XelotX commited on
Commit
ba100a1
1 Parent(s): caf0927

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +613 -0
  3. config.json +27 -0
  4. generation_config.json +7 -0
  5. model-00001-of-00044.safetensors +3 -0
  6. model-00002-of-00044.safetensors +3 -0
  7. model-00003-of-00044.safetensors +3 -0
  8. model-00004-of-00044.safetensors +3 -0
  9. model-00005-of-00044.safetensors +3 -0
  10. model-00006-of-00044.safetensors +3 -0
  11. model-00007-of-00044.safetensors +3 -0
  12. model-00008-of-00044.safetensors +3 -0
  13. model-00009-of-00044.safetensors +3 -0
  14. model-00010-of-00044.safetensors +3 -0
  15. model-00011-of-00044.safetensors +3 -0
  16. model-00012-of-00044.safetensors +3 -0
  17. model-00013-of-00044.safetensors +3 -0
  18. model-00014-of-00044.safetensors +3 -0
  19. model-00015-of-00044.safetensors +3 -0
  20. model-00016-of-00044.safetensors +3 -0
  21. model-00017-of-00044.safetensors +3 -0
  22. model-00018-of-00044.safetensors +3 -0
  23. model-00019-of-00044.safetensors +3 -0
  24. model-00020-of-00044.safetensors +3 -0
  25. model-00021-of-00044.safetensors +3 -0
  26. model-00022-of-00044.safetensors +3 -0
  27. model-00023-of-00044.safetensors +3 -0
  28. model-00024-of-00044.safetensors +3 -0
  29. model-00025-of-00044.safetensors +3 -0
  30. model-00026-of-00044.safetensors +3 -0
  31. model-00027-of-00044.safetensors +3 -0
  32. model-00028-of-00044.safetensors +3 -0
  33. model-00029-of-00044.safetensors +3 -0
  34. model-00030-of-00044.safetensors +3 -0
  35. model-00031-of-00044.safetensors +3 -0
  36. model-00032-of-00044.safetensors +3 -0
  37. model-00033-of-00044.safetensors +3 -0
  38. model-00034-of-00044.safetensors +3 -0
  39. model-00035-of-00044.safetensors +3 -0
  40. model-00036-of-00044.safetensors +3 -0
  41. model-00037-of-00044.safetensors +3 -0
  42. model-00038-of-00044.safetensors +3 -0
  43. model-00039-of-00044.safetensors +3 -0
  44. model-00040-of-00044.safetensors +3 -0
  45. model-00041-of-00044.safetensors +3 -0
  46. model-00042-of-00044.safetensors +3 -0
  47. model-00043-of-00044.safetensors +3 -0
  48. model-00044-of-00044.safetensors +3 -0
  49. model.safetensors.index.json +649 -0
  50. special_tokens_map.json +23 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,613 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ license: cc-by-nc-4.0
4
+ library_name: transformers
5
+ language:
6
+ - en
7
+ - fr
8
+ - de
9
+ - es
10
+ - it
11
+ - pt
12
+ - ja
13
+ - ko
14
+ - zh
15
+ - ar
16
+ extra_gated_prompt: "By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and acknowledge that the information you provide will be collected, used, and shared in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy)."
17
+ extra_gated_fields:
18
+ Name: text
19
+ Affiliation: text
20
+ Country:
21
+ type: select
22
+ options:
23
+ - Aruba
24
+ - Afghanistan
25
+ - Angola
26
+ - Anguilla
27
+ - Åland Islands
28
+ - Albania
29
+ - Andorra
30
+ - United Arab Emirates
31
+ - Argentina
32
+ - Armenia
33
+ - American Samoa
34
+ - Antarctica
35
+ - French Southern Territories
36
+ - Antigua and Barbuda
37
+ - Australia
38
+ - Austria
39
+ - Azerbaijan
40
+ - Burundi
41
+ - Belgium
42
+ - Benin
43
+ - Bonaire Sint Eustatius and Saba
44
+ - Burkina Faso
45
+ - Bangladesh
46
+ - Bulgaria
47
+ - Bahrain
48
+ - Bahamas
49
+ - Bosnia and Herzegovina
50
+ - Saint Barthélemy
51
+ - Belarus
52
+ - Belize
53
+ - Bermuda
54
+ - Plurinational State of Bolivia
55
+ - Brazil
56
+ - Barbados
57
+ - Brunei-Darussalam
58
+ - Bhutan
59
+ - Bouvet-Island
60
+ - Botswana
61
+ - Central African Republic
62
+ - Canada
63
+ - Cocos (Keeling) Islands
64
+ - Switzerland
65
+ - Chile
66
+ - China
67
+ - Côte-dIvoire
68
+ - Cameroon
69
+ - Democratic Republic of the Congo
70
+ - Cook Islands
71
+ - Colombia
72
+ - Comoros
73
+ - Cabo Verde
74
+ - Costa Rica
75
+ - Cuba
76
+ - Curaçao
77
+ - Christmas Island
78
+ - Cayman Islands
79
+ - Cyprus
80
+ - Czechia
81
+ - Germany
82
+ - Djibouti
83
+ - Dominica
84
+ - Denmark
85
+ - Dominican Republic
86
+ - Algeria
87
+ - Ecuador
88
+ - Egypt
89
+ - Eritrea
90
+ - Western Sahara
91
+ - Spain
92
+ - Estonia
93
+ - Ethiopia
94
+ - Finland
95
+ - Fiji
96
+ - Falkland Islands (Malvinas)
97
+ - France
98
+ - Faroe Islands
99
+ - Federated States of Micronesia
100
+ - Gabon
101
+ - United Kingdom
102
+ - Georgia
103
+ - Guernsey
104
+ - Ghana
105
+ - Gibraltar
106
+ - Guinea
107
+ - Guadeloupe
108
+ - Gambia
109
+ - Guinea Bissau
110
+ - Equatorial Guinea
111
+ - Greece
112
+ - Grenada
113
+ - Greenland
114
+ - Guatemala
115
+ - French Guiana
116
+ - Guam
117
+ - Guyana
118
+ - Hong Kong
119
+ - Heard Island and McDonald Islands
120
+ - Honduras
121
+ - Croatia
122
+ - Haiti
123
+ - Hungary
124
+ - Indonesia
125
+ - Isle of Man
126
+ - India
127
+ - British Indian Ocean Territory
128
+ - Ireland
129
+ - Islamic Republic of Iran
130
+ - Iraq
131
+ - Iceland
132
+ - Israel
133
+ - Italy
134
+ - Jamaica
135
+ - Jersey
136
+ - Jordan
137
+ - Japan
138
+ - Kazakhstan
139
+ - Kenya
140
+ - Kyrgyzstan
141
+ - Cambodia
142
+ - Kiribati
143
+ - Saint-Kitts-and-Nevis
144
+ - South Korea
145
+ - Kuwait
146
+ - Lao-Peoples-Democratic-Republic
147
+ - Lebanon
148
+ - Liberia
149
+ - Libya
150
+ - Saint-Lucia
151
+ - Liechtenstein
152
+ - Sri Lanka
153
+ - Lesotho
154
+ - Lithuania
155
+ - Luxembourg
156
+ - Latvia
157
+ - Macao
158
+ - Saint Martin (French-part)
159
+ - Morocco
160
+ - Monaco
161
+ - Republic of Moldova
162
+ - Madagascar
163
+ - Maldives
164
+ - Mexico
165
+ - Marshall Islands
166
+ - North Macedonia
167
+ - Mali
168
+ - Malta
169
+ - Myanmar
170
+ - Montenegro
171
+ - Mongolia
172
+ - Northern Mariana Islands
173
+ - Mozambique
174
+ - Mauritania
175
+ - Montserrat
176
+ - Martinique
177
+ - Mauritius
178
+ - Malawi
179
+ - Malaysia
180
+ - Mayotte
181
+ - Namibia
182
+ - New Caledonia
183
+ - Niger
184
+ - Norfolk Island
185
+ - Nigeria
186
+ - Nicaragua
187
+ - Niue
188
+ - Netherlands
189
+ - Norway
190
+ - Nepal
191
+ - Nauru
192
+ - New Zealand
193
+ - Oman
194
+ - Pakistan
195
+ - Panama
196
+ - Pitcairn
197
+ - Peru
198
+ - Philippines
199
+ - Palau
200
+ - Papua New Guinea
201
+ - Poland
202
+ - Puerto Rico
203
+ - North Korea
204
+ - Portugal
205
+ - Paraguay
206
+ - State of Palestine
207
+ - French Polynesia
208
+ - Qatar
209
+ - Réunion
210
+ - Romania
211
+ - Russia
212
+ - Rwanda
213
+ - Saudi Arabia
214
+ - Sudan
215
+ - Senegal
216
+ - Singapore
217
+ - South Georgia and the South Sandwich Islands
218
+ - Saint Helena Ascension and Tristan da Cunha
219
+ - Svalbard and Jan Mayen
220
+ - Solomon Islands
221
+ - Sierra Leone
222
+ - El Salvador
223
+ - San Marino
224
+ - Somalia
225
+ - Saint Pierre and Miquelon
226
+ - Serbia
227
+ - South Sudan
228
+ - Sao Tome and Principe
229
+ - Suriname
230
+ - Slovakia
231
+ - Slovenia
232
+ - Sweden
233
+ - Eswatini
234
+ - Sint Maarten (Dutch-part)
235
+ - Seychelles
236
+ - Syrian Arab Republic
237
+ - Turks and Caicos Islands
238
+ - Chad
239
+ - Togo
240
+ - Thailand
241
+ - Tajikistan
242
+ - Tokelau
243
+ - Turkmenistan
244
+ - Timor Leste
245
+ - Tonga
246
+ - Trinidad and Tobago
247
+ - Tunisia
248
+ - Turkey
249
+ - Tuvalu
250
+ - Taiwan
251
+ - United Republic of Tanzania
252
+ - Uganda
253
+ - Ukraine
254
+ - United States Minor Outlying Islands
255
+ - Uruguay
256
+ - United-States
257
+ - Uzbekistan
258
+ - Holy See (Vatican City State)
259
+ - Saint Vincent and the Grenadines
260
+ - Bolivarian Republic of Venezuela
261
+ - Virgin Islands British
262
+ - Virgin Islands U.S.
263
+ - VietNam
264
+ - Vanuatu
265
+ - Wallis and Futuna
266
+ - Samoa
267
+ - Yemen
268
+ - South Africa
269
+ - Zambia
270
+ - Zimbabwe
271
+ Receive email updates on C4AI and Cohere research, events, products and services?:
272
+ type: select
273
+ options:
274
+ - Yes
275
+ - No
276
+ I agree to use this model for non-commercial use ONLY: checkbox
277
+ ---
278
+
279
+ # Model Card for C4AI Command R+ 08-2024
280
+
281
+ ## Model Summary
282
+ C4AI Command R+ 08-2024 is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. The tool use in this model generation enables multi-step tool use which allows the model to combine multiple tools over multiple steps to accomplish difficult tasks. C4AI Command R+ 08-2024 is a multilingual model trained on 23 languages and evaluated in 10 languages. Command R+ 08-2024 is optimized for a variety of use cases including reasoning, summarization, and question answering.
283
+
284
+ C4AI Command R+ 08-2024 is part of a family of open weight releases from Cohere For AI and Cohere. Our smaller companion model is [C4AI Command R 08-2024](https://huggingface.co/CohereForAI/c4ai-command-r-08-2024).
285
+
286
+ - Point of Contact: Cohere For AI: [cohere.for.ai](https://cohere.for.ai/)
287
+ - License: [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license), requires also adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy)
288
+ - Model: c4ai-command-r-plus-08-2024
289
+ - Model Size: 104 billion parameters
290
+ - Context length: 128K
291
+
292
+ **Try C4AI Command R+**
293
+
294
+ You can try out C4AI Command R+ before downloading the weights in our hosted [Hugging Face Space](https://huggingface.co/spaces/CohereForAI/c4ai-command?model=command-r-plus-08-2024).
295
+
296
+ **Usage**
297
+
298
+ Please use `transformers` version 4.39.1 or higher
299
+ ```python
300
+ # pip install 'transformers>=4.39.1'
301
+ from transformers import AutoTokenizer, AutoModelForCausalLM
302
+
303
+ model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
304
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
305
+ model = AutoModelForCausalLM.from_pretrained(model_id)
306
+
307
+ # Format message with the command-r-plus-08-2024 chat template
308
+ messages = [{"role": "user", "content": "Hello, how are you?"}]
309
+ input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
310
+ ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
311
+
312
+ gen_tokens = model.generate(
313
+ input_ids,
314
+ max_new_tokens=100,
315
+ do_sample=True,
316
+ temperature=0.3,
317
+ )
318
+
319
+ gen_text = tokenizer.decode(gen_tokens[0])
320
+ print(gen_text)
321
+ ```
322
+
323
+ ## Model Details
324
+
325
+ **Input**: Models input text only.
326
+
327
+ **Output**: Models generate text only.
328
+
329
+ **Model Architecture**: This is an auto-regressive language model that uses an optimized transformer architecture. After pretraining, this model uses supervised fine-tuning (SFT) and preference training to align model behavior to human preferences for helpfulness and safety. We use grouped query attention (GQA) to improve inference speed.
330
+
331
+ **Languages covered**: The model has been trained on 23 languages (English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Simplified Chinese, Russian, Polish, Turkish, Vietnamese, Dutch, Czech, Indonesian, Ukrainian, Romanian, Greek, Hindi, Hebrew, and Persian) and evaluated on 10 languages (English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Arabic, Simplified Chinese).
332
+
333
+ **Context length**: Command R+ 08-2024 supports a context length of 128K.
334
+
335
+
336
+ ### Tool use & Agent capabilities:
337
+
338
+ Command R+ 08-2024 has been specifically trained with conversational tool use capabilities. These have been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template will likely reduce performance, but we encourage experimentation.
339
+
340
+ Command R+ 08-2024’s tool use functionality takes a conversation as input (with an optional user-system preamble), along with a list of available tools. The model will then generate a json-formatted list of actions to execute on a subset of those tools. Command R+ 08-2024 may use one of its supplied tools more than once.
341
+
342
+ The model has been trained to recognise a special `directly_answer` tool, which it uses to indicate that it doesn’t want to use any of its other tools. The ability to abstain from calling a specific tool can be useful in a range of situations, such as greeting a user, or asking clarifying questions. We recommend including the `directly_answer` tool, but it can be removed or renamed if required.
343
+
344
+ Comprehensive documentation for working with Command R+ 08-2024's tool use prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r).
345
+
346
+ Command R+ 08-2024 also supports Hugging Face's [tool use API](https://huggingface.co/docs/transformers/main/en/chat_templating#advanced-tool-use--function-calling).
347
+
348
+ The code snippets below show minimal working examples on how to render a prompt.
349
+
350
+ <details>
351
+ <summary><b>Usage: Rendering Tool Use Prompts [CLICK TO EXPAND]</b> </summary>
352
+
353
+ ```python
354
+ from transformers import AutoTokenizer
355
+
356
+ model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
357
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
358
+
359
+ # define conversation input:
360
+ conversation = [
361
+ {"role": "user", "content": "Whats the biggest penguin in the world?"}
362
+ ]
363
+ # Define tools available for the model to use:
364
+ tools = [
365
+ {
366
+ "name": "internet_search",
367
+ "description": "Returns a list of relevant document snippets for a textual query retrieved from the internet",
368
+ "parameter_definitions": {
369
+ "query": {
370
+ "description": "Query to search the internet with",
371
+ "type": 'str',
372
+ "required": True
373
+ }
374
+ }
375
+ },
376
+ {
377
+ 'name': "directly_answer",
378
+ "description": "Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history",
379
+ 'parameter_definitions': {}
380
+ }
381
+ ]
382
+
383
+ # render the tool use prompt as a string:
384
+ tool_use_prompt = tokenizer.apply_tool_use_template(
385
+ conversation,
386
+ tools=tools,
387
+ tokenize=False,
388
+ add_generation_prompt=True,
389
+ )
390
+ print(tool_use_prompt)
391
+ ```
392
+
393
+ </details>
394
+
395
+
396
+ <details>
397
+ <summary><b>Usage: Rendering prompts with the Tool Use API [CLICK TO EXPAND]</b> </summary>
398
+
399
+ ```python
400
+ from transformers import AutoTokenizer
401
+
402
+ model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
403
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
404
+
405
+ # define conversation input:
406
+ conversation = [
407
+ {"role": "user", "content": "Whats the biggest penguin in the world?"}
408
+ ]
409
+
410
+ # Define tools available for the model to use
411
+ # Type hints and docstrings from Python functions are automatically extracted
412
+ def internet_search(query: str):
413
+ """
414
+ Returns a list of relevant document snippets for a textual query retrieved from the internet
415
+
416
+ Args:
417
+ query: Query to search the internet with
418
+ """
419
+ pass
420
+
421
+ def directly_answer():
422
+ """
423
+ Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history
424
+ """
425
+ pass
426
+
427
+ tools = [internet_search, directly_answer]
428
+
429
+ # render the tool use prompt as a string:
430
+ tool_use_prompt = tokenizer.apply_chat_template(
431
+ conversation,
432
+ tools=tools,
433
+ tokenize=False,
434
+ add_generation_prompt=True,
435
+ )
436
+ print(tool_use_prompt)
437
+ ```
438
+
439
+ </details>
440
+
441
+ <details>
442
+ <summary><b>Example Rendered Tool Use Prompt [CLICK TO EXPAND]</b></summary>
443
+
444
+ ````
445
+ <BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
446
+ The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
447
+
448
+ # System Preamble
449
+ ## Basic Rules
450
+ You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
451
+
452
+ # User Preamble
453
+ ## Task and Context
454
+ You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
455
+
456
+ ## Style Guide
457
+ Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.
458
+
459
+ ## Available Tools
460
+ Here is a list of tools that you have available to you:
461
+
462
+ ```python
463
+ def internet_search(query: str) -> List[Dict]:
464
+ """Returns a list of relevant document snippets for a textual query retrieved from the internet
465
+
466
+ Args:
467
+ query (str): Query to search the internet with
468
+ """
469
+ pass
470
+ ```
471
+
472
+ ```python
473
+ def directly_answer() -> List[Dict]:
474
+ """Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history
475
+ """
476
+ pass
477
+ ```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:
478
+ ```json
479
+ [
480
+ {
481
+ "tool_name": title of the tool in the specification,
482
+ "parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters
483
+ }
484
+ ]```<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
485
+ ````
486
+
487
+ </details>
488
+
489
+
490
+ <details>
491
+ <summary><b>Example Rendered Tool Use Completion [CLICK TO EXPAND]</b></summary>
492
+
493
+ ````
494
+ Action: ```json
495
+ [
496
+ {
497
+ "tool_name": "internet_search",
498
+ "parameters": {
499
+ "query": "biggest penguin in the world"
500
+ }
501
+ }
502
+ ]
503
+ ```
504
+ ````
505
+ </details>
506
+
507
+
508
+ ### Grounded Generation and RAG Capabilities:
509
+
510
+ Command R+ 08-2024 has been specifically trained with grounded generation capabilities. This means that it can generate responses based on a list of supplied document snippets, and it will include grounding spans (citations) in its response indicating the source of the information. This can be used to enable behaviors such as grounded summarization and the final step of Retrieval Augmented Generation (RAG). This behavior has been trained into the model via a mixture of supervised fine-tuning and preference fine-tuning, using a specific prompt template. Deviating from this prompt template may reduce performance, but we encourage experimentation.
511
+
512
+ Command R+ 08-2024’s grounded generation behavior takes a conversation as input (with an optional user-supplied system preamble, indicating task, context and desired output style), along with a list of retrieved document snippets. The document snippets should be chunks, rather than long documents, typically around 100-400 words per chunk. Document snippets consist of key-value pairs. The keys should be short descriptive strings, the values can be text or semi-structured.
513
+
514
+ By default, Command R+ 08-2024 will generate grounded responses by first predicting which documents are relevant, then predicting which ones it will cite, then generating an answer. Finally, it will then insert grounding spans into the answer. See below for an example. This is referred to as `accurate` grounded generation.
515
+
516
+ The model is trained with a number of other answering modes, which can be selected by prompt changes. A `fast` citation mode is supported in the tokenizer, which will directly generate an answer with grounding spans in it, without first writing the answer out in full. This sacrifices some grounding accuracy in favor of generating fewer tokens.
517
+
518
+ Comprehensive documentation for working with Command R+ 08-2024's grounded generation prompt template can be found [here](https://docs.cohere.com/docs/prompting-command-r).
519
+
520
+ The code snippet below shows a minimal working example on how to render a prompt.
521
+
522
+ <details>
523
+ <summary> <b>Usage: Rendering Grounded Generation prompts [CLICK TO EXPAND]</b> </summary>
524
+
525
+ ````python
526
+ from transformers import AutoTokenizer
527
+
528
+ model_id = "CohereForAI/c4ai-command-r-plus-08-2024"
529
+ tokenizer = AutoTokenizer.from_pretrained(model_id)
530
+
531
+ # define conversation input:
532
+ conversation = [
533
+ {"role": "user", "content": "Whats the biggest penguin in the world?"}
534
+ ]
535
+ # define documents to ground on:
536
+ documents = [
537
+ { "title": "Tall penguins", "text": "Emperor penguins are the tallest growing up to 122 cm in height." },
538
+ { "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica."}
539
+ ]
540
+
541
+ # render the tool use prompt as a string:
542
+ grounded_generation_prompt = tokenizer.apply_grounded_generation_template(
543
+ conversation,
544
+ documents=documents,
545
+ citation_mode="accurate", # or "fast"
546
+ tokenize=False,
547
+ add_generation_prompt=True,
548
+ )
549
+ print(grounded_generation_prompt)
550
+ ````
551
+
552
+ </details>
553
+
554
+ <details>
555
+ <summary><b>Example Rendered Grounded Generation Prompt [CLICK TO EXPAND]</b></summary>
556
+
557
+ ````
558
+ <BOS_TOKEN><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
559
+ The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
560
+
561
+ # System Preamble
562
+ ## Basic Rules
563
+ You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
564
+
565
+ # User Preamble
566
+ ## Task and Context
567
+ You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
568
+
569
+ ## Style Guide
570
+ Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|><results>
571
+ Document: 0
572
+ title: Tall penguins
573
+ text: Emperor penguins are the tallest growing up to 122 cm in height.
574
+
575
+ Document: 1
576
+ title: Penguin habitats
577
+ text: Emperor penguins only live in Antarctica.
578
+ </results><|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Carefully perform the following instructions, in order, starting each with a new line.
579
+ Firstly, Decide which of the retrieved documents are relevant to the user's last input by writing 'Relevant Documents:' followed by comma-separated list of document numbers. If none are relevant, you should instead write 'None'.
580
+ Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user's last input by writing 'Cited Documents:' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write 'None'.
581
+ Thirdly, Write 'Answer:' followed by a response to the user's last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.
582
+ Finally, Write 'Grounded answer:' followed by a response to the user's last input in high quality natural english. Use the symbols <co: doc> and </co: doc> to indicate when a fact comes from a document in the search result, e.g <co: 0>my fact</co: 0> for a fact from document 0.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
583
+ ````
584
+
585
+ </details>
586
+
587
+
588
+
589
+ <details>
590
+ <summary><b>Example Rendered Grounded Generation Completion [CLICK TO EXPAND]</b></summary>
591
+
592
+ ````
593
+ Relevant Documents: 0,1
594
+ Cited Documents: 0,1
595
+ Answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres.
596
+ Grounded answer: The <co: 0>Emperor Penguin</co: 0> is the <co: 0>tallest</co: 0> or biggest penguin in the world. It is a bird that <co: 1>lives only in Antarctica</co: 1> and <co: 0>grows to a height of around 122 centimetres.</co: 0>
597
+ ````
598
+
599
+ </details>
600
+
601
+
602
+ ### Code Capabilities:
603
+ Command R+ 08-2024 has been optimized to interact with your code, by requesting code snippets, code explanations, or code rewrites. It might not perform well out-of-the-box for pure code completion. For better performance, we also recommend using a low temperature (and even greedy decoding) for code-generation related instructions.
604
+
605
+ ### Model Card Contact
606
+ For errors or additional questions about details in this model card, contact [[email protected]](mailto:[email protected]).
607
+
608
+ ### Terms of Use:
609
+ We hope that the release of this model will make community-based research efforts more accessible, by releasing the weights of a highly performant 104 billion parameter model to researchers all over the world. This model is governed by a [CC-BY-NC](https://cohere.com/c4ai-cc-by-nc-license) License with an acceptable use addendum, and also requires adhering to [C4AI's Acceptable Use Policy](https://docs.cohere.com/docs/c4ai-acceptable-use-policy).
610
+
611
+ ### Try Chat:
612
+ You can try Command R+ 08-2024 chat in the playground [here](https://dashboard.cohere.com/playground/chat). You can also use it in our dedicated Hugging Face Space [here](https://huggingface.co/spaces/CohereForAI/c4ai-command?model=command-r-plus-08-2024).
613
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CohereForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 5,
8
+ "eos_token_id": 255001,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 12288,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 33792,
13
+ "layer_norm_eps": 1e-05,
14
+ "logit_scale": 0.8333333333333334,
15
+ "max_position_embeddings": 131072,
16
+ "model_type": "cohere",
17
+ "num_attention_heads": 96,
18
+ "num_hidden_layers": 64,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "rope_theta": 8000000,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.44.0",
24
+ "use_cache": true,
25
+ "use_qk_norm": true,
26
+ "vocab_size": 256000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "eos_token_id": 255001,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.0"
7
+ }
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071e9a038e622245778f441975fa8fa7989641667a4a65e6747d5a82d99adb69
3
+ size 6291456144
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbafb79533af8545b58d7d0612fefeced4ac895be1a40c3802f9d8a584d9ffbe
3
+ size 4630591424
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4448a1f30a0965d23b921a0a42218b61d6def855f51cf35da3031f28866a2f54
3
+ size 4806776520
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01567606c2718a1172cb94b3950ff7a978f45f25a65d622a1f342120d2e3121
3
+ size 4630564576
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a3a61c30efaf7ccff0f8194896155fcd407989130460098e36027bb756faa4
3
+ size 4806776520
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6dc6e59b67aaec86d7ae44d6820c0b713954582e5a37b848a6f260131819d09
3
+ size 4630564576
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf76f1b634e1989d6c20e506b473f5e403c338348157d2ec47f89608616ba22e
3
+ size 4806776520
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08be0fbc10add051a68f3c9cbe5b13539dda1753b22c012a4992e67842aba3a5
3
+ size 4630564584
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ac459ad3463e4091de9243a45e612c14510cc86f483ac01cfdbdc6f33ce73b
3
+ size 4806776536
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db96a03d2ce6cf315dfbafa52e960f70ddba48894870cccee394298d80803c0
3
+ size 4630564584
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a34ea0c6d30dde6c389d9195daa2534b6ed5715547e4090682cfc8facb92e0
3
+ size 4806776536
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e38c798f633ff77c2db35525ef99c3cd0790e11ebba76e29b09b1b983cdb12
3
+ size 4630564584
model-00013-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0762d678925758ea27f44bf4e4111bfdf56e7f7d1483e598021d576d81a27c6
3
+ size 4806776536
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22a30fdc51609faa6e3ad59eb9fdf42133551a5e821a8d16a1083b2c96393d2c
3
+ size 4630564584
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4955f09ad506c601956d1fa284880bb543f58bfdc8ff98ebfcd15c9c6d2d74df
3
+ size 4806776536
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6295146ac15cf33329c9395e99c0bf2399620c327211a673b42c351ab3158262
3
+ size 4630564584
model-00017-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:889e37435a6258a19c892d82485efcca02ea4368e4e911851094043f605754d3
3
+ size 4806776536
model-00018-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bea907c8b1e5e53e068c75ca1de101cbe892064f2c7dbf2ebf667cd794a2c4
3
+ size 4630564584
model-00019-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7995cad14fc8c3d964a576481844ad3cc54e632b8ded1a14776f3235ceafbe75
3
+ size 4806776536
model-00020-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd15b7d1608b9c4497bc202cf249f9b455187a69172e9d4879916ebc10298af
3
+ size 4630564584
model-00021-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1362162accb51043b390b9f8ae8e8ea5fa01db10df172c67ab2a2d0d32bbd8dc
3
+ size 4806776536
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755c1b94270174cf3f227dc9049139e65ede7b968dee60413f4fd7517424df20
3
+ size 4630564584
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1657042b99093b423a9c3d9a153830d1a9c7e5b7b9490dc6ef7839e7f03211da
3
+ size 4806776536
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1097b00e67c0054be6b01e415389c10eda81b227c7bcb7fa7804ddbfb2bca5a8
3
+ size 4630564584
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a65c2ac23670d35bbfce1ed4cde7b8a5aaf2203ad0026853ac59153e2b37d1
3
+ size 4806776536
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9635dea40ed9e8ed5926458b0bd18f8280da4bbf3c2316059bbb7cd7c829a1c1
3
+ size 4630564584
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac337f200921ee85b22f92418b3c666e850998e14cc74a8bd86e78e4a813504d
3
+ size 4806776536
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8da6352e3da86630a953e8324c823ffe073666a43465b6119c96710ab9451b61
3
+ size 4630564584
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cc0274cc2766f504bdfdb4feb2b89acf9fdd6799d374df533d447f90bfbd68
3
+ size 4806776536
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4131ecc17e89c259443f2d24d4b8cdbb39e78316944ae0685e419d37a2b15c2
3
+ size 4630564584
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f1c6b49c49a8fbe74869655f428e3dcae42d3973013e6c191cf33c9018e5a8f
3
+ size 4806776536
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0782e3106f9523ea1892c9c0609d648b94b6d7236f70f6d34a9dea4f0cfc5f05
3
+ size 4630564584
model-00033-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1706c7f1c6e5639e6ca212798bbc535e71171c2b9e77122a2311ced33f85e72
3
+ size 4806776536
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:559ab9dd027340f29204b28f5f1187cb2a5722152db31b92d7d7726e49dac85f
3
+ size 4630564584
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b437b2501bf1b1b6b145aed10539993dd78d6790d035396318b7d2d3b34cd42
3
+ size 4806776536
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a426ed7754be31f8c77872e13d7e7b647c01e4a4b8429cc4dafe56604abbd853
3
+ size 4630564584
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318d30546512215e19638bcc20b75239455d6bc951a64344dae37c5358038173
3
+ size 4806776536
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0af099491d5b9d3161126e7e5d22f7628749442eea79b3d59050d186171401
3
+ size 4630564584
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c96c381d4bd4cf4da800f00e9257b01cb3ac50b6fed43298cc3867133df33d9f
3
+ size 4806776536
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0e78808a880a92ea25ffe79fadb52323ff85d2e7f26458b8f337f54b294dfd
3
+ size 4630564584
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:109888158931bea8318a1509c1755ded869ab0e33a1b05ff7ef35f740a0fcb11
3
+ size 4806776536
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc2bb000de70774a0ff918a6e36cec2100ffd5f7da7d3e7d0401cf50d9172b2d
3
+ size 4630564584
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c08d9f427eb4895fb53ca28df1b3781b85514f797fccd033f130561d8420fdec
3
+ size 4806776536
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2abc1e86e38940514f0ed03bb05bffc2bdd149a5e52cb49207565c505a00cf42
3
+ size 3145778200
model.safetensors.index.json ADDED
@@ -0,0 +1,649 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 207621349376
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00044.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00002-of-00044.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00002-of-00044.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00044.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00002-of-00044.safetensors",
11
+ "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00044.safetensors",
12
+ "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00044.safetensors",
13
+ "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00044.safetensors",
14
+ "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00044.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00044.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00044.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00003-of-00044.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00003-of-00044.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00044.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00003-of-00044.safetensors",
21
+ "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00044.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00044.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00044.safetensors",
24
+ "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00044.safetensors",
25
+ "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00044.safetensors",
26
+ "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00044.safetensors",
27
+ "model.layers.10.input_layernorm.weight": "model-00009-of-00044.safetensors",
28
+ "model.layers.10.mlp.down_proj.weight": "model-00009-of-00044.safetensors",
29
+ "model.layers.10.mlp.gate_proj.weight": "model-00008-of-00044.safetensors",
30
+ "model.layers.10.mlp.up_proj.weight": "model-00009-of-00044.safetensors",
31
+ "model.layers.10.self_attn.k_norm.weight": "model-00008-of-00044.safetensors",
32
+ "model.layers.10.self_attn.k_proj.weight": "model-00008-of-00044.safetensors",
33
+ "model.layers.10.self_attn.o_proj.weight": "model-00008-of-00044.safetensors",
34
+ "model.layers.10.self_attn.q_norm.weight": "model-00008-of-00044.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00008-of-00044.safetensors",
36
+ "model.layers.10.self_attn.v_proj.weight": "model-00008-of-00044.safetensors",
37
+ "model.layers.11.input_layernorm.weight": "model-00009-of-00044.safetensors",
38
+ "model.layers.11.mlp.down_proj.weight": "model-00009-of-00044.safetensors",
39
+ "model.layers.11.mlp.gate_proj.weight": "model-00009-of-00044.safetensors",
40
+ "model.layers.11.mlp.up_proj.weight": "model-00009-of-00044.safetensors",
41
+ "model.layers.11.self_attn.k_norm.weight": "model-00009-of-00044.safetensors",
42
+ "model.layers.11.self_attn.k_proj.weight": "model-00009-of-00044.safetensors",
43
+ "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00044.safetensors",
44
+ "model.layers.11.self_attn.q_norm.weight": "model-00009-of-00044.safetensors",
45
+ "model.layers.11.self_attn.q_proj.weight": "model-00009-of-00044.safetensors",
46
+ "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00044.safetensors",
47
+ "model.layers.12.input_layernorm.weight": "model-00010-of-00044.safetensors",
48
+ "model.layers.12.mlp.down_proj.weight": "model-00010-of-00044.safetensors",
49
+ "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00044.safetensors",
50
+ "model.layers.12.mlp.up_proj.weight": "model-00010-of-00044.safetensors",
51
+ "model.layers.12.self_attn.k_norm.weight": "model-00009-of-00044.safetensors",
52
+ "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00044.safetensors",
53
+ "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",
54
+ "model.layers.12.self_attn.q_norm.weight": "model-00009-of-00044.safetensors",
55
+ "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00044.safetensors",
56
+ "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00044.safetensors",
57
+ "model.layers.13.input_layernorm.weight": "model-00011-of-00044.safetensors",
58
+ "model.layers.13.mlp.down_proj.weight": "model-00011-of-00044.safetensors",
59
+ "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00044.safetensors",
60
+ "model.layers.13.mlp.up_proj.weight": "model-00011-of-00044.safetensors",
61
+ "model.layers.13.self_attn.k_norm.weight": "model-00010-of-00044.safetensors",
62
+ "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00044.safetensors",
63
+ "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",
64
+ "model.layers.13.self_attn.q_norm.weight": "model-00010-of-00044.safetensors",
65
+ "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00044.safetensors",
66
+ "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00044.safetensors",
67
+ "model.layers.14.input_layernorm.weight": "model-00011-of-00044.safetensors",
68
+ "model.layers.14.mlp.down_proj.weight": "model-00011-of-00044.safetensors",
69
+ "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00044.safetensors",
70
+ "model.layers.14.mlp.up_proj.weight": "model-00011-of-00044.safetensors",
71
+ "model.layers.14.self_attn.k_norm.weight": "model-00011-of-00044.safetensors",
72
+ "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00044.safetensors",
73
+ "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00044.safetensors",
74
+ "model.layers.14.self_attn.q_norm.weight": "model-00011-of-00044.safetensors",
75
+ "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00044.safetensors",
76
+ "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00044.safetensors",
77
+ "model.layers.15.input_layernorm.weight": "model-00012-of-00044.safetensors",
78
+ "model.layers.15.mlp.down_proj.weight": "model-00012-of-00044.safetensors",
79
+ "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00044.safetensors",
80
+ "model.layers.15.mlp.up_proj.weight": "model-00012-of-00044.safetensors",
81
+ "model.layers.15.self_attn.k_norm.weight": "model-00011-of-00044.safetensors",
82
+ "model.layers.15.self_attn.k_proj.weight": "model-00012-of-00044.safetensors",
83
+ "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",
84
+ "model.layers.15.self_attn.q_norm.weight": "model-00011-of-00044.safetensors",
85
+ "model.layers.15.self_attn.q_proj.weight": "model-00012-of-00044.safetensors",
86
+ "model.layers.15.self_attn.v_proj.weight": "model-00012-of-00044.safetensors",
87
+ "model.layers.16.input_layernorm.weight": "model-00013-of-00044.safetensors",
88
+ "model.layers.16.mlp.down_proj.weight": "model-00013-of-00044.safetensors",
89
+ "model.layers.16.mlp.gate_proj.weight": "model-00012-of-00044.safetensors",
90
+ "model.layers.16.mlp.up_proj.weight": "model-00013-of-00044.safetensors",
91
+ "model.layers.16.self_attn.k_norm.weight": "model-00012-of-00044.safetensors",
92
+ "model.layers.16.self_attn.k_proj.weight": "model-00012-of-00044.safetensors",
93
+ "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",
94
+ "model.layers.16.self_attn.q_norm.weight": "model-00012-of-00044.safetensors",
95
+ "model.layers.16.self_attn.q_proj.weight": "model-00012-of-00044.safetensors",
96
+ "model.layers.16.self_attn.v_proj.weight": "model-00012-of-00044.safetensors",
97
+ "model.layers.17.input_layernorm.weight": "model-00013-of-00044.safetensors",
98
+ "model.layers.17.mlp.down_proj.weight": "model-00013-of-00044.safetensors",
99
+ "model.layers.17.mlp.gate_proj.weight": "model-00013-of-00044.safetensors",
100
+ "model.layers.17.mlp.up_proj.weight": "model-00013-of-00044.safetensors",
101
+ "model.layers.17.self_attn.k_norm.weight": "model-00013-of-00044.safetensors",
102
+ "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00044.safetensors",
103
+ "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00044.safetensors",
104
+ "model.layers.17.self_attn.q_norm.weight": "model-00013-of-00044.safetensors",
105
+ "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00044.safetensors",
106
+ "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00044.safetensors",
107
+ "model.layers.18.input_layernorm.weight": "model-00014-of-00044.safetensors",
108
+ "model.layers.18.mlp.down_proj.weight": "model-00014-of-00044.safetensors",
109
+ "model.layers.18.mlp.gate_proj.weight": "model-00014-of-00044.safetensors",
110
+ "model.layers.18.mlp.up_proj.weight": "model-00014-of-00044.safetensors",
111
+ "model.layers.18.self_attn.k_norm.weight": "model-00013-of-00044.safetensors",
112
+ "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00044.safetensors",
113
+ "model.layers.18.self_attn.o_proj.weight": "model-00014-of-00044.safetensors",
114
+ "model.layers.18.self_attn.q_norm.weight": "model-00013-of-00044.safetensors",
115
+ "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00044.safetensors",
116
+ "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00044.safetensors",
117
+ "model.layers.19.input_layernorm.weight": "model-00015-of-00044.safetensors",
118
+ "model.layers.19.mlp.down_proj.weight": "model-00015-of-00044.safetensors",
119
+ "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00044.safetensors",
120
+ "model.layers.19.mlp.up_proj.weight": "model-00015-of-00044.safetensors",
121
+ "model.layers.19.self_attn.k_norm.weight": "model-00014-of-00044.safetensors",
122
+ "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00044.safetensors",
123
+ "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00044.safetensors",
124
+ "model.layers.19.self_attn.q_norm.weight": "model-00014-of-00044.safetensors",
125
+ "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00044.safetensors",
126
+ "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00044.safetensors",
127
+ "model.layers.2.input_layernorm.weight": "model-00003-of-00044.safetensors",
128
+ "model.layers.2.mlp.down_proj.weight": "model-00003-of-00044.safetensors",
129
+ "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00044.safetensors",
130
+ "model.layers.2.mlp.up_proj.weight": "model-00003-of-00044.safetensors",
131
+ "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00044.safetensors",
132
+ "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00044.safetensors",
133
+ "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00044.safetensors",
134
+ "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00044.safetensors",
135
+ "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00044.safetensors",
136
+ "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00044.safetensors",
137
+ "model.layers.20.input_layernorm.weight": "model-00015-of-00044.safetensors",
138
+ "model.layers.20.mlp.down_proj.weight": "model-00015-of-00044.safetensors",
139
+ "model.layers.20.mlp.gate_proj.weight": "model-00015-of-00044.safetensors",
140
+ "model.layers.20.mlp.up_proj.weight": "model-00015-of-00044.safetensors",
141
+ "model.layers.20.self_attn.k_norm.weight": "model-00015-of-00044.safetensors",
142
+ "model.layers.20.self_attn.k_proj.weight": "model-00015-of-00044.safetensors",
143
+ "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00044.safetensors",
144
+ "model.layers.20.self_attn.q_norm.weight": "model-00015-of-00044.safetensors",
145
+ "model.layers.20.self_attn.q_proj.weight": "model-00015-of-00044.safetensors",
146
+ "model.layers.20.self_attn.v_proj.weight": "model-00015-of-00044.safetensors",
147
+ "model.layers.21.input_layernorm.weight": "model-00016-of-00044.safetensors",
148
+ "model.layers.21.mlp.down_proj.weight": "model-00016-of-00044.safetensors",
149
+ "model.layers.21.mlp.gate_proj.weight": "model-00016-of-00044.safetensors",
150
+ "model.layers.21.mlp.up_proj.weight": "model-00016-of-00044.safetensors",
151
+ "model.layers.21.self_attn.k_norm.weight": "model-00015-of-00044.safetensors",
152
+ "model.layers.21.self_attn.k_proj.weight": "model-00016-of-00044.safetensors",
153
+ "model.layers.21.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",
154
+ "model.layers.21.self_attn.q_norm.weight": "model-00015-of-00044.safetensors",
155
+ "model.layers.21.self_attn.q_proj.weight": "model-00016-of-00044.safetensors",
156
+ "model.layers.21.self_attn.v_proj.weight": "model-00016-of-00044.safetensors",
157
+ "model.layers.22.input_layernorm.weight": "model-00017-of-00044.safetensors",
158
+ "model.layers.22.mlp.down_proj.weight": "model-00017-of-00044.safetensors",
159
+ "model.layers.22.mlp.gate_proj.weight": "model-00016-of-00044.safetensors",
160
+ "model.layers.22.mlp.up_proj.weight": "model-00017-of-00044.safetensors",
161
+ "model.layers.22.self_attn.k_norm.weight": "model-00016-of-00044.safetensors",
162
+ "model.layers.22.self_attn.k_proj.weight": "model-00016-of-00044.safetensors",
163
+ "model.layers.22.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",
164
+ "model.layers.22.self_attn.q_norm.weight": "model-00016-of-00044.safetensors",
165
+ "model.layers.22.self_attn.q_proj.weight": "model-00016-of-00044.safetensors",
166
+ "model.layers.22.self_attn.v_proj.weight": "model-00016-of-00044.safetensors",
167
+ "model.layers.23.input_layernorm.weight": "model-00017-of-00044.safetensors",
168
+ "model.layers.23.mlp.down_proj.weight": "model-00017-of-00044.safetensors",
169
+ "model.layers.23.mlp.gate_proj.weight": "model-00017-of-00044.safetensors",
170
+ "model.layers.23.mlp.up_proj.weight": "model-00017-of-00044.safetensors",
171
+ "model.layers.23.self_attn.k_norm.weight": "model-00017-of-00044.safetensors",
172
+ "model.layers.23.self_attn.k_proj.weight": "model-00017-of-00044.safetensors",
173
+ "model.layers.23.self_attn.o_proj.weight": "model-00017-of-00044.safetensors",
174
+ "model.layers.23.self_attn.q_norm.weight": "model-00017-of-00044.safetensors",
175
+ "model.layers.23.self_attn.q_proj.weight": "model-00017-of-00044.safetensors",
176
+ "model.layers.23.self_attn.v_proj.weight": "model-00017-of-00044.safetensors",
177
+ "model.layers.24.input_layernorm.weight": "model-00018-of-00044.safetensors",
178
+ "model.layers.24.mlp.down_proj.weight": "model-00018-of-00044.safetensors",
179
+ "model.layers.24.mlp.gate_proj.weight": "model-00018-of-00044.safetensors",
180
+ "model.layers.24.mlp.up_proj.weight": "model-00018-of-00044.safetensors",
181
+ "model.layers.24.self_attn.k_norm.weight": "model-00017-of-00044.safetensors",
182
+ "model.layers.24.self_attn.k_proj.weight": "model-00018-of-00044.safetensors",
183
+ "model.layers.24.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",
184
+ "model.layers.24.self_attn.q_norm.weight": "model-00017-of-00044.safetensors",
185
+ "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00044.safetensors",
186
+ "model.layers.24.self_attn.v_proj.weight": "model-00018-of-00044.safetensors",
187
+ "model.layers.25.input_layernorm.weight": "model-00019-of-00044.safetensors",
188
+ "model.layers.25.mlp.down_proj.weight": "model-00019-of-00044.safetensors",
189
+ "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00044.safetensors",
190
+ "model.layers.25.mlp.up_proj.weight": "model-00019-of-00044.safetensors",
191
+ "model.layers.25.self_attn.k_norm.weight": "model-00018-of-00044.safetensors",
192
+ "model.layers.25.self_attn.k_proj.weight": "model-00018-of-00044.safetensors",
193
+ "model.layers.25.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",
194
+ "model.layers.25.self_attn.q_norm.weight": "model-00018-of-00044.safetensors",
195
+ "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00044.safetensors",
196
+ "model.layers.25.self_attn.v_proj.weight": "model-00018-of-00044.safetensors",
197
+ "model.layers.26.input_layernorm.weight": "model-00019-of-00044.safetensors",
198
+ "model.layers.26.mlp.down_proj.weight": "model-00019-of-00044.safetensors",
199
+ "model.layers.26.mlp.gate_proj.weight": "model-00019-of-00044.safetensors",
200
+ "model.layers.26.mlp.up_proj.weight": "model-00019-of-00044.safetensors",
201
+ "model.layers.26.self_attn.k_norm.weight": "model-00019-of-00044.safetensors",
202
+ "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00044.safetensors",
203
+ "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00044.safetensors",
204
+ "model.layers.26.self_attn.q_norm.weight": "model-00019-of-00044.safetensors",
205
+ "model.layers.26.self_attn.q_proj.weight": "model-00019-of-00044.safetensors",
206
+ "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00044.safetensors",
207
+ "model.layers.27.input_layernorm.weight": "model-00020-of-00044.safetensors",
208
+ "model.layers.27.mlp.down_proj.weight": "model-00020-of-00044.safetensors",
209
+ "model.layers.27.mlp.gate_proj.weight": "model-00020-of-00044.safetensors",
210
+ "model.layers.27.mlp.up_proj.weight": "model-00020-of-00044.safetensors",
211
+ "model.layers.27.self_attn.k_norm.weight": "model-00019-of-00044.safetensors",
212
+ "model.layers.27.self_attn.k_proj.weight": "model-00020-of-00044.safetensors",
213
+ "model.layers.27.self_attn.o_proj.weight": "model-00020-of-00044.safetensors",
214
+ "model.layers.27.self_attn.q_norm.weight": "model-00019-of-00044.safetensors",
215
+ "model.layers.27.self_attn.q_proj.weight": "model-00020-of-00044.safetensors",
216
+ "model.layers.27.self_attn.v_proj.weight": "model-00020-of-00044.safetensors",
217
+ "model.layers.28.input_layernorm.weight": "model-00021-of-00044.safetensors",
218
+ "model.layers.28.mlp.down_proj.weight": "model-00021-of-00044.safetensors",
219
+ "model.layers.28.mlp.gate_proj.weight": "model-00020-of-00044.safetensors",
220
+ "model.layers.28.mlp.up_proj.weight": "model-00021-of-00044.safetensors",
221
+ "model.layers.28.self_attn.k_norm.weight": "model-00020-of-00044.safetensors",
222
+ "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00044.safetensors",
223
+ "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00044.safetensors",
224
+ "model.layers.28.self_attn.q_norm.weight": "model-00020-of-00044.safetensors",
225
+ "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00044.safetensors",
226
+ "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00044.safetensors",
227
+ "model.layers.29.input_layernorm.weight": "model-00021-of-00044.safetensors",
228
+ "model.layers.29.mlp.down_proj.weight": "model-00021-of-00044.safetensors",
229
+ "model.layers.29.mlp.gate_proj.weight": "model-00021-of-00044.safetensors",
230
+ "model.layers.29.mlp.up_proj.weight": "model-00021-of-00044.safetensors",
231
+ "model.layers.29.self_attn.k_norm.weight": "model-00021-of-00044.safetensors",
232
+ "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00044.safetensors",
233
+ "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00044.safetensors",
234
+ "model.layers.29.self_attn.q_norm.weight": "model-00021-of-00044.safetensors",
235
+ "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00044.safetensors",
236
+ "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00044.safetensors",
237
+ "model.layers.3.input_layernorm.weight": "model-00004-of-00044.safetensors",
238
+ "model.layers.3.mlp.down_proj.weight": "model-00004-of-00044.safetensors",
239
+ "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00044.safetensors",
240
+ "model.layers.3.mlp.up_proj.weight": "model-00004-of-00044.safetensors",
241
+ "model.layers.3.self_attn.k_norm.weight": "model-00003-of-00044.safetensors",
242
+ "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00044.safetensors",
243
+ "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00044.safetensors",
244
+ "model.layers.3.self_attn.q_norm.weight": "model-00003-of-00044.safetensors",
245
+ "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00044.safetensors",
246
+ "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00044.safetensors",
247
+ "model.layers.30.input_layernorm.weight": "model-00022-of-00044.safetensors",
248
+ "model.layers.30.mlp.down_proj.weight": "model-00022-of-00044.safetensors",
249
+ "model.layers.30.mlp.gate_proj.weight": "model-00022-of-00044.safetensors",
250
+ "model.layers.30.mlp.up_proj.weight": "model-00022-of-00044.safetensors",
251
+ "model.layers.30.self_attn.k_norm.weight": "model-00021-of-00044.safetensors",
252
+ "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00044.safetensors",
253
+ "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",
254
+ "model.layers.30.self_attn.q_norm.weight": "model-00021-of-00044.safetensors",
255
+ "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00044.safetensors",
256
+ "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00044.safetensors",
257
+ "model.layers.31.input_layernorm.weight": "model-00023-of-00044.safetensors",
258
+ "model.layers.31.mlp.down_proj.weight": "model-00023-of-00044.safetensors",
259
+ "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00044.safetensors",
260
+ "model.layers.31.mlp.up_proj.weight": "model-00023-of-00044.safetensors",
261
+ "model.layers.31.self_attn.k_norm.weight": "model-00022-of-00044.safetensors",
262
+ "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00044.safetensors",
263
+ "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",
264
+ "model.layers.31.self_attn.q_norm.weight": "model-00022-of-00044.safetensors",
265
+ "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00044.safetensors",
266
+ "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00044.safetensors",
267
+ "model.layers.32.input_layernorm.weight": "model-00023-of-00044.safetensors",
268
+ "model.layers.32.mlp.down_proj.weight": "model-00023-of-00044.safetensors",
269
+ "model.layers.32.mlp.gate_proj.weight": "model-00023-of-00044.safetensors",
270
+ "model.layers.32.mlp.up_proj.weight": "model-00023-of-00044.safetensors",
271
+ "model.layers.32.self_attn.k_norm.weight": "model-00023-of-00044.safetensors",
272
+ "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00044.safetensors",
273
+ "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00044.safetensors",
274
+ "model.layers.32.self_attn.q_norm.weight": "model-00023-of-00044.safetensors",
275
+ "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00044.safetensors",
276
+ "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00044.safetensors",
277
+ "model.layers.33.input_layernorm.weight": "model-00024-of-00044.safetensors",
278
+ "model.layers.33.mlp.down_proj.weight": "model-00024-of-00044.safetensors",
279
+ "model.layers.33.mlp.gate_proj.weight": "model-00024-of-00044.safetensors",
280
+ "model.layers.33.mlp.up_proj.weight": "model-00024-of-00044.safetensors",
281
+ "model.layers.33.self_attn.k_norm.weight": "model-00023-of-00044.safetensors",
282
+ "model.layers.33.self_attn.k_proj.weight": "model-00024-of-00044.safetensors",
283
+ "model.layers.33.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",
284
+ "model.layers.33.self_attn.q_norm.weight": "model-00023-of-00044.safetensors",
285
+ "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00044.safetensors",
286
+ "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00044.safetensors",
287
+ "model.layers.34.input_layernorm.weight": "model-00025-of-00044.safetensors",
288
+ "model.layers.34.mlp.down_proj.weight": "model-00025-of-00044.safetensors",
289
+ "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00044.safetensors",
290
+ "model.layers.34.mlp.up_proj.weight": "model-00025-of-00044.safetensors",
291
+ "model.layers.34.self_attn.k_norm.weight": "model-00024-of-00044.safetensors",
292
+ "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00044.safetensors",
293
+ "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",
294
+ "model.layers.34.self_attn.q_norm.weight": "model-00024-of-00044.safetensors",
295
+ "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00044.safetensors",
296
+ "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00044.safetensors",
297
+ "model.layers.35.input_layernorm.weight": "model-00025-of-00044.safetensors",
298
+ "model.layers.35.mlp.down_proj.weight": "model-00025-of-00044.safetensors",
299
+ "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00044.safetensors",
300
+ "model.layers.35.mlp.up_proj.weight": "model-00025-of-00044.safetensors",
301
+ "model.layers.35.self_attn.k_norm.weight": "model-00025-of-00044.safetensors",
302
+ "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00044.safetensors",
303
+ "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00044.safetensors",
304
+ "model.layers.35.self_attn.q_norm.weight": "model-00025-of-00044.safetensors",
305
+ "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00044.safetensors",
306
+ "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00044.safetensors",
307
+ "model.layers.36.input_layernorm.weight": "model-00026-of-00044.safetensors",
308
+ "model.layers.36.mlp.down_proj.weight": "model-00026-of-00044.safetensors",
309
+ "model.layers.36.mlp.gate_proj.weight": "model-00026-of-00044.safetensors",
310
+ "model.layers.36.mlp.up_proj.weight": "model-00026-of-00044.safetensors",
311
+ "model.layers.36.self_attn.k_norm.weight": "model-00025-of-00044.safetensors",
312
+ "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00044.safetensors",
313
+ "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00044.safetensors",
314
+ "model.layers.36.self_attn.q_norm.weight": "model-00025-of-00044.safetensors",
315
+ "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00044.safetensors",
316
+ "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00044.safetensors",
317
+ "model.layers.37.input_layernorm.weight": "model-00027-of-00044.safetensors",
318
+ "model.layers.37.mlp.down_proj.weight": "model-00027-of-00044.safetensors",
319
+ "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00044.safetensors",
320
+ "model.layers.37.mlp.up_proj.weight": "model-00027-of-00044.safetensors",
321
+ "model.layers.37.self_attn.k_norm.weight": "model-00026-of-00044.safetensors",
322
+ "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00044.safetensors",
323
+ "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00044.safetensors",
324
+ "model.layers.37.self_attn.q_norm.weight": "model-00026-of-00044.safetensors",
325
+ "model.layers.37.self_attn.q_proj.weight": "model-00026-of-00044.safetensors",
326
+ "model.layers.37.self_attn.v_proj.weight": "model-00026-of-00044.safetensors",
327
+ "model.layers.38.input_layernorm.weight": "model-00027-of-00044.safetensors",
328
+ "model.layers.38.mlp.down_proj.weight": "model-00027-of-00044.safetensors",
329
+ "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00044.safetensors",
330
+ "model.layers.38.mlp.up_proj.weight": "model-00027-of-00044.safetensors",
331
+ "model.layers.38.self_attn.k_norm.weight": "model-00027-of-00044.safetensors",
332
+ "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00044.safetensors",
333
+ "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00044.safetensors",
334
+ "model.layers.38.self_attn.q_norm.weight": "model-00027-of-00044.safetensors",
335
+ "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00044.safetensors",
336
+ "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00044.safetensors",
337
+ "model.layers.39.input_layernorm.weight": "model-00028-of-00044.safetensors",
338
+ "model.layers.39.mlp.down_proj.weight": "model-00028-of-00044.safetensors",
339
+ "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00044.safetensors",
340
+ "model.layers.39.mlp.up_proj.weight": "model-00028-of-00044.safetensors",
341
+ "model.layers.39.self_attn.k_norm.weight": "model-00027-of-00044.safetensors",
342
+ "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00044.safetensors",
343
+ "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00044.safetensors",
344
+ "model.layers.39.self_attn.q_norm.weight": "model-00027-of-00044.safetensors",
345
+ "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00044.safetensors",
346
+ "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00044.safetensors",
347
+ "model.layers.4.input_layernorm.weight": "model-00005-of-00044.safetensors",
348
+ "model.layers.4.mlp.down_proj.weight": "model-00005-of-00044.safetensors",
349
+ "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00044.safetensors",
350
+ "model.layers.4.mlp.up_proj.weight": "model-00005-of-00044.safetensors",
351
+ "model.layers.4.self_attn.k_norm.weight": "model-00004-of-00044.safetensors",
352
+ "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00044.safetensors",
353
+ "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00044.safetensors",
354
+ "model.layers.4.self_attn.q_norm.weight": "model-00004-of-00044.safetensors",
355
+ "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00044.safetensors",
356
+ "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00044.safetensors",
357
+ "model.layers.40.input_layernorm.weight": "model-00029-of-00044.safetensors",
358
+ "model.layers.40.mlp.down_proj.weight": "model-00029-of-00044.safetensors",
359
+ "model.layers.40.mlp.gate_proj.weight": "model-00028-of-00044.safetensors",
360
+ "model.layers.40.mlp.up_proj.weight": "model-00029-of-00044.safetensors",
361
+ "model.layers.40.self_attn.k_norm.weight": "model-00028-of-00044.safetensors",
362
+ "model.layers.40.self_attn.k_proj.weight": "model-00028-of-00044.safetensors",
363
+ "model.layers.40.self_attn.o_proj.weight": "model-00028-of-00044.safetensors",
364
+ "model.layers.40.self_attn.q_norm.weight": "model-00028-of-00044.safetensors",
365
+ "model.layers.40.self_attn.q_proj.weight": "model-00028-of-00044.safetensors",
366
+ "model.layers.40.self_attn.v_proj.weight": "model-00028-of-00044.safetensors",
367
+ "model.layers.41.input_layernorm.weight": "model-00029-of-00044.safetensors",
368
+ "model.layers.41.mlp.down_proj.weight": "model-00029-of-00044.safetensors",
369
+ "model.layers.41.mlp.gate_proj.weight": "model-00029-of-00044.safetensors",
370
+ "model.layers.41.mlp.up_proj.weight": "model-00029-of-00044.safetensors",
371
+ "model.layers.41.self_attn.k_norm.weight": "model-00029-of-00044.safetensors",
372
+ "model.layers.41.self_attn.k_proj.weight": "model-00029-of-00044.safetensors",
373
+ "model.layers.41.self_attn.o_proj.weight": "model-00029-of-00044.safetensors",
374
+ "model.layers.41.self_attn.q_norm.weight": "model-00029-of-00044.safetensors",
375
+ "model.layers.41.self_attn.q_proj.weight": "model-00029-of-00044.safetensors",
376
+ "model.layers.41.self_attn.v_proj.weight": "model-00029-of-00044.safetensors",
377
+ "model.layers.42.input_layernorm.weight": "model-00030-of-00044.safetensors",
378
+ "model.layers.42.mlp.down_proj.weight": "model-00030-of-00044.safetensors",
379
+ "model.layers.42.mlp.gate_proj.weight": "model-00030-of-00044.safetensors",
380
+ "model.layers.42.mlp.up_proj.weight": "model-00030-of-00044.safetensors",
381
+ "model.layers.42.self_attn.k_norm.weight": "model-00029-of-00044.safetensors",
382
+ "model.layers.42.self_attn.k_proj.weight": "model-00030-of-00044.safetensors",
383
+ "model.layers.42.self_attn.o_proj.weight": "model-00030-of-00044.safetensors",
384
+ "model.layers.42.self_attn.q_norm.weight": "model-00029-of-00044.safetensors",
385
+ "model.layers.42.self_attn.q_proj.weight": "model-00030-of-00044.safetensors",
386
+ "model.layers.42.self_attn.v_proj.weight": "model-00030-of-00044.safetensors",
387
+ "model.layers.43.input_layernorm.weight": "model-00031-of-00044.safetensors",
388
+ "model.layers.43.mlp.down_proj.weight": "model-00031-of-00044.safetensors",
389
+ "model.layers.43.mlp.gate_proj.weight": "model-00030-of-00044.safetensors",
390
+ "model.layers.43.mlp.up_proj.weight": "model-00031-of-00044.safetensors",
391
+ "model.layers.43.self_attn.k_norm.weight": "model-00030-of-00044.safetensors",
392
+ "model.layers.43.self_attn.k_proj.weight": "model-00030-of-00044.safetensors",
393
+ "model.layers.43.self_attn.o_proj.weight": "model-00030-of-00044.safetensors",
394
+ "model.layers.43.self_attn.q_norm.weight": "model-00030-of-00044.safetensors",
395
+ "model.layers.43.self_attn.q_proj.weight": "model-00030-of-00044.safetensors",
396
+ "model.layers.43.self_attn.v_proj.weight": "model-00030-of-00044.safetensors",
397
+ "model.layers.44.input_layernorm.weight": "model-00031-of-00044.safetensors",
398
+ "model.layers.44.mlp.down_proj.weight": "model-00031-of-00044.safetensors",
399
+ "model.layers.44.mlp.gate_proj.weight": "model-00031-of-00044.safetensors",
400
+ "model.layers.44.mlp.up_proj.weight": "model-00031-of-00044.safetensors",
401
+ "model.layers.44.self_attn.k_norm.weight": "model-00031-of-00044.safetensors",
402
+ "model.layers.44.self_attn.k_proj.weight": "model-00031-of-00044.safetensors",
403
+ "model.layers.44.self_attn.o_proj.weight": "model-00031-of-00044.safetensors",
404
+ "model.layers.44.self_attn.q_norm.weight": "model-00031-of-00044.safetensors",
405
+ "model.layers.44.self_attn.q_proj.weight": "model-00031-of-00044.safetensors",
406
+ "model.layers.44.self_attn.v_proj.weight": "model-00031-of-00044.safetensors",
407
+ "model.layers.45.input_layernorm.weight": "model-00032-of-00044.safetensors",
408
+ "model.layers.45.mlp.down_proj.weight": "model-00032-of-00044.safetensors",
409
+ "model.layers.45.mlp.gate_proj.weight": "model-00032-of-00044.safetensors",
410
+ "model.layers.45.mlp.up_proj.weight": "model-00032-of-00044.safetensors",
411
+ "model.layers.45.self_attn.k_norm.weight": "model-00031-of-00044.safetensors",
412
+ "model.layers.45.self_attn.k_proj.weight": "model-00032-of-00044.safetensors",
413
+ "model.layers.45.self_attn.o_proj.weight": "model-00032-of-00044.safetensors",
414
+ "model.layers.45.self_attn.q_norm.weight": "model-00031-of-00044.safetensors",
415
+ "model.layers.45.self_attn.q_proj.weight": "model-00032-of-00044.safetensors",
416
+ "model.layers.45.self_attn.v_proj.weight": "model-00032-of-00044.safetensors",
417
+ "model.layers.46.input_layernorm.weight": "model-00033-of-00044.safetensors",
418
+ "model.layers.46.mlp.down_proj.weight": "model-00033-of-00044.safetensors",
419
+ "model.layers.46.mlp.gate_proj.weight": "model-00032-of-00044.safetensors",
420
+ "model.layers.46.mlp.up_proj.weight": "model-00033-of-00044.safetensors",
421
+ "model.layers.46.self_attn.k_norm.weight": "model-00032-of-00044.safetensors",
422
+ "model.layers.46.self_attn.k_proj.weight": "model-00032-of-00044.safetensors",
423
+ "model.layers.46.self_attn.o_proj.weight": "model-00032-of-00044.safetensors",
424
+ "model.layers.46.self_attn.q_norm.weight": "model-00032-of-00044.safetensors",
425
+ "model.layers.46.self_attn.q_proj.weight": "model-00032-of-00044.safetensors",
426
+ "model.layers.46.self_attn.v_proj.weight": "model-00032-of-00044.safetensors",
427
+ "model.layers.47.input_layernorm.weight": "model-00033-of-00044.safetensors",
428
+ "model.layers.47.mlp.down_proj.weight": "model-00033-of-00044.safetensors",
429
+ "model.layers.47.mlp.gate_proj.weight": "model-00033-of-00044.safetensors",
430
+ "model.layers.47.mlp.up_proj.weight": "model-00033-of-00044.safetensors",
431
+ "model.layers.47.self_attn.k_norm.weight": "model-00033-of-00044.safetensors",
432
+ "model.layers.47.self_attn.k_proj.weight": "model-00033-of-00044.safetensors",
433
+ "model.layers.47.self_attn.o_proj.weight": "model-00033-of-00044.safetensors",
434
+ "model.layers.47.self_attn.q_norm.weight": "model-00033-of-00044.safetensors",
435
+ "model.layers.47.self_attn.q_proj.weight": "model-00033-of-00044.safetensors",
436
+ "model.layers.47.self_attn.v_proj.weight": "model-00033-of-00044.safetensors",
437
+ "model.layers.48.input_layernorm.weight": "model-00034-of-00044.safetensors",
438
+ "model.layers.48.mlp.down_proj.weight": "model-00034-of-00044.safetensors",
439
+ "model.layers.48.mlp.gate_proj.weight": "model-00034-of-00044.safetensors",
440
+ "model.layers.48.mlp.up_proj.weight": "model-00034-of-00044.safetensors",
441
+ "model.layers.48.self_attn.k_norm.weight": "model-00033-of-00044.safetensors",
442
+ "model.layers.48.self_attn.k_proj.weight": "model-00034-of-00044.safetensors",
443
+ "model.layers.48.self_attn.o_proj.weight": "model-00034-of-00044.safetensors",
444
+ "model.layers.48.self_attn.q_norm.weight": "model-00033-of-00044.safetensors",
445
+ "model.layers.48.self_attn.q_proj.weight": "model-00034-of-00044.safetensors",
446
+ "model.layers.48.self_attn.v_proj.weight": "model-00034-of-00044.safetensors",
447
+ "model.layers.49.input_layernorm.weight": "model-00035-of-00044.safetensors",
448
+ "model.layers.49.mlp.down_proj.weight": "model-00035-of-00044.safetensors",
449
+ "model.layers.49.mlp.gate_proj.weight": "model-00034-of-00044.safetensors",
450
+ "model.layers.49.mlp.up_proj.weight": "model-00035-of-00044.safetensors",
451
+ "model.layers.49.self_attn.k_norm.weight": "model-00034-of-00044.safetensors",
452
+ "model.layers.49.self_attn.k_proj.weight": "model-00034-of-00044.safetensors",
453
+ "model.layers.49.self_attn.o_proj.weight": "model-00034-of-00044.safetensors",
454
+ "model.layers.49.self_attn.q_norm.weight": "model-00034-of-00044.safetensors",
455
+ "model.layers.49.self_attn.q_proj.weight": "model-00034-of-00044.safetensors",
456
+ "model.layers.49.self_attn.v_proj.weight": "model-00034-of-00044.safetensors",
457
+ "model.layers.5.input_layernorm.weight": "model-00005-of-00044.safetensors",
458
+ "model.layers.5.mlp.down_proj.weight": "model-00005-of-00044.safetensors",
459
+ "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00044.safetensors",
460
+ "model.layers.5.mlp.up_proj.weight": "model-00005-of-00044.safetensors",
461
+ "model.layers.5.self_attn.k_norm.weight": "model-00005-of-00044.safetensors",
462
+ "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00044.safetensors",
463
+ "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00044.safetensors",
464
+ "model.layers.5.self_attn.q_norm.weight": "model-00005-of-00044.safetensors",
465
+ "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00044.safetensors",
466
+ "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00044.safetensors",
467
+ "model.layers.50.input_layernorm.weight": "model-00035-of-00044.safetensors",
468
+ "model.layers.50.mlp.down_proj.weight": "model-00035-of-00044.safetensors",
469
+ "model.layers.50.mlp.gate_proj.weight": "model-00035-of-00044.safetensors",
470
+ "model.layers.50.mlp.up_proj.weight": "model-00035-of-00044.safetensors",
471
+ "model.layers.50.self_attn.k_norm.weight": "model-00035-of-00044.safetensors",
472
+ "model.layers.50.self_attn.k_proj.weight": "model-00035-of-00044.safetensors",
473
+ "model.layers.50.self_attn.o_proj.weight": "model-00035-of-00044.safetensors",
474
+ "model.layers.50.self_attn.q_norm.weight": "model-00035-of-00044.safetensors",
475
+ "model.layers.50.self_attn.q_proj.weight": "model-00035-of-00044.safetensors",
476
+ "model.layers.50.self_attn.v_proj.weight": "model-00035-of-00044.safetensors",
477
+ "model.layers.51.input_layernorm.weight": "model-00036-of-00044.safetensors",
478
+ "model.layers.51.mlp.down_proj.weight": "model-00036-of-00044.safetensors",
479
+ "model.layers.51.mlp.gate_proj.weight": "model-00036-of-00044.safetensors",
480
+ "model.layers.51.mlp.up_proj.weight": "model-00036-of-00044.safetensors",
481
+ "model.layers.51.self_attn.k_norm.weight": "model-00035-of-00044.safetensors",
482
+ "model.layers.51.self_attn.k_proj.weight": "model-00036-of-00044.safetensors",
483
+ "model.layers.51.self_attn.o_proj.weight": "model-00036-of-00044.safetensors",
484
+ "model.layers.51.self_attn.q_norm.weight": "model-00035-of-00044.safetensors",
485
+ "model.layers.51.self_attn.q_proj.weight": "model-00036-of-00044.safetensors",
486
+ "model.layers.51.self_attn.v_proj.weight": "model-00036-of-00044.safetensors",
487
+ "model.layers.52.input_layernorm.weight": "model-00037-of-00044.safetensors",
488
+ "model.layers.52.mlp.down_proj.weight": "model-00037-of-00044.safetensors",
489
+ "model.layers.52.mlp.gate_proj.weight": "model-00036-of-00044.safetensors",
490
+ "model.layers.52.mlp.up_proj.weight": "model-00037-of-00044.safetensors",
491
+ "model.layers.52.self_attn.k_norm.weight": "model-00036-of-00044.safetensors",
492
+ "model.layers.52.self_attn.k_proj.weight": "model-00036-of-00044.safetensors",
493
+ "model.layers.52.self_attn.o_proj.weight": "model-00036-of-00044.safetensors",
494
+ "model.layers.52.self_attn.q_norm.weight": "model-00036-of-00044.safetensors",
495
+ "model.layers.52.self_attn.q_proj.weight": "model-00036-of-00044.safetensors",
496
+ "model.layers.52.self_attn.v_proj.weight": "model-00036-of-00044.safetensors",
497
+ "model.layers.53.input_layernorm.weight": "model-00037-of-00044.safetensors",
498
+ "model.layers.53.mlp.down_proj.weight": "model-00037-of-00044.safetensors",
499
+ "model.layers.53.mlp.gate_proj.weight": "model-00037-of-00044.safetensors",
500
+ "model.layers.53.mlp.up_proj.weight": "model-00037-of-00044.safetensors",
501
+ "model.layers.53.self_attn.k_norm.weight": "model-00037-of-00044.safetensors",
502
+ "model.layers.53.self_attn.k_proj.weight": "model-00037-of-00044.safetensors",
503
+ "model.layers.53.self_attn.o_proj.weight": "model-00037-of-00044.safetensors",
504
+ "model.layers.53.self_attn.q_norm.weight": "model-00037-of-00044.safetensors",
505
+ "model.layers.53.self_attn.q_proj.weight": "model-00037-of-00044.safetensors",
506
+ "model.layers.53.self_attn.v_proj.weight": "model-00037-of-00044.safetensors",
507
+ "model.layers.54.input_layernorm.weight": "model-00038-of-00044.safetensors",
508
+ "model.layers.54.mlp.down_proj.weight": "model-00038-of-00044.safetensors",
509
+ "model.layers.54.mlp.gate_proj.weight": "model-00038-of-00044.safetensors",
510
+ "model.layers.54.mlp.up_proj.weight": "model-00038-of-00044.safetensors",
511
+ "model.layers.54.self_attn.k_norm.weight": "model-00037-of-00044.safetensors",
512
+ "model.layers.54.self_attn.k_proj.weight": "model-00038-of-00044.safetensors",
513
+ "model.layers.54.self_attn.o_proj.weight": "model-00038-of-00044.safetensors",
514
+ "model.layers.54.self_attn.q_norm.weight": "model-00037-of-00044.safetensors",
515
+ "model.layers.54.self_attn.q_proj.weight": "model-00038-of-00044.safetensors",
516
+ "model.layers.54.self_attn.v_proj.weight": "model-00038-of-00044.safetensors",
517
+ "model.layers.55.input_layernorm.weight": "model-00039-of-00044.safetensors",
518
+ "model.layers.55.mlp.down_proj.weight": "model-00039-of-00044.safetensors",
519
+ "model.layers.55.mlp.gate_proj.weight": "model-00038-of-00044.safetensors",
520
+ "model.layers.55.mlp.up_proj.weight": "model-00039-of-00044.safetensors",
521
+ "model.layers.55.self_attn.k_norm.weight": "model-00038-of-00044.safetensors",
522
+ "model.layers.55.self_attn.k_proj.weight": "model-00038-of-00044.safetensors",
523
+ "model.layers.55.self_attn.o_proj.weight": "model-00038-of-00044.safetensors",
524
+ "model.layers.55.self_attn.q_norm.weight": "model-00038-of-00044.safetensors",
525
+ "model.layers.55.self_attn.q_proj.weight": "model-00038-of-00044.safetensors",
526
+ "model.layers.55.self_attn.v_proj.weight": "model-00038-of-00044.safetensors",
527
+ "model.layers.56.input_layernorm.weight": "model-00039-of-00044.safetensors",
528
+ "model.layers.56.mlp.down_proj.weight": "model-00039-of-00044.safetensors",
529
+ "model.layers.56.mlp.gate_proj.weight": "model-00039-of-00044.safetensors",
530
+ "model.layers.56.mlp.up_proj.weight": "model-00039-of-00044.safetensors",
531
+ "model.layers.56.self_attn.k_norm.weight": "model-00039-of-00044.safetensors",
532
+ "model.layers.56.self_attn.k_proj.weight": "model-00039-of-00044.safetensors",
533
+ "model.layers.56.self_attn.o_proj.weight": "model-00039-of-00044.safetensors",
534
+ "model.layers.56.self_attn.q_norm.weight": "model-00039-of-00044.safetensors",
535
+ "model.layers.56.self_attn.q_proj.weight": "model-00039-of-00044.safetensors",
536
+ "model.layers.56.self_attn.v_proj.weight": "model-00039-of-00044.safetensors",
537
+ "model.layers.57.input_layernorm.weight": "model-00040-of-00044.safetensors",
538
+ "model.layers.57.mlp.down_proj.weight": "model-00040-of-00044.safetensors",
539
+ "model.layers.57.mlp.gate_proj.weight": "model-00040-of-00044.safetensors",
540
+ "model.layers.57.mlp.up_proj.weight": "model-00040-of-00044.safetensors",
541
+ "model.layers.57.self_attn.k_norm.weight": "model-00039-of-00044.safetensors",
542
+ "model.layers.57.self_attn.k_proj.weight": "model-00040-of-00044.safetensors",
543
+ "model.layers.57.self_attn.o_proj.weight": "model-00040-of-00044.safetensors",
544
+ "model.layers.57.self_attn.q_norm.weight": "model-00039-of-00044.safetensors",
545
+ "model.layers.57.self_attn.q_proj.weight": "model-00040-of-00044.safetensors",
546
+ "model.layers.57.self_attn.v_proj.weight": "model-00040-of-00044.safetensors",
547
+ "model.layers.58.input_layernorm.weight": "model-00041-of-00044.safetensors",
548
+ "model.layers.58.mlp.down_proj.weight": "model-00041-of-00044.safetensors",
549
+ "model.layers.58.mlp.gate_proj.weight": "model-00040-of-00044.safetensors",
550
+ "model.layers.58.mlp.up_proj.weight": "model-00041-of-00044.safetensors",
551
+ "model.layers.58.self_attn.k_norm.weight": "model-00040-of-00044.safetensors",
552
+ "model.layers.58.self_attn.k_proj.weight": "model-00040-of-00044.safetensors",
553
+ "model.layers.58.self_attn.o_proj.weight": "model-00040-of-00044.safetensors",
554
+ "model.layers.58.self_attn.q_norm.weight": "model-00040-of-00044.safetensors",
555
+ "model.layers.58.self_attn.q_proj.weight": "model-00040-of-00044.safetensors",
556
+ "model.layers.58.self_attn.v_proj.weight": "model-00040-of-00044.safetensors",
557
+ "model.layers.59.input_layernorm.weight": "model-00041-of-00044.safetensors",
558
+ "model.layers.59.mlp.down_proj.weight": "model-00041-of-00044.safetensors",
559
+ "model.layers.59.mlp.gate_proj.weight": "model-00041-of-00044.safetensors",
560
+ "model.layers.59.mlp.up_proj.weight": "model-00041-of-00044.safetensors",
561
+ "model.layers.59.self_attn.k_norm.weight": "model-00041-of-00044.safetensors",
562
+ "model.layers.59.self_attn.k_proj.weight": "model-00041-of-00044.safetensors",
563
+ "model.layers.59.self_attn.o_proj.weight": "model-00041-of-00044.safetensors",
564
+ "model.layers.59.self_attn.q_norm.weight": "model-00041-of-00044.safetensors",
565
+ "model.layers.59.self_attn.q_proj.weight": "model-00041-of-00044.safetensors",
566
+ "model.layers.59.self_attn.v_proj.weight": "model-00041-of-00044.safetensors",
567
+ "model.layers.6.input_layernorm.weight": "model-00006-of-00044.safetensors",
568
+ "model.layers.6.mlp.down_proj.weight": "model-00006-of-00044.safetensors",
569
+ "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00044.safetensors",
570
+ "model.layers.6.mlp.up_proj.weight": "model-00006-of-00044.safetensors",
571
+ "model.layers.6.self_attn.k_norm.weight": "model-00005-of-00044.safetensors",
572
+ "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00044.safetensors",
573
+ "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",
574
+ "model.layers.6.self_attn.q_norm.weight": "model-00005-of-00044.safetensors",
575
+ "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00044.safetensors",
576
+ "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00044.safetensors",
577
+ "model.layers.60.input_layernorm.weight": "model-00042-of-00044.safetensors",
578
+ "model.layers.60.mlp.down_proj.weight": "model-00042-of-00044.safetensors",
579
+ "model.layers.60.mlp.gate_proj.weight": "model-00042-of-00044.safetensors",
580
+ "model.layers.60.mlp.up_proj.weight": "model-00042-of-00044.safetensors",
581
+ "model.layers.60.self_attn.k_norm.weight": "model-00041-of-00044.safetensors",
582
+ "model.layers.60.self_attn.k_proj.weight": "model-00042-of-00044.safetensors",
583
+ "model.layers.60.self_attn.o_proj.weight": "model-00042-of-00044.safetensors",
584
+ "model.layers.60.self_attn.q_norm.weight": "model-00041-of-00044.safetensors",
585
+ "model.layers.60.self_attn.q_proj.weight": "model-00042-of-00044.safetensors",
586
+ "model.layers.60.self_attn.v_proj.weight": "model-00042-of-00044.safetensors",
587
+ "model.layers.61.input_layernorm.weight": "model-00043-of-00044.safetensors",
588
+ "model.layers.61.mlp.down_proj.weight": "model-00043-of-00044.safetensors",
589
+ "model.layers.61.mlp.gate_proj.weight": "model-00042-of-00044.safetensors",
590
+ "model.layers.61.mlp.up_proj.weight": "model-00043-of-00044.safetensors",
591
+ "model.layers.61.self_attn.k_norm.weight": "model-00042-of-00044.safetensors",
592
+ "model.layers.61.self_attn.k_proj.weight": "model-00042-of-00044.safetensors",
593
+ "model.layers.61.self_attn.o_proj.weight": "model-00042-of-00044.safetensors",
594
+ "model.layers.61.self_attn.q_norm.weight": "model-00042-of-00044.safetensors",
595
+ "model.layers.61.self_attn.q_proj.weight": "model-00042-of-00044.safetensors",
596
+ "model.layers.61.self_attn.v_proj.weight": "model-00042-of-00044.safetensors",
597
+ "model.layers.62.input_layernorm.weight": "model-00043-of-00044.safetensors",
598
+ "model.layers.62.mlp.down_proj.weight": "model-00043-of-00044.safetensors",
599
+ "model.layers.62.mlp.gate_proj.weight": "model-00043-of-00044.safetensors",
600
+ "model.layers.62.mlp.up_proj.weight": "model-00043-of-00044.safetensors",
601
+ "model.layers.62.self_attn.k_norm.weight": "model-00043-of-00044.safetensors",
602
+ "model.layers.62.self_attn.k_proj.weight": "model-00043-of-00044.safetensors",
603
+ "model.layers.62.self_attn.o_proj.weight": "model-00043-of-00044.safetensors",
604
+ "model.layers.62.self_attn.q_norm.weight": "model-00043-of-00044.safetensors",
605
+ "model.layers.62.self_attn.q_proj.weight": "model-00043-of-00044.safetensors",
606
+ "model.layers.62.self_attn.v_proj.weight": "model-00043-of-00044.safetensors",
607
+ "model.layers.63.input_layernorm.weight": "model-00044-of-00044.safetensors",
608
+ "model.layers.63.mlp.down_proj.weight": "model-00044-of-00044.safetensors",
609
+ "model.layers.63.mlp.gate_proj.weight": "model-00044-of-00044.safetensors",
610
+ "model.layers.63.mlp.up_proj.weight": "model-00044-of-00044.safetensors",
611
+ "model.layers.63.self_attn.k_norm.weight": "model-00043-of-00044.safetensors",
612
+ "model.layers.63.self_attn.k_proj.weight": "model-00044-of-00044.safetensors",
613
+ "model.layers.63.self_attn.o_proj.weight": "model-00044-of-00044.safetensors",
614
+ "model.layers.63.self_attn.q_norm.weight": "model-00043-of-00044.safetensors",
615
+ "model.layers.63.self_attn.q_proj.weight": "model-00044-of-00044.safetensors",
616
+ "model.layers.63.self_attn.v_proj.weight": "model-00044-of-00044.safetensors",
617
+ "model.layers.7.input_layernorm.weight": "model-00007-of-00044.safetensors",
618
+ "model.layers.7.mlp.down_proj.weight": "model-00007-of-00044.safetensors",
619
+ "model.layers.7.mlp.gate_proj.weight": "model-00006-of-00044.safetensors",
620
+ "model.layers.7.mlp.up_proj.weight": "model-00007-of-00044.safetensors",
621
+ "model.layers.7.self_attn.k_norm.weight": "model-00006-of-00044.safetensors",
622
+ "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00044.safetensors",
623
+ "model.layers.7.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",
624
+ "model.layers.7.self_attn.q_norm.weight": "model-00006-of-00044.safetensors",
625
+ "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00044.safetensors",
626
+ "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00044.safetensors",
627
+ "model.layers.8.input_layernorm.weight": "model-00007-of-00044.safetensors",
628
+ "model.layers.8.mlp.down_proj.weight": "model-00007-of-00044.safetensors",
629
+ "model.layers.8.mlp.gate_proj.weight": "model-00007-of-00044.safetensors",
630
+ "model.layers.8.mlp.up_proj.weight": "model-00007-of-00044.safetensors",
631
+ "model.layers.8.self_attn.k_norm.weight": "model-00007-of-00044.safetensors",
632
+ "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00044.safetensors",
633
+ "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00044.safetensors",
634
+ "model.layers.8.self_attn.q_norm.weight": "model-00007-of-00044.safetensors",
635
+ "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00044.safetensors",
636
+ "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00044.safetensors",
637
+ "model.layers.9.input_layernorm.weight": "model-00008-of-00044.safetensors",
638
+ "model.layers.9.mlp.down_proj.weight": "model-00008-of-00044.safetensors",
639
+ "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00044.safetensors",
640
+ "model.layers.9.mlp.up_proj.weight": "model-00008-of-00044.safetensors",
641
+ "model.layers.9.self_attn.k_norm.weight": "model-00007-of-00044.safetensors",
642
+ "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00044.safetensors",
643
+ "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00044.safetensors",
644
+ "model.layers.9.self_attn.q_norm.weight": "model-00007-of-00044.safetensors",
645
+ "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00044.safetensors",
646
+ "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00044.safetensors",
647
+ "model.norm.weight": "model-00044-of-00044.safetensors"
648
+ }
649
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<BOS_TOKEN>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|END_OF_TURN_TOKEN|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }