Quant for 3.75
Browse files- README.md +309 -38
- SYSTEM_PROMPT.txt +18 -0
- config.json +36 -0
- generation_config.json +6 -0
- model.safetensors.index.json +802 -0
- output-00001-of-00007.safetensors +3 -0
- output-00002-of-00007.safetensors +3 -0
- output-00003-of-00007.safetensors +3 -0
- output-00004-of-00007.safetensors +3 -0
- output-00005-of-00007.safetensors +3 -0
- output-00006-of-00007.safetensors +3 -0
- output-00007-of-00007.safetensors +3 -0
- params.json +11 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer.model.v7 +0 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
|
@@ -119,73 +119,344 @@ extra_gated_description: >-
|
|
| 119 |
Mistral AI processes your personal data below to provide the model and enforce its license. If you are affiliated with a commercial entity, we may also send you communications about our models. For more information on your rights and data handling, please see our <a href="https://mistral.ai/terms/">privacy policy</a>.
|
| 120 |
extra_gated_button_content: Submit
|
| 121 |
library_name: vllm
|
| 122 |
-
quantized_by: bartowski
|
| 123 |
-
pipeline_tag: text-generation
|
| 124 |
---
|
| 125 |
|
| 126 |
-
|
| 127 |
|
| 128 |
-
|
| 129 |
|
| 130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
-
|
|
|
|
|
|
|
|
|
|
| 133 |
|
| 134 |
-
|
| 135 |
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
|
|
|
|
| 140 |
|
| 141 |
-
|
| 142 |
|
| 143 |
-
|
| 144 |
|
| 145 |
-
|
| 146 |
|
| 147 |
-
|
| 148 |
|
| 149 |
-
|
| 150 |
|
| 151 |
-
|
|
|
|
| 152 |
|
| 153 |
-
|
| 154 |
|
|
|
|
| 155 |
|
| 156 |
-
|
|
|
|
|
|
|
| 157 |
|
| 158 |
-
|
| 159 |
|
| 160 |
-
```
|
| 161 |
-
|
| 162 |
```
|
| 163 |
|
| 164 |
-
|
| 165 |
|
| 166 |
-
|
| 167 |
-
|
| 168 |
-
|
|
|
|
|
|
|
| 169 |
|
| 170 |
-
To download the `main` (only useful if you only care about measurement.json) branch to a folder called `Mistral-Large-Instruct-2411-exl2`:
|
| 171 |
|
| 172 |
-
```shell
|
| 173 |
-
mkdir Mistral-Large-Instruct-2411-exl2
|
| 174 |
-
huggingface-cli download bartowski/Mistral-Large-Instruct-2411-exl2 --local-dir Mistral-Large-Instruct-2411-exl2
|
| 175 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 176 |
|
| 177 |
-
To download from a different branch, add the `--revision` parameter:
|
| 178 |
|
| 179 |
-
|
| 180 |
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
```
|
| 185 |
|
| 186 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 187 |
|
| 188 |
-
```shell
|
| 189 |
-
mkdir Mistral-Large-Instruct-2411-exl2-6.5
|
| 190 |
-
huggingface-cli download bartowski/Mistral-Large-Instruct-2411-exl2 --revision 6_5 --local-dir Mistral-Large-Instruct-2411-exl2-6.5
|
| 191 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
Mistral AI processes your personal data below to provide the model and enforce its license. If you are affiliated with a commercial entity, we may also send you communications about our models. For more information on your rights and data handling, please see our <a href="https://mistral.ai/terms/">privacy policy</a>.
|
| 120 |
extra_gated_button_content: Submit
|
| 121 |
library_name: vllm
|
|
|
|
|
|
|
| 122 |
---
|
| 123 |
|
| 124 |
+
# Model Card for Mistral-Large-Instruct-2411
|
| 125 |
|
| 126 |
+
Mistral-Large-Instruct-2411 is an advanced dense Large Language Model (LLM) of 123B parameters with state-of-the-art reasoning, knowledge and coding capabilities extending [Mistral-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407) with better Long Context, Function Calling and System Prompt.
|
| 127 |
|
| 128 |
+
## Key features
|
| 129 |
+
- **Multi-lingual by design:** Dozens of languages supported, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch and Polish.
|
| 130 |
+
- **Proficient in coding:** Trained on 80+ coding languages such as Python, Java, C, C++, Javacsript, and Bash. Also trained on more specific languages such as Swift and Fortran.
|
| 131 |
+
- **Agent-centric:** Best-in-class agentic capabilities with native function calling and JSON outputting.
|
| 132 |
+
- **Advanced Reasoning:** State-of-the-art mathematical and reasoning capabilities.
|
| 133 |
+
- **Mistral Research License:** Allows usage and modification for non-commercial usages.
|
| 134 |
+
- **Large Context:** A large 128k context window.
|
| 135 |
+
- **Robust Context Adherence:** Ensures strong adherence for RAG and large context applications.
|
| 136 |
+
- **System Prompt:** Maintains strong adherence and support for more reliable system prompts.
|
| 137 |
|
| 138 |
+
### System Prompt
|
| 139 |
+
We appreciate the feedback received from our community regarding our system prompt handling.
|
| 140 |
+
In response, we have implemented stronger support for system prompts.
|
| 141 |
+
To achieve optimal results, we recommend always including a system prompt that clearly outlines the bot's purpose, even if it is minimal.
|
| 142 |
|
| 143 |
+
### Basic Instruct Template (V7)
|
| 144 |
|
| 145 |
+
```
|
| 146 |
+
<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]
|
| 147 |
+
```
|
| 148 |
|
| 149 |
+
**Be careful with subtle missing or trailing white spaces!**
|
| 150 |
|
| 151 |
+
*Please make sure to use [mistral-common](https://github.com/mistralai/mistral-common) as the source of truth*
|
| 152 |
|
| 153 |
+
## Usage
|
| 154 |
|
| 155 |
+
The model can be used with the following frameworks
|
| 156 |
|
| 157 |
+
- [`vllm`](https://github.com/vllm-project/vllm): See [here](#vLLM)
|
| 158 |
|
| 159 |
+
### vLLM
|
| 160 |
|
| 161 |
+
We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
|
| 162 |
+
to implement production-ready inference pipelines.
|
| 163 |
|
| 164 |
+
**_Installation_**
|
| 165 |
|
| 166 |
+
Make sure you install [`vLLM >= v0.6.4.post1`](https://github.com/vllm-project/vllm/releases/tag/v0.6.4.post1):
|
| 167 |
|
| 168 |
+
```
|
| 169 |
+
pip install --upgrade vllm
|
| 170 |
+
```
|
| 171 |
|
| 172 |
+
Also make sure you have [`mistral_common >= 1.5.0`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.0) installed:
|
| 173 |
|
| 174 |
+
```
|
| 175 |
+
pip install --upgrade mistral_common
|
| 176 |
```
|
| 177 |
|
| 178 |
+
You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-55a88146a4da0b6e193431b5b1d3492dfd7bebdc16919df4d031273e85a6157c?context=explore).
|
| 179 |
|
| 180 |
+
### Server
|
| 181 |
+
|
| 182 |
+
We recommand that you use Mistral-Large-Instruct-2411 in a server/client setting.
|
| 183 |
+
|
| 184 |
+
1. Spin up a server:
|
| 185 |
|
|
|
|
| 186 |
|
|
|
|
|
|
|
|
|
|
| 187 |
```
|
| 188 |
+
vllm serve mistralai/Mistral-Large-Instruct-2411 --tokenizer_mode mistral --config_format mistral --load_format mistral --tensor_parallel_size 8
|
| 189 |
+
```
|
| 190 |
+
|
| 191 |
+
**Note:** Running Mistral-Large-Instruct-2411 on GPU requires over 300 GB of GPU RAM.
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
2. To ping the client you can use a simple Python snippet.
|
| 195 |
+
|
| 196 |
+
```py
|
| 197 |
+
import requests
|
| 198 |
+
import json
|
| 199 |
+
from huggingface_hub import hf_hub_download
|
| 200 |
+
from datetime import datetime, timedelta
|
| 201 |
+
|
| 202 |
+
url = "http://<your-server>:8000/v1/chat/completions"
|
| 203 |
+
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
|
| 204 |
+
|
| 205 |
+
model = "mistralai/Mistral-Large-Instruct-2411"
|
| 206 |
+
|
| 207 |
+
|
| 208 |
+
def load_system_prompt(repo_id: str, filename: str) -> str:
|
| 209 |
+
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
|
| 210 |
+
with open(file_path, "r") as file:
|
| 211 |
+
system_prompt = file.read()
|
| 212 |
+
today = datetime.today().strftime("%Y-%m-%d")
|
| 213 |
+
yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
|
| 214 |
+
model_name = repo_id.split("/")[-1]
|
| 215 |
+
return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
|
| 216 |
|
|
|
|
| 217 |
|
| 218 |
+
SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
|
| 219 |
|
| 220 |
+
|
| 221 |
+
messages = [
|
| 222 |
+
{"role": "system", "content": SYSTEM_PROMPT + "\n\nThink step by step. You're a math genius."},
|
| 223 |
+
{
|
| 224 |
+
"role": "user",
|
| 225 |
+
"content": "Think of four random numbers. Then add, substract or multiply them so that the solution is 10. If it's not possible, say it."
|
| 226 |
+
},
|
| 227 |
+
]
|
| 228 |
+
|
| 229 |
+
data = {"model": model, "messages": messages}
|
| 230 |
+
|
| 231 |
+
response = requests.post(url, headers=headers, data=json.dumps(data))
|
| 232 |
+
print(response.json()["choices"][0]["message"]["content"])
|
| 233 |
+
# Sure, let's start by thinking of four random numbers. For example, let's take 3, 5, 2, and 1.
|
| 234 |
+
#
|
| 235 |
+
# Now, we need to find a combination of addition, subtraction, or multiplication that results in 10.
|
| 236 |
+
|
| 237 |
+
# Let's try:
|
| 238 |
+
|
| 239 |
+
# \[ 3 + 5 + 2 - 1 = 9 \]
|
| 240 |
+
|
| 241 |
+
# This doesn't work. Let's try another combination:
|
| 242 |
+
|
| 243 |
+
# \[ 3 \times 2 + 5 - 1 = 6 + 5 - 1 = 10 \]
|
| 244 |
+
|
| 245 |
+
# This works! So, with the numbers 3, 5, 2, and 1, we can achieve the result 10 by performing the operations \( 3 \times 2 + 5 - 1 \).
|
| 246 |
+
```
|
| 247 |
+
|
| 248 |
+
### Offline
|
| 249 |
+
|
| 250 |
+
```py
|
| 251 |
+
from vllm import LLM
|
| 252 |
+
from vllm.sampling_params import SamplingParams
|
| 253 |
+
from huggingface_hub import hf_hub_download
|
| 254 |
+
from datetime import datetime, timedelta
|
| 255 |
+
|
| 256 |
+
model_name = "mistralai/Mistral-Large-Instruct-2411"
|
| 257 |
+
|
| 258 |
+
def load_system_prompt(repo_id: str, filename: str) -> str:
|
| 259 |
+
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
|
| 260 |
+
with open(file_path, 'r') as file:
|
| 261 |
+
system_prompt = file.read()
|
| 262 |
+
today = datetime.today().strftime('%Y-%m-%d')
|
| 263 |
+
yesterday = (datetime.today() - timedelta(days=1)).strftime('%Y-%m-%d')
|
| 264 |
+
model_name = repo_id.split("/")[-1]
|
| 265 |
+
return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
|
| 266 |
+
|
| 267 |
+
|
| 268 |
+
SYSTEM_PROMPT = load_system_prompt(model_name, "SYSTEM_PROMPT.txt") + "\n\nThink step by step. You're a math genius."
|
| 269 |
+
|
| 270 |
+
user_prompt = "Without browsing the web, how many days ago was Mistral founded?"
|
| 271 |
+
|
| 272 |
+
messages = [
|
| 273 |
+
{
|
| 274 |
+
"role": "system",
|
| 275 |
+
"content": SYSTEM_PROMPT
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"role": "user",
|
| 279 |
+
"content": user_prompt
|
| 280 |
+
},
|
| 281 |
+
]
|
| 282 |
+
|
| 283 |
+
# note that running this model on GPU requires over 300 GB of GPU RAM
|
| 284 |
+
llm = LLM(model=model_name, tokenizer_mode="mistral", tensor_parallel_size=8)
|
| 285 |
+
|
| 286 |
+
sampling_params = SamplingParams(max_tokens=512)
|
| 287 |
+
|
| 288 |
+
outputs = llm.chat(messages, sampling_params=sampling_params)
|
| 289 |
+
|
| 290 |
+
print(outputs[0].outputs[0].text)
|
| 291 |
+
# I don't have real-time web browsing capabilities or access to current data, but I can help you calculate the number of days based on the information I have.
|
| 292 |
+
#
|
| 293 |
+
#Mistral AI was founded in April 2023. To determine how many days ago that was from today's date, November 18, 2024, we need to calculate the total number of days between April 2023 and November 2024.
|
| 294 |
+
#
|
| 295 |
+
#Here's the step-by-step calculation:
|
| 296 |
+
#
|
| 297 |
+
#1. **Days from April 2023 to December 2023:**
|
| 298 |
+
# - April 2023: 30 days (April has 30 days)
|
| 299 |
+
# - May 2023: 31 days
|
| 300 |
+
# - June 2023: 30 days
|
| 301 |
+
# - July 2023: 31 days
|
| 302 |
+
# - August 2023: 31 days
|
| 303 |
+
# - September 2023: 30 days
|
| 304 |
+
# - October 2023: 31 days
|
| 305 |
+
# - November 2023: 30 days
|
| 306 |
+
# - December 2023: 31 days
|
| 307 |
+
#
|
| 308 |
+
# Total days in 2023 from April to December = 30 + 31 + 30 + 31 + 31 + 30 + 31 + 30 + 31 = 275 days
|
| 309 |
+
#
|
| 310 |
+
#2. **Days from January 2024 to November 18, 2024:**
|
| 311 |
+
# - January 2024: 31 days
|
| 312 |
+
# - February 2024: 29 days (2024 is a leap year)
|
| 313 |
+
# - March 2024: 31 days
|
| 314 |
+
# - April 2024: 30 days
|
| 315 |
+
# - May 2024: 31 days
|
| 316 |
+
# - June 2024: 30 days
|
| 317 |
+
# - July 2024: 31 days
|
| 318 |
+
# - August 2024: 31 days
|
| 319 |
+
# - September 2024: 30 days
|
| 320 |
+
# - October 2024: 31 days
|
| 321 |
+
# - November 2024 (up to the 18th): 18 days
|
| 322 |
+
#
|
| 323 |
+
# Total days in 2024 from January to November 18 = 31 + 29 + 31 + 30 + 31 + 30 + 31 + 31 + 30 + 31 + 18 = 323 days
|
| 324 |
+
#
|
| 325 |
+
#3. **Total days from April 2023 to November 18, 2024:**
|
| 326 |
+
# Total days = 275 days (2023) + 323 days (2024) = 598 days
|
| 327 |
+
#
|
| 328 |
+
#Therefore, Mistral AI was founded 598 days ago from today's date, November 18, 2024.
|
| 329 |
```
|
| 330 |
|
| 331 |
+
### Improved Function Calling
|
| 332 |
+
|
| 333 |
+
Mistral-Large-2411 has much improved function calling capabilities that are fully supported
|
| 334 |
+
using [`mistral_common >= 1.5.0`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.0) and [`vLLM >= v0.6.4.post1`](https://github.com/vllm-project/vllm/releases/tag/v0.6.4.post1).
|
| 335 |
+
|
| 336 |
+
Make sure to serve the model with the following flags in vLLM:
|
| 337 |
|
|
|
|
|
|
|
|
|
|
| 338 |
```
|
| 339 |
+
vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --tensor-parallel-size 8 --tool-call-parser mistral --enable-auto-tool-choice
|
| 340 |
+
```
|
| 341 |
+
|
| 342 |
+
<details>
|
| 343 |
+
<summary>Example</summary>
|
| 344 |
+
|
| 345 |
+
```py
|
| 346 |
+
import requests
|
| 347 |
+
import json
|
| 348 |
+
from huggingface_hub import hf_hub_download
|
| 349 |
+
from datetime import datetime, timedelta
|
| 350 |
+
|
| 351 |
+
url = "http://<your-server>:8000/v1/chat/completions"
|
| 352 |
+
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
|
| 353 |
+
|
| 354 |
+
model = "mistralai/Mistral-Large-Instruct-2411"
|
| 355 |
+
|
| 356 |
+
|
| 357 |
+
def load_system_prompt(repo_id: str, filename: str) -> str:
|
| 358 |
+
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
|
| 359 |
+
with open(file_path, "r") as file:
|
| 360 |
+
system_prompt = file.read()
|
| 361 |
+
today = datetime.today().strftime("%Y-%m-%d")
|
| 362 |
+
yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
|
| 363 |
+
model_name = repo_id.split("/")[-1]
|
| 364 |
+
return system_prompt.format(name=model_name, today=today, yesterday=yesterday)
|
| 365 |
+
|
| 366 |
+
|
| 367 |
+
SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
|
| 368 |
+
|
| 369 |
+
|
| 370 |
+
tools = [
|
| 371 |
+
{
|
| 372 |
+
"type": "function",
|
| 373 |
+
"function": {
|
| 374 |
+
"name": "get_current_weather",
|
| 375 |
+
"description": "Get the current weather in a given location",
|
| 376 |
+
"parameters": {
|
| 377 |
+
"type": "object",
|
| 378 |
+
"properties": {
|
| 379 |
+
"city": {
|
| 380 |
+
"type": "string",
|
| 381 |
+
"description": "The city to find the weather for, e.g. 'San Francisco'",
|
| 382 |
+
},
|
| 383 |
+
"state": {
|
| 384 |
+
"type": "string",
|
| 385 |
+
"description": "The state abbreviation, e.g. 'CA' for California",
|
| 386 |
+
},
|
| 387 |
+
"unit": {
|
| 388 |
+
"type": "string",
|
| 389 |
+
"description": "The unit for temperature",
|
| 390 |
+
"enum": ["celsius", "fahrenheit"],
|
| 391 |
+
},
|
| 392 |
+
},
|
| 393 |
+
"required": ["city", "state", "unit"],
|
| 394 |
+
},
|
| 395 |
+
},
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"type": "function",
|
| 399 |
+
"function": {
|
| 400 |
+
"name": "rewrite",
|
| 401 |
+
"description": "Rewrite a given text for improved clarity",
|
| 402 |
+
"parameters": {
|
| 403 |
+
"type": "object",
|
| 404 |
+
"properties": {
|
| 405 |
+
"text": {
|
| 406 |
+
"type": "string",
|
| 407 |
+
"description": "The input text to rewrite",
|
| 408 |
+
}
|
| 409 |
+
},
|
| 410 |
+
},
|
| 411 |
+
},
|
| 412 |
+
},
|
| 413 |
+
]
|
| 414 |
+
|
| 415 |
+
messages = [
|
| 416 |
+
{"role": "system", "content": SYSTEM_PROMPT},
|
| 417 |
+
{
|
| 418 |
+
"role": "user",
|
| 419 |
+
"content": "Could you please make the below article more concise?\n\nOpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership.",
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"role": "assistant",
|
| 423 |
+
"content": "",
|
| 424 |
+
"tool_calls": [
|
| 425 |
+
{
|
| 426 |
+
"id": "bbc5b7ede",
|
| 427 |
+
"type": "function",
|
| 428 |
+
"function": {
|
| 429 |
+
"name": "rewrite",
|
| 430 |
+
"arguments": '{"text": "OpenAI is an artificial intelligence research laboratory consisting of the non-profit OpenAI Incorporated and its for-profit subsidiary corporation OpenAI Limited Partnership."}',
|
| 431 |
+
},
|
| 432 |
+
}
|
| 433 |
+
],
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"role": "tool",
|
| 437 |
+
"content": '{"action":"rewrite","outcome":"OpenAI is a FOR-profit company."}',
|
| 438 |
+
"tool_call_id": "bbc5b7ede",
|
| 439 |
+
"name": "rewrite",
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"role": "assistant",
|
| 443 |
+
"content": "---\n\nOpenAI is a FOR-profit company.",
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"role": "user",
|
| 447 |
+
"content": "Can you tell me what the temperature will be in Dallas, in Fahrenheit?",
|
| 448 |
+
},
|
| 449 |
+
]
|
| 450 |
+
|
| 451 |
+
data = {"model": model, "messages": messages, "tools": tools}
|
| 452 |
+
|
| 453 |
+
response = requests.post(url, headers=headers, data=json.dumps(data))
|
| 454 |
+
print(response.json()["choices"][0]["message"]["tool_calls"])
|
| 455 |
+
# [{'id': '8PdihwL6d', 'type': 'function', 'function': {'name': 'get_current_weather', 'arguments': '{"city": "Dallas", "state": "TX", "unit": "fahrenheit"}'}}]
|
| 456 |
+
```
|
| 457 |
+
|
| 458 |
+
</details>
|
| 459 |
+
|
| 460 |
+
## The Mistral AI Team
|
| 461 |
+
|
| 462 |
+
Albert Jiang, Alexandre Sablayrolles, Alexis Tacnet, Alok Kothari, Antoine Roux, Arthur Mensch, Audrey Herblin-Stoop, Augustin Garreau, Austin Birky, Bam4d, Baptiste Bout, Baudouin de Monicault, Blanche Savary, Carole Rambaud, Caroline Feldman, Devendra Singh Chaplot, Diego de las Casas, Diogo Costa, Eleonore Arcelin, Emma Bou Hanna, Etienne Metzger, Gaspard Blanchet, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Harizo Rajaona, Henri Roussez, Hichem Sattouf, Ian Mack, Jean-Malo Delignon, Jessica Chudnovsky, Justus Murke, Kartik Khandelwal, Lawrence Stewart, Louis Martin, Louis Ternon, Lucile Saulnier, Lélio Renard Lavaud, Margaret Jennings, Marie Pellat, Marie Torelli, Marie-Anne Lachaux, Marjorie Janiewicz, Mickaël Seznec, Nicolas Schuhl, Niklas Muhs, Olivier de Garrigues, Patrick von Platen, Paul Jacob, Pauline Buche, Pavan Kumar Reddy, Perry Savas, Pierre Stock, Romain Sauvestre, Sagar Vaze, Sandeep Subramanian, Saurabh Garg, Sophia Yang, Szymon Antoniak, Teven Le Scao, Thibault Schueller, Thibaut Lavril, Thomas Wang, Théophile Gervet, Timothée Lacroix, Valera Nemychnikova, Wendy Shang, William El Sayed, William Marshall
|
SYSTEM_PROMPT.txt
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
You are {name}, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.
|
| 2 |
+
You power an AI assistant called Le Chat.
|
| 3 |
+
Your knowledge base was last updated on 2023-10-01.
|
| 4 |
+
The current date is {today}.
|
| 5 |
+
|
| 6 |
+
When you're not sure about some information, you say that you don't have the information and don't make up anything.
|
| 7 |
+
If the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. "What are some good restaurants around me?" => "Where are you?" or "When is the next flight to Tokyo" => "Where do you travel from?").
|
| 8 |
+
You are always very attentive to dates, in particular you try to resolve dates (e.g. "yesterday" is {yesterday}) and when asked about information at specific dates, you discard information that is at another date.
|
| 9 |
+
You follow these instructions in all languages, and always respond to the user in the language they use or request.
|
| 10 |
+
Next sections describe the capabilities that you have.
|
| 11 |
+
|
| 12 |
+
# WEB BROWSING INSTRUCTIONS
|
| 13 |
+
|
| 14 |
+
You cannot perform any web search or access internet to open URLs, links etc. If it seems like the user is expecting you to do so, you clarify the situation and ask the user to copy paste the text directly in the chat.
|
| 15 |
+
|
| 16 |
+
# MULTI-MODAL INSTRUCTIONS
|
| 17 |
+
|
| 18 |
+
You do not have any multimodal capability, in particular you cannot read nor generate images, or transcribe audio files or videos.
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 12288,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 28672,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 96,
|
| 16 |
+
"num_hidden_layers": 88,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"transformers_version": "4.46.2",
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 32768,
|
| 25 |
+
"quantization_config": {
|
| 26 |
+
"quant_method": "exl2",
|
| 27 |
+
"version": "0.2.4",
|
| 28 |
+
"bits": 3.75,
|
| 29 |
+
"head_bits": 6,
|
| 30 |
+
"calibration": {
|
| 31 |
+
"rows": 115,
|
| 32 |
+
"length": 2048,
|
| 33 |
+
"dataset": "(default)"
|
| 34 |
+
}
|
| 35 |
+
}
|
| 36 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.46.2"
|
| 6 |
+
}
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,802 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 245220139008
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00051-of-00051.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00051.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00051.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00051.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00051.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00051.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00051.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00051.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00051.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00051.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00051.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00051.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00007-of-00051.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00007-of-00051.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00007-of-00051.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00007-of-00051.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00051.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00051.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00007-of-00051.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00007-of-00051.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00007-of-00051.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00007-of-00051.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00008-of-00051.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00008-of-00051.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00008-of-00051.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00009-of-00051.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00008-of-00051.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00008-of-00051.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00008-of-00051.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00008-of-00051.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00008-of-00051.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00008-of-00051.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00009-of-00051.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00009-of-00051.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00009-of-00051.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00009-of-00051.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00010-of-00051.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00009-of-00051.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00009-of-00051.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00009-of-00051.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00009-of-00051.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00009-of-00051.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00010-of-00051.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00010-of-00051.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00010-of-00051.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00010-of-00051.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00010-of-00051.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00011-of-00051.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00010-of-00051.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00010-of-00051.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00010-of-00051.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00010-of-00051.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00011-of-00051.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00011-of-00051.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00011-of-00051.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00011-of-00051.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00011-of-00051.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00011-of-00051.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00011-of-00051.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00011-of-00051.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00011-of-00051.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00012-of-00051.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00012-of-00051.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00012-of-00051.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00051.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00051.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00051.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00051.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00051.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00013-of-00051.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00012-of-00051.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00012-of-00051.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00012-of-00051.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00012-of-00051.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00012-of-00051.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00012-of-00051.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00013-of-00051.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00013-of-00051.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00013-of-00051.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00013-of-00051.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00014-of-00051.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00013-of-00051.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00013-of-00051.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00013-of-00051.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00013-of-00051.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00013-of-00051.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00014-of-00051.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00014-of-00051.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00014-of-00051.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00014-of-00051.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00014-of-00051.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00015-of-00051.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00014-of-00051.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00014-of-00051.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00014-of-00051.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00014-of-00051.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00015-of-00051.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00015-of-00051.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00015-of-00051.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00015-of-00051.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00015-of-00051.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00015-of-00051.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00015-of-00051.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00015-of-00051.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00015-of-00051.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00016-of-00051.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00016-of-00051.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00016-of-00051.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00017-of-00051.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00016-of-00051.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00016-of-00051.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00016-of-00051.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00016-of-00051.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00016-of-00051.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00016-of-00051.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00017-of-00051.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00017-of-00051.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00017-of-00051.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00017-of-00051.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00018-of-00051.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00017-of-00051.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00017-of-00051.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00017-of-00051.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00017-of-00051.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00017-of-00051.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00003-of-00051.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00051.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00051.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00051.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00051.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00018-of-00051.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00018-of-00051.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00018-of-00051.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00018-of-00051.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00018-of-00051.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00019-of-00051.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00018-of-00051.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00018-of-00051.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00018-of-00051.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00018-of-00051.safetensors",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "model-00019-of-00051.safetensors",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "model-00019-of-00051.safetensors",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00019-of-00051.safetensors",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "model-00019-of-00051.safetensors",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00019-of-00051.safetensors",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00019-of-00051.safetensors",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00019-of-00051.safetensors",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00019-of-00051.safetensors",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00019-of-00051.safetensors",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "model-00020-of-00051.safetensors",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "model-00020-of-00051.safetensors",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00020-of-00051.safetensors",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "model-00021-of-00051.safetensors",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00020-of-00051.safetensors",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "model-00020-of-00051.safetensors",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00020-of-00051.safetensors",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00020-of-00051.safetensors",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00020-of-00051.safetensors",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00020-of-00051.safetensors",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "model-00021-of-00051.safetensors",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "model-00021-of-00051.safetensors",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "model-00021-of-00051.safetensors",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00021-of-00051.safetensors",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "model-00022-of-00051.safetensors",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00021-of-00051.safetensors",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00021-of-00051.safetensors",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00021-of-00051.safetensors",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00021-of-00051.safetensors",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00021-of-00051.safetensors",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "model-00022-of-00051.safetensors",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "model-00022-of-00051.safetensors",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00022-of-00051.safetensors",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "model-00022-of-00051.safetensors",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00022-of-00051.safetensors",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "model-00023-of-00051.safetensors",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00022-of-00051.safetensors",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00022-of-00051.safetensors",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00022-of-00051.safetensors",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00022-of-00051.safetensors",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "model-00023-of-00051.safetensors",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "model-00023-of-00051.safetensors",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00023-of-00051.safetensors",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "model-00023-of-00051.safetensors",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00023-of-00051.safetensors",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00023-of-00051.safetensors",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00023-of-00051.safetensors",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00023-of-00051.safetensors",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00023-of-00051.safetensors",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "model-00003-of-00051.safetensors",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00051.safetensors",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00051.safetensors",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00051.safetensors",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00051.safetensors",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00051.safetensors",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00051.safetensors",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00051.safetensors",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00051.safetensors",
|
| 323 |
+
"model.layers.40.input_layernorm.weight": "model-00024-of-00051.safetensors",
|
| 324 |
+
"model.layers.40.mlp.down_proj.weight": "model-00024-of-00051.safetensors",
|
| 325 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
|
| 326 |
+
"model.layers.40.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
|
| 327 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00024-of-00051.safetensors",
|
| 328 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
|
| 329 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
|
| 330 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
|
| 331 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
|
| 332 |
+
"model.layers.41.input_layernorm.weight": "model-00025-of-00051.safetensors",
|
| 333 |
+
"model.layers.41.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
|
| 334 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00024-of-00051.safetensors",
|
| 335 |
+
"model.layers.41.mlp.up_proj.weight": "model-00024-of-00051.safetensors",
|
| 336 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
|
| 337 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00024-of-00051.safetensors",
|
| 338 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00024-of-00051.safetensors",
|
| 339 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00024-of-00051.safetensors",
|
| 340 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00024-of-00051.safetensors",
|
| 341 |
+
"model.layers.42.input_layernorm.weight": "model-00025-of-00051.safetensors",
|
| 342 |
+
"model.layers.42.mlp.down_proj.weight": "model-00025-of-00051.safetensors",
|
| 343 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
|
| 344 |
+
"model.layers.42.mlp.up_proj.weight": "model-00025-of-00051.safetensors",
|
| 345 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00025-of-00051.safetensors",
|
| 346 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
|
| 347 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
|
| 348 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
|
| 349 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
|
| 350 |
+
"model.layers.43.input_layernorm.weight": "model-00026-of-00051.safetensors",
|
| 351 |
+
"model.layers.43.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
|
| 352 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00025-of-00051.safetensors",
|
| 353 |
+
"model.layers.43.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
|
| 354 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
|
| 355 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00025-of-00051.safetensors",
|
| 356 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00025-of-00051.safetensors",
|
| 357 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00025-of-00051.safetensors",
|
| 358 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00025-of-00051.safetensors",
|
| 359 |
+
"model.layers.44.input_layernorm.weight": "model-00026-of-00051.safetensors",
|
| 360 |
+
"model.layers.44.mlp.down_proj.weight": "model-00026-of-00051.safetensors",
|
| 361 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00026-of-00051.safetensors",
|
| 362 |
+
"model.layers.44.mlp.up_proj.weight": "model-00026-of-00051.safetensors",
|
| 363 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00026-of-00051.safetensors",
|
| 364 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
|
| 365 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
|
| 366 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
|
| 367 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
|
| 368 |
+
"model.layers.45.input_layernorm.weight": "model-00027-of-00051.safetensors",
|
| 369 |
+
"model.layers.45.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
|
| 370 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
|
| 371 |
+
"model.layers.45.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
|
| 372 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
|
| 373 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00026-of-00051.safetensors",
|
| 374 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00026-of-00051.safetensors",
|
| 375 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00026-of-00051.safetensors",
|
| 376 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00026-of-00051.safetensors",
|
| 377 |
+
"model.layers.46.input_layernorm.weight": "model-00027-of-00051.safetensors",
|
| 378 |
+
"model.layers.46.mlp.down_proj.weight": "model-00027-of-00051.safetensors",
|
| 379 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00027-of-00051.safetensors",
|
| 380 |
+
"model.layers.46.mlp.up_proj.weight": "model-00027-of-00051.safetensors",
|
| 381 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00027-of-00051.safetensors",
|
| 382 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00027-of-00051.safetensors",
|
| 383 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00027-of-00051.safetensors",
|
| 384 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00027-of-00051.safetensors",
|
| 385 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00027-of-00051.safetensors",
|
| 386 |
+
"model.layers.47.input_layernorm.weight": "model-00028-of-00051.safetensors",
|
| 387 |
+
"model.layers.47.mlp.down_proj.weight": "model-00028-of-00051.safetensors",
|
| 388 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
|
| 389 |
+
"model.layers.47.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
|
| 390 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00028-of-00051.safetensors",
|
| 391 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
|
| 392 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
|
| 393 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
|
| 394 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
|
| 395 |
+
"model.layers.48.input_layernorm.weight": "model-00029-of-00051.safetensors",
|
| 396 |
+
"model.layers.48.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
|
| 397 |
+
"model.layers.48.mlp.gate_proj.weight": "model-00028-of-00051.safetensors",
|
| 398 |
+
"model.layers.48.mlp.up_proj.weight": "model-00028-of-00051.safetensors",
|
| 399 |
+
"model.layers.48.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
|
| 400 |
+
"model.layers.48.self_attn.k_proj.weight": "model-00028-of-00051.safetensors",
|
| 401 |
+
"model.layers.48.self_attn.o_proj.weight": "model-00028-of-00051.safetensors",
|
| 402 |
+
"model.layers.48.self_attn.q_proj.weight": "model-00028-of-00051.safetensors",
|
| 403 |
+
"model.layers.48.self_attn.v_proj.weight": "model-00028-of-00051.safetensors",
|
| 404 |
+
"model.layers.49.input_layernorm.weight": "model-00029-of-00051.safetensors",
|
| 405 |
+
"model.layers.49.mlp.down_proj.weight": "model-00029-of-00051.safetensors",
|
| 406 |
+
"model.layers.49.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
|
| 407 |
+
"model.layers.49.mlp.up_proj.weight": "model-00029-of-00051.safetensors",
|
| 408 |
+
"model.layers.49.post_attention_layernorm.weight": "model-00029-of-00051.safetensors",
|
| 409 |
+
"model.layers.49.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
|
| 410 |
+
"model.layers.49.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
|
| 411 |
+
"model.layers.49.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
|
| 412 |
+
"model.layers.49.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
|
| 413 |
+
"model.layers.5.input_layernorm.weight": "model-00004-of-00051.safetensors",
|
| 414 |
+
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00051.safetensors",
|
| 415 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
|
| 416 |
+
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
|
| 417 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00051.safetensors",
|
| 418 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
|
| 419 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
|
| 420 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
|
| 421 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
|
| 422 |
+
"model.layers.50.input_layernorm.weight": "model-00030-of-00051.safetensors",
|
| 423 |
+
"model.layers.50.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
|
| 424 |
+
"model.layers.50.mlp.gate_proj.weight": "model-00029-of-00051.safetensors",
|
| 425 |
+
"model.layers.50.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
|
| 426 |
+
"model.layers.50.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
|
| 427 |
+
"model.layers.50.self_attn.k_proj.weight": "model-00029-of-00051.safetensors",
|
| 428 |
+
"model.layers.50.self_attn.o_proj.weight": "model-00029-of-00051.safetensors",
|
| 429 |
+
"model.layers.50.self_attn.q_proj.weight": "model-00029-of-00051.safetensors",
|
| 430 |
+
"model.layers.50.self_attn.v_proj.weight": "model-00029-of-00051.safetensors",
|
| 431 |
+
"model.layers.51.input_layernorm.weight": "model-00030-of-00051.safetensors",
|
| 432 |
+
"model.layers.51.mlp.down_proj.weight": "model-00030-of-00051.safetensors",
|
| 433 |
+
"model.layers.51.mlp.gate_proj.weight": "model-00030-of-00051.safetensors",
|
| 434 |
+
"model.layers.51.mlp.up_proj.weight": "model-00030-of-00051.safetensors",
|
| 435 |
+
"model.layers.51.post_attention_layernorm.weight": "model-00030-of-00051.safetensors",
|
| 436 |
+
"model.layers.51.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
|
| 437 |
+
"model.layers.51.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
|
| 438 |
+
"model.layers.51.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
|
| 439 |
+
"model.layers.51.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
|
| 440 |
+
"model.layers.52.input_layernorm.weight": "model-00031-of-00051.safetensors",
|
| 441 |
+
"model.layers.52.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
|
| 442 |
+
"model.layers.52.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
|
| 443 |
+
"model.layers.52.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
|
| 444 |
+
"model.layers.52.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
|
| 445 |
+
"model.layers.52.self_attn.k_proj.weight": "model-00030-of-00051.safetensors",
|
| 446 |
+
"model.layers.52.self_attn.o_proj.weight": "model-00030-of-00051.safetensors",
|
| 447 |
+
"model.layers.52.self_attn.q_proj.weight": "model-00030-of-00051.safetensors",
|
| 448 |
+
"model.layers.52.self_attn.v_proj.weight": "model-00030-of-00051.safetensors",
|
| 449 |
+
"model.layers.53.input_layernorm.weight": "model-00031-of-00051.safetensors",
|
| 450 |
+
"model.layers.53.mlp.down_proj.weight": "model-00031-of-00051.safetensors",
|
| 451 |
+
"model.layers.53.mlp.gate_proj.weight": "model-00031-of-00051.safetensors",
|
| 452 |
+
"model.layers.53.mlp.up_proj.weight": "model-00031-of-00051.safetensors",
|
| 453 |
+
"model.layers.53.post_attention_layernorm.weight": "model-00031-of-00051.safetensors",
|
| 454 |
+
"model.layers.53.self_attn.k_proj.weight": "model-00031-of-00051.safetensors",
|
| 455 |
+
"model.layers.53.self_attn.o_proj.weight": "model-00031-of-00051.safetensors",
|
| 456 |
+
"model.layers.53.self_attn.q_proj.weight": "model-00031-of-00051.safetensors",
|
| 457 |
+
"model.layers.53.self_attn.v_proj.weight": "model-00031-of-00051.safetensors",
|
| 458 |
+
"model.layers.54.input_layernorm.weight": "model-00032-of-00051.safetensors",
|
| 459 |
+
"model.layers.54.mlp.down_proj.weight": "model-00032-of-00051.safetensors",
|
| 460 |
+
"model.layers.54.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
|
| 461 |
+
"model.layers.54.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
|
| 462 |
+
"model.layers.54.post_attention_layernorm.weight": "model-00032-of-00051.safetensors",
|
| 463 |
+
"model.layers.54.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
|
| 464 |
+
"model.layers.54.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
|
| 465 |
+
"model.layers.54.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
|
| 466 |
+
"model.layers.54.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
|
| 467 |
+
"model.layers.55.input_layernorm.weight": "model-00033-of-00051.safetensors",
|
| 468 |
+
"model.layers.55.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
|
| 469 |
+
"model.layers.55.mlp.gate_proj.weight": "model-00032-of-00051.safetensors",
|
| 470 |
+
"model.layers.55.mlp.up_proj.weight": "model-00032-of-00051.safetensors",
|
| 471 |
+
"model.layers.55.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
|
| 472 |
+
"model.layers.55.self_attn.k_proj.weight": "model-00032-of-00051.safetensors",
|
| 473 |
+
"model.layers.55.self_attn.o_proj.weight": "model-00032-of-00051.safetensors",
|
| 474 |
+
"model.layers.55.self_attn.q_proj.weight": "model-00032-of-00051.safetensors",
|
| 475 |
+
"model.layers.55.self_attn.v_proj.weight": "model-00032-of-00051.safetensors",
|
| 476 |
+
"model.layers.56.input_layernorm.weight": "model-00033-of-00051.safetensors",
|
| 477 |
+
"model.layers.56.mlp.down_proj.weight": "model-00033-of-00051.safetensors",
|
| 478 |
+
"model.layers.56.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
|
| 479 |
+
"model.layers.56.mlp.up_proj.weight": "model-00033-of-00051.safetensors",
|
| 480 |
+
"model.layers.56.post_attention_layernorm.weight": "model-00033-of-00051.safetensors",
|
| 481 |
+
"model.layers.56.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
|
| 482 |
+
"model.layers.56.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
|
| 483 |
+
"model.layers.56.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
|
| 484 |
+
"model.layers.56.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
|
| 485 |
+
"model.layers.57.input_layernorm.weight": "model-00034-of-00051.safetensors",
|
| 486 |
+
"model.layers.57.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
|
| 487 |
+
"model.layers.57.mlp.gate_proj.weight": "model-00033-of-00051.safetensors",
|
| 488 |
+
"model.layers.57.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
|
| 489 |
+
"model.layers.57.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
|
| 490 |
+
"model.layers.57.self_attn.k_proj.weight": "model-00033-of-00051.safetensors",
|
| 491 |
+
"model.layers.57.self_attn.o_proj.weight": "model-00033-of-00051.safetensors",
|
| 492 |
+
"model.layers.57.self_attn.q_proj.weight": "model-00033-of-00051.safetensors",
|
| 493 |
+
"model.layers.57.self_attn.v_proj.weight": "model-00033-of-00051.safetensors",
|
| 494 |
+
"model.layers.58.input_layernorm.weight": "model-00034-of-00051.safetensors",
|
| 495 |
+
"model.layers.58.mlp.down_proj.weight": "model-00034-of-00051.safetensors",
|
| 496 |
+
"model.layers.58.mlp.gate_proj.weight": "model-00034-of-00051.safetensors",
|
| 497 |
+
"model.layers.58.mlp.up_proj.weight": "model-00034-of-00051.safetensors",
|
| 498 |
+
"model.layers.58.post_attention_layernorm.weight": "model-00034-of-00051.safetensors",
|
| 499 |
+
"model.layers.58.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
|
| 500 |
+
"model.layers.58.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
|
| 501 |
+
"model.layers.58.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
|
| 502 |
+
"model.layers.58.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
|
| 503 |
+
"model.layers.59.input_layernorm.weight": "model-00035-of-00051.safetensors",
|
| 504 |
+
"model.layers.59.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
|
| 505 |
+
"model.layers.59.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
|
| 506 |
+
"model.layers.59.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
|
| 507 |
+
"model.layers.59.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
|
| 508 |
+
"model.layers.59.self_attn.k_proj.weight": "model-00034-of-00051.safetensors",
|
| 509 |
+
"model.layers.59.self_attn.o_proj.weight": "model-00034-of-00051.safetensors",
|
| 510 |
+
"model.layers.59.self_attn.q_proj.weight": "model-00034-of-00051.safetensors",
|
| 511 |
+
"model.layers.59.self_attn.v_proj.weight": "model-00034-of-00051.safetensors",
|
| 512 |
+
"model.layers.6.input_layernorm.weight": "model-00005-of-00051.safetensors",
|
| 513 |
+
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
|
| 514 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00004-of-00051.safetensors",
|
| 515 |
+
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00051.safetensors",
|
| 516 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
|
| 517 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00051.safetensors",
|
| 518 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00051.safetensors",
|
| 519 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00051.safetensors",
|
| 520 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00051.safetensors",
|
| 521 |
+
"model.layers.60.input_layernorm.weight": "model-00035-of-00051.safetensors",
|
| 522 |
+
"model.layers.60.mlp.down_proj.weight": "model-00035-of-00051.safetensors",
|
| 523 |
+
"model.layers.60.mlp.gate_proj.weight": "model-00035-of-00051.safetensors",
|
| 524 |
+
"model.layers.60.mlp.up_proj.weight": "model-00035-of-00051.safetensors",
|
| 525 |
+
"model.layers.60.post_attention_layernorm.weight": "model-00035-of-00051.safetensors",
|
| 526 |
+
"model.layers.60.self_attn.k_proj.weight": "model-00035-of-00051.safetensors",
|
| 527 |
+
"model.layers.60.self_attn.o_proj.weight": "model-00035-of-00051.safetensors",
|
| 528 |
+
"model.layers.60.self_attn.q_proj.weight": "model-00035-of-00051.safetensors",
|
| 529 |
+
"model.layers.60.self_attn.v_proj.weight": "model-00035-of-00051.safetensors",
|
| 530 |
+
"model.layers.61.input_layernorm.weight": "model-00036-of-00051.safetensors",
|
| 531 |
+
"model.layers.61.mlp.down_proj.weight": "model-00036-of-00051.safetensors",
|
| 532 |
+
"model.layers.61.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
|
| 533 |
+
"model.layers.61.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
|
| 534 |
+
"model.layers.61.post_attention_layernorm.weight": "model-00036-of-00051.safetensors",
|
| 535 |
+
"model.layers.61.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
|
| 536 |
+
"model.layers.61.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
|
| 537 |
+
"model.layers.61.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
|
| 538 |
+
"model.layers.61.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
|
| 539 |
+
"model.layers.62.input_layernorm.weight": "model-00037-of-00051.safetensors",
|
| 540 |
+
"model.layers.62.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
|
| 541 |
+
"model.layers.62.mlp.gate_proj.weight": "model-00036-of-00051.safetensors",
|
| 542 |
+
"model.layers.62.mlp.up_proj.weight": "model-00036-of-00051.safetensors",
|
| 543 |
+
"model.layers.62.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
|
| 544 |
+
"model.layers.62.self_attn.k_proj.weight": "model-00036-of-00051.safetensors",
|
| 545 |
+
"model.layers.62.self_attn.o_proj.weight": "model-00036-of-00051.safetensors",
|
| 546 |
+
"model.layers.62.self_attn.q_proj.weight": "model-00036-of-00051.safetensors",
|
| 547 |
+
"model.layers.62.self_attn.v_proj.weight": "model-00036-of-00051.safetensors",
|
| 548 |
+
"model.layers.63.input_layernorm.weight": "model-00037-of-00051.safetensors",
|
| 549 |
+
"model.layers.63.mlp.down_proj.weight": "model-00037-of-00051.safetensors",
|
| 550 |
+
"model.layers.63.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
|
| 551 |
+
"model.layers.63.mlp.up_proj.weight": "model-00037-of-00051.safetensors",
|
| 552 |
+
"model.layers.63.post_attention_layernorm.weight": "model-00037-of-00051.safetensors",
|
| 553 |
+
"model.layers.63.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
|
| 554 |
+
"model.layers.63.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
|
| 555 |
+
"model.layers.63.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
|
| 556 |
+
"model.layers.63.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
|
| 557 |
+
"model.layers.64.input_layernorm.weight": "model-00038-of-00051.safetensors",
|
| 558 |
+
"model.layers.64.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
|
| 559 |
+
"model.layers.64.mlp.gate_proj.weight": "model-00037-of-00051.safetensors",
|
| 560 |
+
"model.layers.64.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
|
| 561 |
+
"model.layers.64.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
|
| 562 |
+
"model.layers.64.self_attn.k_proj.weight": "model-00037-of-00051.safetensors",
|
| 563 |
+
"model.layers.64.self_attn.o_proj.weight": "model-00037-of-00051.safetensors",
|
| 564 |
+
"model.layers.64.self_attn.q_proj.weight": "model-00037-of-00051.safetensors",
|
| 565 |
+
"model.layers.64.self_attn.v_proj.weight": "model-00037-of-00051.safetensors",
|
| 566 |
+
"model.layers.65.input_layernorm.weight": "model-00038-of-00051.safetensors",
|
| 567 |
+
"model.layers.65.mlp.down_proj.weight": "model-00038-of-00051.safetensors",
|
| 568 |
+
"model.layers.65.mlp.gate_proj.weight": "model-00038-of-00051.safetensors",
|
| 569 |
+
"model.layers.65.mlp.up_proj.weight": "model-00038-of-00051.safetensors",
|
| 570 |
+
"model.layers.65.post_attention_layernorm.weight": "model-00038-of-00051.safetensors",
|
| 571 |
+
"model.layers.65.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
|
| 572 |
+
"model.layers.65.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
|
| 573 |
+
"model.layers.65.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
|
| 574 |
+
"model.layers.65.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
|
| 575 |
+
"model.layers.66.input_layernorm.weight": "model-00039-of-00051.safetensors",
|
| 576 |
+
"model.layers.66.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
|
| 577 |
+
"model.layers.66.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
|
| 578 |
+
"model.layers.66.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
|
| 579 |
+
"model.layers.66.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
|
| 580 |
+
"model.layers.66.self_attn.k_proj.weight": "model-00038-of-00051.safetensors",
|
| 581 |
+
"model.layers.66.self_attn.o_proj.weight": "model-00038-of-00051.safetensors",
|
| 582 |
+
"model.layers.66.self_attn.q_proj.weight": "model-00038-of-00051.safetensors",
|
| 583 |
+
"model.layers.66.self_attn.v_proj.weight": "model-00038-of-00051.safetensors",
|
| 584 |
+
"model.layers.67.input_layernorm.weight": "model-00039-of-00051.safetensors",
|
| 585 |
+
"model.layers.67.mlp.down_proj.weight": "model-00039-of-00051.safetensors",
|
| 586 |
+
"model.layers.67.mlp.gate_proj.weight": "model-00039-of-00051.safetensors",
|
| 587 |
+
"model.layers.67.mlp.up_proj.weight": "model-00039-of-00051.safetensors",
|
| 588 |
+
"model.layers.67.post_attention_layernorm.weight": "model-00039-of-00051.safetensors",
|
| 589 |
+
"model.layers.67.self_attn.k_proj.weight": "model-00039-of-00051.safetensors",
|
| 590 |
+
"model.layers.67.self_attn.o_proj.weight": "model-00039-of-00051.safetensors",
|
| 591 |
+
"model.layers.67.self_attn.q_proj.weight": "model-00039-of-00051.safetensors",
|
| 592 |
+
"model.layers.67.self_attn.v_proj.weight": "model-00039-of-00051.safetensors",
|
| 593 |
+
"model.layers.68.input_layernorm.weight": "model-00040-of-00051.safetensors",
|
| 594 |
+
"model.layers.68.mlp.down_proj.weight": "model-00040-of-00051.safetensors",
|
| 595 |
+
"model.layers.68.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
|
| 596 |
+
"model.layers.68.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
|
| 597 |
+
"model.layers.68.post_attention_layernorm.weight": "model-00040-of-00051.safetensors",
|
| 598 |
+
"model.layers.68.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
|
| 599 |
+
"model.layers.68.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
|
| 600 |
+
"model.layers.68.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
|
| 601 |
+
"model.layers.68.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
|
| 602 |
+
"model.layers.69.input_layernorm.weight": "model-00041-of-00051.safetensors",
|
| 603 |
+
"model.layers.69.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
|
| 604 |
+
"model.layers.69.mlp.gate_proj.weight": "model-00040-of-00051.safetensors",
|
| 605 |
+
"model.layers.69.mlp.up_proj.weight": "model-00040-of-00051.safetensors",
|
| 606 |
+
"model.layers.69.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
|
| 607 |
+
"model.layers.69.self_attn.k_proj.weight": "model-00040-of-00051.safetensors",
|
| 608 |
+
"model.layers.69.self_attn.o_proj.weight": "model-00040-of-00051.safetensors",
|
| 609 |
+
"model.layers.69.self_attn.q_proj.weight": "model-00040-of-00051.safetensors",
|
| 610 |
+
"model.layers.69.self_attn.v_proj.weight": "model-00040-of-00051.safetensors",
|
| 611 |
+
"model.layers.7.input_layernorm.weight": "model-00005-of-00051.safetensors",
|
| 612 |
+
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00051.safetensors",
|
| 613 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
|
| 614 |
+
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00051.safetensors",
|
| 615 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00051.safetensors",
|
| 616 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
|
| 617 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
|
| 618 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
|
| 619 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
|
| 620 |
+
"model.layers.70.input_layernorm.weight": "model-00041-of-00051.safetensors",
|
| 621 |
+
"model.layers.70.mlp.down_proj.weight": "model-00041-of-00051.safetensors",
|
| 622 |
+
"model.layers.70.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
|
| 623 |
+
"model.layers.70.mlp.up_proj.weight": "model-00041-of-00051.safetensors",
|
| 624 |
+
"model.layers.70.post_attention_layernorm.weight": "model-00041-of-00051.safetensors",
|
| 625 |
+
"model.layers.70.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
|
| 626 |
+
"model.layers.70.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
|
| 627 |
+
"model.layers.70.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
|
| 628 |
+
"model.layers.70.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
|
| 629 |
+
"model.layers.71.input_layernorm.weight": "model-00042-of-00051.safetensors",
|
| 630 |
+
"model.layers.71.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
|
| 631 |
+
"model.layers.71.mlp.gate_proj.weight": "model-00041-of-00051.safetensors",
|
| 632 |
+
"model.layers.71.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
|
| 633 |
+
"model.layers.71.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
|
| 634 |
+
"model.layers.71.self_attn.k_proj.weight": "model-00041-of-00051.safetensors",
|
| 635 |
+
"model.layers.71.self_attn.o_proj.weight": "model-00041-of-00051.safetensors",
|
| 636 |
+
"model.layers.71.self_attn.q_proj.weight": "model-00041-of-00051.safetensors",
|
| 637 |
+
"model.layers.71.self_attn.v_proj.weight": "model-00041-of-00051.safetensors",
|
| 638 |
+
"model.layers.72.input_layernorm.weight": "model-00042-of-00051.safetensors",
|
| 639 |
+
"model.layers.72.mlp.down_proj.weight": "model-00042-of-00051.safetensors",
|
| 640 |
+
"model.layers.72.mlp.gate_proj.weight": "model-00042-of-00051.safetensors",
|
| 641 |
+
"model.layers.72.mlp.up_proj.weight": "model-00042-of-00051.safetensors",
|
| 642 |
+
"model.layers.72.post_attention_layernorm.weight": "model-00042-of-00051.safetensors",
|
| 643 |
+
"model.layers.72.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
|
| 644 |
+
"model.layers.72.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
|
| 645 |
+
"model.layers.72.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
|
| 646 |
+
"model.layers.72.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
|
| 647 |
+
"model.layers.73.input_layernorm.weight": "model-00043-of-00051.safetensors",
|
| 648 |
+
"model.layers.73.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
|
| 649 |
+
"model.layers.73.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
|
| 650 |
+
"model.layers.73.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
|
| 651 |
+
"model.layers.73.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
|
| 652 |
+
"model.layers.73.self_attn.k_proj.weight": "model-00042-of-00051.safetensors",
|
| 653 |
+
"model.layers.73.self_attn.o_proj.weight": "model-00042-of-00051.safetensors",
|
| 654 |
+
"model.layers.73.self_attn.q_proj.weight": "model-00042-of-00051.safetensors",
|
| 655 |
+
"model.layers.73.self_attn.v_proj.weight": "model-00042-of-00051.safetensors",
|
| 656 |
+
"model.layers.74.input_layernorm.weight": "model-00043-of-00051.safetensors",
|
| 657 |
+
"model.layers.74.mlp.down_proj.weight": "model-00043-of-00051.safetensors",
|
| 658 |
+
"model.layers.74.mlp.gate_proj.weight": "model-00043-of-00051.safetensors",
|
| 659 |
+
"model.layers.74.mlp.up_proj.weight": "model-00043-of-00051.safetensors",
|
| 660 |
+
"model.layers.74.post_attention_layernorm.weight": "model-00043-of-00051.safetensors",
|
| 661 |
+
"model.layers.74.self_attn.k_proj.weight": "model-00043-of-00051.safetensors",
|
| 662 |
+
"model.layers.74.self_attn.o_proj.weight": "model-00043-of-00051.safetensors",
|
| 663 |
+
"model.layers.74.self_attn.q_proj.weight": "model-00043-of-00051.safetensors",
|
| 664 |
+
"model.layers.74.self_attn.v_proj.weight": "model-00043-of-00051.safetensors",
|
| 665 |
+
"model.layers.75.input_layernorm.weight": "model-00044-of-00051.safetensors",
|
| 666 |
+
"model.layers.75.mlp.down_proj.weight": "model-00044-of-00051.safetensors",
|
| 667 |
+
"model.layers.75.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
|
| 668 |
+
"model.layers.75.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
|
| 669 |
+
"model.layers.75.post_attention_layernorm.weight": "model-00044-of-00051.safetensors",
|
| 670 |
+
"model.layers.75.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
|
| 671 |
+
"model.layers.75.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
|
| 672 |
+
"model.layers.75.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
|
| 673 |
+
"model.layers.75.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
|
| 674 |
+
"model.layers.76.input_layernorm.weight": "model-00045-of-00051.safetensors",
|
| 675 |
+
"model.layers.76.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
|
| 676 |
+
"model.layers.76.mlp.gate_proj.weight": "model-00044-of-00051.safetensors",
|
| 677 |
+
"model.layers.76.mlp.up_proj.weight": "model-00044-of-00051.safetensors",
|
| 678 |
+
"model.layers.76.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
|
| 679 |
+
"model.layers.76.self_attn.k_proj.weight": "model-00044-of-00051.safetensors",
|
| 680 |
+
"model.layers.76.self_attn.o_proj.weight": "model-00044-of-00051.safetensors",
|
| 681 |
+
"model.layers.76.self_attn.q_proj.weight": "model-00044-of-00051.safetensors",
|
| 682 |
+
"model.layers.76.self_attn.v_proj.weight": "model-00044-of-00051.safetensors",
|
| 683 |
+
"model.layers.77.input_layernorm.weight": "model-00045-of-00051.safetensors",
|
| 684 |
+
"model.layers.77.mlp.down_proj.weight": "model-00045-of-00051.safetensors",
|
| 685 |
+
"model.layers.77.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
|
| 686 |
+
"model.layers.77.mlp.up_proj.weight": "model-00045-of-00051.safetensors",
|
| 687 |
+
"model.layers.77.post_attention_layernorm.weight": "model-00045-of-00051.safetensors",
|
| 688 |
+
"model.layers.77.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
|
| 689 |
+
"model.layers.77.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
|
| 690 |
+
"model.layers.77.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
|
| 691 |
+
"model.layers.77.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
|
| 692 |
+
"model.layers.78.input_layernorm.weight": "model-00046-of-00051.safetensors",
|
| 693 |
+
"model.layers.78.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
|
| 694 |
+
"model.layers.78.mlp.gate_proj.weight": "model-00045-of-00051.safetensors",
|
| 695 |
+
"model.layers.78.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
|
| 696 |
+
"model.layers.78.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
|
| 697 |
+
"model.layers.78.self_attn.k_proj.weight": "model-00045-of-00051.safetensors",
|
| 698 |
+
"model.layers.78.self_attn.o_proj.weight": "model-00045-of-00051.safetensors",
|
| 699 |
+
"model.layers.78.self_attn.q_proj.weight": "model-00045-of-00051.safetensors",
|
| 700 |
+
"model.layers.78.self_attn.v_proj.weight": "model-00045-of-00051.safetensors",
|
| 701 |
+
"model.layers.79.input_layernorm.weight": "model-00046-of-00051.safetensors",
|
| 702 |
+
"model.layers.79.mlp.down_proj.weight": "model-00046-of-00051.safetensors",
|
| 703 |
+
"model.layers.79.mlp.gate_proj.weight": "model-00046-of-00051.safetensors",
|
| 704 |
+
"model.layers.79.mlp.up_proj.weight": "model-00046-of-00051.safetensors",
|
| 705 |
+
"model.layers.79.post_attention_layernorm.weight": "model-00046-of-00051.safetensors",
|
| 706 |
+
"model.layers.79.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
|
| 707 |
+
"model.layers.79.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
|
| 708 |
+
"model.layers.79.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
|
| 709 |
+
"model.layers.79.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
|
| 710 |
+
"model.layers.8.input_layernorm.weight": "model-00006-of-00051.safetensors",
|
| 711 |
+
"model.layers.8.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
|
| 712 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00051.safetensors",
|
| 713 |
+
"model.layers.8.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
|
| 714 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
|
| 715 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00051.safetensors",
|
| 716 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00051.safetensors",
|
| 717 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00051.safetensors",
|
| 718 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00051.safetensors",
|
| 719 |
+
"model.layers.80.input_layernorm.weight": "model-00047-of-00051.safetensors",
|
| 720 |
+
"model.layers.80.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
|
| 721 |
+
"model.layers.80.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
|
| 722 |
+
"model.layers.80.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
|
| 723 |
+
"model.layers.80.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
|
| 724 |
+
"model.layers.80.self_attn.k_proj.weight": "model-00046-of-00051.safetensors",
|
| 725 |
+
"model.layers.80.self_attn.o_proj.weight": "model-00046-of-00051.safetensors",
|
| 726 |
+
"model.layers.80.self_attn.q_proj.weight": "model-00046-of-00051.safetensors",
|
| 727 |
+
"model.layers.80.self_attn.v_proj.weight": "model-00046-of-00051.safetensors",
|
| 728 |
+
"model.layers.81.input_layernorm.weight": "model-00047-of-00051.safetensors",
|
| 729 |
+
"model.layers.81.mlp.down_proj.weight": "model-00047-of-00051.safetensors",
|
| 730 |
+
"model.layers.81.mlp.gate_proj.weight": "model-00047-of-00051.safetensors",
|
| 731 |
+
"model.layers.81.mlp.up_proj.weight": "model-00047-of-00051.safetensors",
|
| 732 |
+
"model.layers.81.post_attention_layernorm.weight": "model-00047-of-00051.safetensors",
|
| 733 |
+
"model.layers.81.self_attn.k_proj.weight": "model-00047-of-00051.safetensors",
|
| 734 |
+
"model.layers.81.self_attn.o_proj.weight": "model-00047-of-00051.safetensors",
|
| 735 |
+
"model.layers.81.self_attn.q_proj.weight": "model-00047-of-00051.safetensors",
|
| 736 |
+
"model.layers.81.self_attn.v_proj.weight": "model-00047-of-00051.safetensors",
|
| 737 |
+
"model.layers.82.input_layernorm.weight": "model-00048-of-00051.safetensors",
|
| 738 |
+
"model.layers.82.mlp.down_proj.weight": "model-00048-of-00051.safetensors",
|
| 739 |
+
"model.layers.82.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
|
| 740 |
+
"model.layers.82.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
|
| 741 |
+
"model.layers.82.post_attention_layernorm.weight": "model-00048-of-00051.safetensors",
|
| 742 |
+
"model.layers.82.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
|
| 743 |
+
"model.layers.82.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
|
| 744 |
+
"model.layers.82.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
|
| 745 |
+
"model.layers.82.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
|
| 746 |
+
"model.layers.83.input_layernorm.weight": "model-00049-of-00051.safetensors",
|
| 747 |
+
"model.layers.83.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
|
| 748 |
+
"model.layers.83.mlp.gate_proj.weight": "model-00048-of-00051.safetensors",
|
| 749 |
+
"model.layers.83.mlp.up_proj.weight": "model-00048-of-00051.safetensors",
|
| 750 |
+
"model.layers.83.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
|
| 751 |
+
"model.layers.83.self_attn.k_proj.weight": "model-00048-of-00051.safetensors",
|
| 752 |
+
"model.layers.83.self_attn.o_proj.weight": "model-00048-of-00051.safetensors",
|
| 753 |
+
"model.layers.83.self_attn.q_proj.weight": "model-00048-of-00051.safetensors",
|
| 754 |
+
"model.layers.83.self_attn.v_proj.weight": "model-00048-of-00051.safetensors",
|
| 755 |
+
"model.layers.84.input_layernorm.weight": "model-00049-of-00051.safetensors",
|
| 756 |
+
"model.layers.84.mlp.down_proj.weight": "model-00049-of-00051.safetensors",
|
| 757 |
+
"model.layers.84.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
|
| 758 |
+
"model.layers.84.mlp.up_proj.weight": "model-00049-of-00051.safetensors",
|
| 759 |
+
"model.layers.84.post_attention_layernorm.weight": "model-00049-of-00051.safetensors",
|
| 760 |
+
"model.layers.84.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
|
| 761 |
+
"model.layers.84.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
|
| 762 |
+
"model.layers.84.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
|
| 763 |
+
"model.layers.84.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
|
| 764 |
+
"model.layers.85.input_layernorm.weight": "model-00050-of-00051.safetensors",
|
| 765 |
+
"model.layers.85.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
|
| 766 |
+
"model.layers.85.mlp.gate_proj.weight": "model-00049-of-00051.safetensors",
|
| 767 |
+
"model.layers.85.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
|
| 768 |
+
"model.layers.85.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
|
| 769 |
+
"model.layers.85.self_attn.k_proj.weight": "model-00049-of-00051.safetensors",
|
| 770 |
+
"model.layers.85.self_attn.o_proj.weight": "model-00049-of-00051.safetensors",
|
| 771 |
+
"model.layers.85.self_attn.q_proj.weight": "model-00049-of-00051.safetensors",
|
| 772 |
+
"model.layers.85.self_attn.v_proj.weight": "model-00049-of-00051.safetensors",
|
| 773 |
+
"model.layers.86.input_layernorm.weight": "model-00050-of-00051.safetensors",
|
| 774 |
+
"model.layers.86.mlp.down_proj.weight": "model-00050-of-00051.safetensors",
|
| 775 |
+
"model.layers.86.mlp.gate_proj.weight": "model-00050-of-00051.safetensors",
|
| 776 |
+
"model.layers.86.mlp.up_proj.weight": "model-00050-of-00051.safetensors",
|
| 777 |
+
"model.layers.86.post_attention_layernorm.weight": "model-00050-of-00051.safetensors",
|
| 778 |
+
"model.layers.86.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
|
| 779 |
+
"model.layers.86.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
|
| 780 |
+
"model.layers.86.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
|
| 781 |
+
"model.layers.86.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
|
| 782 |
+
"model.layers.87.input_layernorm.weight": "model-00051-of-00051.safetensors",
|
| 783 |
+
"model.layers.87.mlp.down_proj.weight": "model-00051-of-00051.safetensors",
|
| 784 |
+
"model.layers.87.mlp.gate_proj.weight": "model-00051-of-00051.safetensors",
|
| 785 |
+
"model.layers.87.mlp.up_proj.weight": "model-00051-of-00051.safetensors",
|
| 786 |
+
"model.layers.87.post_attention_layernorm.weight": "model-00051-of-00051.safetensors",
|
| 787 |
+
"model.layers.87.self_attn.k_proj.weight": "model-00050-of-00051.safetensors",
|
| 788 |
+
"model.layers.87.self_attn.o_proj.weight": "model-00050-of-00051.safetensors",
|
| 789 |
+
"model.layers.87.self_attn.q_proj.weight": "model-00050-of-00051.safetensors",
|
| 790 |
+
"model.layers.87.self_attn.v_proj.weight": "model-00050-of-00051.safetensors",
|
| 791 |
+
"model.layers.9.input_layernorm.weight": "model-00006-of-00051.safetensors",
|
| 792 |
+
"model.layers.9.mlp.down_proj.weight": "model-00006-of-00051.safetensors",
|
| 793 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00006-of-00051.safetensors",
|
| 794 |
+
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00051.safetensors",
|
| 795 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00051.safetensors",
|
| 796 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00006-of-00051.safetensors",
|
| 797 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00051.safetensors",
|
| 798 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00051.safetensors",
|
| 799 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00051.safetensors",
|
| 800 |
+
"model.norm.weight": "model-00051-of-00051.safetensors"
|
| 801 |
+
}
|
| 802 |
+
}
|
output-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aaefee2d14d8aa2b3fac3d109acda298888fc9ded4e64da50fc118f8b1dc2d5
|
| 3 |
+
size 8536140834
|
output-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:215a96e1271ff0d11dfba0e2065352d2f8ac40f04e9a855d46beb24176d236ac
|
| 3 |
+
size 8509706610
|
output-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c3af8b8618c4cc9d0319133601dcd22352b5b2925814e2d622d1399abb309a
|
| 3 |
+
size 8575250588
|
output-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eaa7b0b9208b4121c00c8834a39fa23d665c0071220faaff8cf0d0eaa2a77a7
|
| 3 |
+
size 8571265148
|
output-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2e94b4e77047bd41dab1a122a9e6a666a486b5c48e37a8fe8be65723262332a
|
| 3 |
+
size 8518654948
|
output-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36f2e0610b757b004a886fa4d789f1dff2b5b7e760cca3bf53e252f5c64e8e16
|
| 3 |
+
size 8588501112
|
output-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c74380e42a8b3d1865b9b75f78b6eb891d3fb03d0bf461c41ddb3b6f5a4ee485
|
| 3 |
+
size 6920573972
|
params.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dim": 12288,
|
| 3 |
+
"n_layers": 88,
|
| 4 |
+
"head_dim": 128,
|
| 5 |
+
"hidden_dim": 28672,
|
| 6 |
+
"n_heads": 96,
|
| 7 |
+
"n_kv_heads": 8,
|
| 8 |
+
"norm_eps": 1e-05,
|
| 9 |
+
"vocab_size": 32768,
|
| 10 |
+
"rope_theta": 1000000.0
|
| 11 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
|
| 3 |
+
size 587562
|
tokenizer.model.v7
ADDED
|
Binary file (588 kB). View file
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|