mlp.experts.6.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66543 |
+
"model.layers.47.mlp.experts.6.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66544 |
+
"model.layers.47.mlp.experts.6.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66545 |
+
"model.layers.47.mlp.experts.6.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66546 |
+
"model.layers.47.mlp.experts.6.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66547 |
+
"model.layers.47.mlp.experts.6.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66548 |
+
"model.layers.47.mlp.experts.6.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 66549 |
"model.layers.47.mlp.experts.60.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66550 |
"model.layers.47.mlp.experts.60.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66551 |
"model.layers.47.mlp.experts.60.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 66666 |
"model.layers.47.mlp.experts.69.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66667 |
"model.layers.47.mlp.experts.69.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66668 |
"model.layers.47.mlp.experts.69.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66669 |
+
"model.layers.47.mlp.experts.7.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66670 |
+
"model.layers.47.mlp.experts.7.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66671 |
+
"model.layers.47.mlp.experts.7.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66672 |
+
"model.layers.47.mlp.experts.7.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 66673 |
+
"model.layers.47.mlp.experts.7.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66674 |
+
"model.layers.47.mlp.experts.7.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66675 |
+
"model.layers.47.mlp.experts.7.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66676 |
+
"model.layers.47.mlp.experts.7.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66677 |
+
"model.layers.47.mlp.experts.7.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66678 |
+
"model.layers.47.mlp.experts.7.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66679 |
+
"model.layers.47.mlp.experts.7.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66680 |
+
"model.layers.47.mlp.experts.7.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 66681 |
"model.layers.47.mlp.experts.70.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66682 |
"model.layers.47.mlp.experts.70.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66683 |
"model.layers.47.mlp.experts.70.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 66798 |
"model.layers.47.mlp.experts.79.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66799 |
"model.layers.47.mlp.experts.79.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66800 |
"model.layers.47.mlp.experts.79.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66801 |
+
"model.layers.47.mlp.experts.8.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66802 |
+
"model.layers.47.mlp.experts.8.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66803 |
+
"model.layers.47.mlp.experts.8.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66804 |
+
"model.layers.47.mlp.experts.8.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 66805 |
+
"model.layers.47.mlp.experts.8.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66806 |
+
"model.layers.47.mlp.experts.8.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66807 |
+
"model.layers.47.mlp.experts.8.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66808 |
+
"model.layers.47.mlp.experts.8.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66809 |
+
"model.layers.47.mlp.experts.8.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66810 |
+
"model.layers.47.mlp.experts.8.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66811 |
+
"model.layers.47.mlp.experts.8.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66812 |
+
"model.layers.47.mlp.experts.8.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 66813 |
"model.layers.47.mlp.experts.80.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66814 |
"model.layers.47.mlp.experts.80.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66815 |
"model.layers.47.mlp.experts.80.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 66930 |
"model.layers.47.mlp.experts.89.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66931 |
"model.layers.47.mlp.experts.89.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 66932 |
"model.layers.47.mlp.experts.89.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 66933 |
+
"model.layers.47.mlp.experts.9.down_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66934 |
+
"model.layers.47.mlp.experts.9.down_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66935 |
+
"model.layers.47.mlp.experts.9.down_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66936 |
+
"model.layers.47.mlp.experts.9.down_proj.scales": "model-00004-of-00005.safetensors",
|
| 66937 |
+
"model.layers.47.mlp.experts.9.gate_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66938 |
+
"model.layers.47.mlp.experts.9.gate_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66939 |
+
"model.layers.47.mlp.experts.9.gate_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66940 |
+
"model.layers.47.mlp.experts.9.gate_proj.scales": "model-00004-of-00005.safetensors",
|
| 66941 |
+
"model.layers.47.mlp.experts.9.up_proj.g_idx": "model-00004-of-00005.safetensors",
|
| 66942 |
+
"model.layers.47.mlp.experts.9.up_proj.qweight": "model-00004-of-00005.safetensors",
|
| 66943 |
+
"model.layers.47.mlp.experts.9.up_proj.qzeros": "model-00004-of-00005.safetensors",
|
| 66944 |
+
"model.layers.47.mlp.experts.9.up_proj.scales": "model-00004-of-00005.safetensors",
|
| 66945 |
"model.layers.47.mlp.experts.90.down_proj.g_idx": "model-00005-of-00005.safetensors",
|
| 66946 |
"model.layers.47.mlp.experts.90.down_proj.qweight": "model-00005-of-00005.safetensors",
|
| 66947 |
"model.layers.47.mlp.experts.90.down_proj.qzeros": "model-00005-of-00005.safetensors",
|
|
|
|
| 67062 |
"model.layers.47.mlp.experts.99.up_proj.qweight": "model-00005-of-00005.safetensors",
|
| 67063 |
"model.layers.47.mlp.experts.99.up_proj.qzeros": "model-00005-of-00005.safetensors",
|
| 67064 |
"model.layers.47.mlp.experts.99.up_proj.scales": "model-00005-of-00005.safetensors",
|
| 67065 |
+
"model.layers.47.mlp.gate.g_idx": "model-00004-of-00005.safetensors",
|
| 67066 |
+
"model.layers.47.mlp.gate.qweight": "model-00004-of-00005.safetensors",
|
| 67067 |
+
"model.layers.47.mlp.gate.qzeros": "model-00004-of-00005.safetensors",
|
| 67068 |
+
"model.layers.47.mlp.gate.scales": "model-00004-of-00005.safetensors",
|
| 67069 |
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 67070 |
"model.layers.47.self_attn.k_norm.weight": "model-00004-of-00005.safetensors",
|
| 67071 |
"model.layers.47.self_attn.k_proj.g_idx": "model-00004-of-00005.safetensors",
|
|
|
|
| 68622 |
"model.layers.5.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 68623 |
"model.layers.5.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 68624 |
"model.layers.5.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 68625 |
+
"model.layers.5.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 68626 |
+
"model.layers.5.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 68627 |
+
"model.layers.5.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 68628 |
+
"model.layers.5.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 68629 |
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 68630 |
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 68631 |
"model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 70182 |
"model.layers.6.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 70183 |
"model.layers.6.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 70184 |
"model.layers.6.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 70185 |
+
"model.layers.6.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 70186 |
+
"model.layers.6.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 70187 |
+
"model.layers.6.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 70188 |
+
"model.layers.6.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 70189 |
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 70190 |
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 70191 |
"model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 71742 |
"model.layers.7.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 71743 |
"model.layers.7.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 71744 |
"model.layers.7.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 71745 |
+
"model.layers.7.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 71746 |
+
"model.layers.7.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 71747 |
+
"model.layers.7.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 71748 |
+
"model.layers.7.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 71749 |
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 71750 |
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 71751 |
"model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 73302 |
"model.layers.8.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 73303 |
"model.layers.8.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 73304 |
"model.layers.8.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 73305 |
+
"model.layers.8.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 73306 |
+
"model.layers.8.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 73307 |
+
"model.layers.8.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 73308 |
+
"model.layers.8.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 73309 |
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 73310 |
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 73311 |
"model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
|
|
|
| 74862 |
"model.layers.9.mlp.experts.99.up_proj.qweight": "model-00001-of-00005.safetensors",
|
| 74863 |
"model.layers.9.mlp.experts.99.up_proj.qzeros": "model-00001-of-00005.safetensors",
|
| 74864 |
"model.layers.9.mlp.experts.99.up_proj.scales": "model-00001-of-00005.safetensors",
|
| 74865 |
+
"model.layers.9.mlp.gate.g_idx": "model-00001-of-00005.safetensors",
|
| 74866 |
+
"model.layers.9.mlp.gate.qweight": "model-00001-of-00005.safetensors",
|
| 74867 |
+
"model.layers.9.mlp.gate.qzeros": "model-00001-of-00005.safetensors",
|
| 74868 |
+
"model.layers.9.mlp.gate.scales": "model-00001-of-00005.safetensors",
|
| 74869 |
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
| 74870 |
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00005.safetensors",
|
| 74871 |
"model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00005.safetensors",
|
quantize_config.json
CHANGED
|
@@ -9,13 +9,15 @@
|
|
| 9 |
"pack_dtype": "int32",
|
| 10 |
"meta": {
|
| 11 |
"quantizer": [
|
| 12 |
-
"gptqmodel:
|
| 13 |
],
|
| 14 |
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
-
"damp_percent": 0.
|
| 16 |
-
"damp_auto_increment": 0.
|
| 17 |
"static_groups": false,
|
| 18 |
"true_sequential": true,
|
| 19 |
-
"mse": 0.0
|
|
|
|
|
|
|
| 20 |
}
|
| 21 |
}
|
|
|
|
| 9 |
"pack_dtype": "int32",
|
| 10 |
"meta": {
|
| 11 |
"quantizer": [
|
| 12 |
+
"gptqmodel:4.0.0-dev"
|
| 13 |
],
|
| 14 |
"uri": "https://github.com/modelcloud/gptqmodel",
|
| 15 |
+
"damp_percent": 0.05,
|
| 16 |
+
"damp_auto_increment": 0.01,
|
| 17 |
"static_groups": false,
|
| 18 |
"true_sequential": true,
|
| 19 |
+
"mse": 0.0,
|
| 20 |
+
"v2": false,
|
| 21 |
+
"v2_alpha": 0.25
|
| 22 |
}
|
| 23 |
}
|