Add Github link, Transformers library, pipeline tag
Browse filesThis PR fixes the pipeline tag to text-generation, and makes sure the relevant "how to use" button is displayed on the top right.
README.md
CHANGED
@@ -1,5 +1,18 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
datasets:
|
4 |
- Satori-reasoning/Satori_FT_data
|
5 |
- Satori-reasoning/Satori_RL_data
|
@@ -112,7 +125,7 @@ Satori-7B-Round2 achieves SOTA performance and outperforms Qwen-2.5-Math-7B-Inst
|
|
112 |
| | OpenMath2-Llama3.1-8B | 90.5 | 67.8 | 28.9 | 37.5 | 6.7 | 46.3 |
|
113 |
| | NuminaMath-7B-CoT | 78.9 | 54.6 | 15.9 | 20.0 | 10.0 | 35.9 |
|
114 |
| | Qwen-2.5-7B-Instruct | 91.6 | 75.5 | 35.5 | 52.5 | 6.7 | 52.4 |
|
115 |
-
| | Qwen-2.5-Math-7B-Instruct |95.2
|
116 |
| | **Satori-7B-Round2** | 93.9 | 83.6 | 48.5 | 72.5 | 23.3 | **64.4** |
|
117 |
|
118 |
### **General Domain Reasoning Benchmarks**
|
@@ -140,6 +153,8 @@ Please refer to our blog and research paper for more technical details of Satori
|
|
140 |
- [Blog](https://satori-reasoning.github.io/blog/satori/)
|
141 |
- [Paper](https://arxiv.org/pdf/2502.02508)
|
142 |
|
|
|
|
|
143 |
# **Citation**
|
144 |
If you find our model and data helpful, please cite our paper:
|
145 |
```
|
@@ -152,4 +167,321 @@ If you find our model and data helpful, please cite our paper:
|
|
152 |
primaryClass={cs.CL},
|
153 |
url={https://arxiv.org/abs/2502.02508},
|
154 |
}
|
155 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
library_name: transformers
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
datasets:
|
6 |
+
- Satori-reasoning/Satori_FT_data
|
7 |
+
- Satori-reasoning/Satori_RL_data
|
8 |
+
base_model:
|
9 |
+
- Qwen/Qwen2.5-Math-7B
|
10 |
+
---
|
11 |
+
|
12 |
+
---
|
13 |
+
license: apache-2.0
|
14 |
+
library_name: transformers
|
15 |
+
pipeline_tag: text-generation
|
16 |
datasets:
|
17 |
- Satori-reasoning/Satori_FT_data
|
18 |
- Satori-reasoning/Satori_RL_data
|
|
|
125 |
| | OpenMath2-Llama3.1-8B | 90.5 | 67.8 | 28.9 | 37.5 | 6.7 | 46.3 |
|
126 |
| | NuminaMath-7B-CoT | 78.9 | 54.6 | 15.9 | 20.0 | 10.0 | 35.9 |
|
127 |
| | Qwen-2.5-7B-Instruct | 91.6 | 75.5 | 35.5 | 52.5 | 6.7 | 52.4 |
|
128 |
+
| | Qwen-2.5-Math-7B-Instruct | 95.2 | 83.6 | 41.6 | 62.5 | 16.7 | 59.9 |
|
129 |
| | **Satori-7B-Round2** | 93.9 | 83.6 | 48.5 | 72.5 | 23.3 | **64.4** |
|
130 |
|
131 |
### **General Domain Reasoning Benchmarks**
|
|
|
153 |
- [Blog](https://satori-reasoning.github.io/blog/satori/)
|
154 |
- [Paper](https://arxiv.org/pdf/2502.02508)
|
155 |
|
156 |
+
For code, see https://github.com/Satori-reasoning/Satori
|
157 |
+
|
158 |
# **Citation**
|
159 |
If you find our model and data helpful, please cite our paper:
|
160 |
```
|
|
|
167 |
primaryClass={cs.CL},
|
168 |
url={https://arxiv.org/abs/2502.02508},
|
169 |
}
|
170 |
+
```
|
171 |
+
|
172 |
+
# File information
|
173 |
+
|
174 |
+
The repository contains the following file information:
|
175 |
+
|
176 |
+
Filename: added_tokens.json
|
177 |
+
Content: {
|
178 |
+
"</tool_call>": 151658,
|
179 |
+
"<tool_call>": 151657,
|
180 |
+
"<|explore|>": 151667,
|
181 |
+
"<|box_end|>": 151649,
|
182 |
+
"<|box_start|>": 151648,
|
183 |
+
"<|continue|>": 151665,
|
184 |
+
"<|endoftext|>": 151643,
|
185 |
+
"<|file_sep|>": 151664,
|
186 |
+
"<|fim_middle|>": 151660,
|
187 |
+
"<|fim_pad|>": 151662,
|
188 |
+
"<|fim_prefix|>": 151659,
|
189 |
+
"<|fim_suffix|>": 151661,
|
190 |
+
"<|im_end|>": 151645,
|
191 |
+
"<|im_start|>": 151644,
|
192 |
+
"<|image_pad|>": 151655,
|
193 |
+
"<|mask|>": 151668,
|
194 |
+
"<|object_ref_end|>": 151647,
|
195 |
+
"<|object_ref_start|>": 151646,
|
196 |
+
"<|quad_end|>": 151651,
|
197 |
+
"<|quad_start|>": 151650,
|
198 |
+
"<|reflect|>": 151666,
|
199 |
+
"<|repo_name|>": 151663,
|
200 |
+
"<|video_pad|>": 151656,
|
201 |
+
"<|vision_end|>": 151653,
|
202 |
+
"<|vision_pad|>": 151654,
|
203 |
+
"<|vision_start|>": 151652
|
204 |
+
}
|
205 |
+
|
206 |
+
Filename: tokenizer_config.json
|
207 |
+
Content: {
|
208 |
+
"add_bos_token": false,
|
209 |
+
"add_prefix_space": false,
|
210 |
+
"added_tokens_decoder": {
|
211 |
+
"151643": {
|
212 |
+
"content": "<|endoftext|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"151644": {
|
220 |
+
"content": "<|im_start|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"151645": {
|
228 |
+
"content": "<|im_end|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"151646": {
|
236 |
+
"content": "<|object_ref_start|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"151647": {
|
244 |
+
"content": "<|object_ref_end|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"151648": {
|
252 |
+
"content": "<|box_start|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"151649": {
|
260 |
+
"content": "<|box_end|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"151650": {
|
268 |
+
"content": "<|quad_start|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"151651": {
|
276 |
+
"content": "<|quad_end|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"151652": {
|
284 |
+
"content": "<|vision_start|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"151653": {
|
292 |
+
"content": "<|vision_end|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"151654": {
|
300 |
+
"content": "<|vision_pad|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"151655": {
|
308 |
+
"content": "<|image_pad|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"151656": {
|
316 |
+
"content": "<|video_pad|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"151657": {
|
324 |
+
"content": "<tool_call>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": false
|
330 |
+
},
|
331 |
+
"151658": {
|
332 |
+
"content": "</tool_call>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": false
|
338 |
+
},
|
339 |
+
"151659": {
|
340 |
+
"content": "<|fim_prefix|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": false
|
346 |
+
},
|
347 |
+
"151660": {
|
348 |
+
"content": "<|fim_middle|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": false
|
354 |
+
},
|
355 |
+
"151661": {
|
356 |
+
"content": "<|fim_suffix|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": false
|
362 |
+
},
|
363 |
+
"151662": {
|
364 |
+
"content": "<|fim_pad|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": false
|
370 |
+
},
|
371 |
+
"151663": {
|
372 |
+
"content": "<|repo_name|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": false
|
378 |
+
},
|
379 |
+
"151664": {
|
380 |
+
"content": "<|file_sep|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": false
|
386 |
+
},
|
387 |
+
"151665": {
|
388 |
+
"content": "<|continue|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"151666": {
|
396 |
+
"content": "<|reflect|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"151667": {
|
404 |
+
"content": "<|explore|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"151668": {
|
412 |
+
"content": "<|mask|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
}
|
419 |
+
},
|
420 |
+
"additional_special_tokens": [
|
421 |
+
"<|im_start|>",
|
422 |
+
"<|im_end|>",
|
423 |
+
"<|object_ref_start|>",
|
424 |
+
"<|object_ref_end|>",
|
425 |
+
"<|box_start|>",
|
426 |
+
"<|box_end|>",
|
427 |
+
"<|quad_start|>",
|
428 |
+
"<|quad_end|>",
|
429 |
+
"<|vision_start|>",
|
430 |
+
"<|vision_end|>",
|
431 |
+
"<|vision_pad|>",
|
432 |
+
"<|image_pad|>",
|
433 |
+
"<|video_pad|>",
|
434 |
+
"<|continue|>",
|
435 |
+
"<|reflect|>",
|
436 |
+
"<|explore|>",
|
437 |
+
"<|mask|>"
|
438 |
+
],
|
439 |
+
"bos_token": null,
|
440 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
441 |
+
"clean_up_tokenization_spaces": false,
|
442 |
+
"eos_token": "<|im_end|>",
|
443 |
+
"errors": "replace",
|
444 |
+
"model_max_length": 131072,
|
445 |
+
"pad_token": "<|endoftext|>",
|
446 |
+
"padding_side": "left",
|
447 |
+
"split_special_tokens": false,
|
448 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
449 |
+
"unk_token": null
|
450 |
+
}
|
451 |
+
|
452 |
+
Filename: model.safetensors.index.json
|
453 |
+
Content: {
|
454 |
+
"metadata": {
|
455 |
+
"total_size": 15231233024
|
456 |
+
},
|
457 |
+
"weight_map": {
|
458 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
459 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
460 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
461 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
462 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
463 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
464 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
465 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
466 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
467 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
468 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
469 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
470 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
471 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
472 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
473 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
474 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
475 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
476 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
477 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
478 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
479 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
480 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
481 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
482 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
483 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
484 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
485 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
486 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
487 |
+
"model.layers.1
|