Hugging Face's logo

mlx-community
/
command-a-vision-07-2025-4bit

Image-Text-to-Text
Transformers
Safetensors
MLX
cohere2_vision
conversational
4-bit precision
Model card Files
xet
 Community
prince-canuma commited on
Commit
8864bb5
·
verified ·
1 Parent(s): a6d013e

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +1 -0
  2. README.md +41 -0
  3. chat_template.jinja +61 -0
  4. config.json +316 -0
  5. generation_config.json +11 -0
  6. model-00001-of-00013.safetensors +3 -0
  7. model-00002-of-00013.safetensors +3 -0
  8. model-00003-of-00013.safetensors +3 -0
  9. model-00004-of-00013.safetensors +3 -0
  10. model-00005-of-00013.safetensors +3 -0
  11. model-00006-of-00013.safetensors +3 -0
  12. model-00007-of-00013.safetensors +3 -0
  13. model-00008-of-00013.safetensors +3 -0
  14. model-00009-of-00013.safetensors +3 -0
  15. model-00010-of-00013.safetensors +3 -0
  16. model-00011-of-00013.safetensors +3 -0
  17. model-00012-of-00013.safetensors +3 -0
  18. model-00013-of-00013.safetensors +3 -0
  19. model.safetensors.index.json +963 -0
  20. preprocessor_config.json +42 -0
  21. special_tokens_map.json +38 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +395 -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 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ license: cc-by-nc-4.0
12
+ extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
13
+ acknowledge that the information you provide will be collected, used, and shared
14
+ in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
15
+ receive email updates about C4AI and Cohere research, events, products and services.
16
+ You can unsubscribe at any time.
17
+ extra_gated_fields:
18
+ Name: text
19
+ Affiliation: text
20
+ Country: country
21
+ I agree to use this model for non-commercial use ONLY: checkbox
22
+ pipeline_tag: image-text-to-text
23
+ base_model:
24
+ - CohereLabs/c4ai-command-a-03-2025
25
+ - google/siglip2-so400m-patch16-512
26
+ tags:
27
+ - mlx
28
+ ---
29
+
30
+ # mlx-community/command-a-vision-07-2025-4bit
31
+ This model was converted to MLX format from [`CohereLabs/command-a-vision-07-2025`]() using mlx-vlm version **0.3.3**.
32
+ Refer to the [original model card](https://huggingface.co/CohereLabs/command-a-vision-07-2025) for more details on the model.
33
+ ## Use with mlx
34
+
35
+ ```bash
36
+ pip install -U mlx-vlm
37
+ ```
38
+
39
+ ```bash
40
+ python -m mlx_vlm.generate --model mlx-community/command-a-vision-07-2025-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
41
+ ```
chat_template.jinja ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- "<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
2
+ You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
3
+
4
+ Your information cutoff date is June 2024.
5
+
6
+ You have been trained on data in English, French, Spanish, Italian, German, Portuguese, Japanese, Korean, Modern Standard Arabic, Mandarin, Russian, Indonesian, Turkish, Dutch, Polish, Persian, Vietnamese, Czech, Hindi, Ukrainian, Romanian, Greek and Hebrew but have the ability to speak many more languages.
7
+
8
+ # Default Preamble
9
+ The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
10
+ - Your name is Command.
11
+ - You are a large language model built by Cohere.
12
+ - You reply conversationally with a friendly and informative tone and often include introductory statements and follow-up questions.
13
+ - If the input is ambiguous, ask clarifying follow-up questions.
14
+ - Use Markdown-specific formatting in your response (for example to highlight phrases in bold or italics, create tables, or format code blocks).
15
+ - Use LaTeX to generate mathematical notation for complex equations.
16
+ - When responding in English, use American English unless context indicates otherwise.
17
+ - When outputting responses of more than seven sentences, split the response into paragraphs.
18
+ - Prefer the active voice.
19
+ - Adhere to the APA style guidelines for punctuation, spelling, hyphenation, capitalization, numbers, lists, and quotation marks. Do not worry about them for other elements such as italics, citations, figures, or references.
20
+ - Use gender-neutral pronouns for unspecified persons.
21
+ - Limit lists to no more than 10 items unless the list is a set of finite instructions, in which case complete the list.
22
+ - Use the third person when asked to write a summary.
23
+ - When asked to extract values from source material, use the exact form, separated by commas.
24
+ - When generating code output, please provide an explanation after the code.
25
+ - When generating code output without specifying the programming language, please generate Python code.
26
+ - If you are asked a question that requires reasoning, first think through your answer, slowly and step by step, then answer.<|END_OF_TURN_TOKEN|>" -}}
27
+ {%- for message in messages -%}
28
+ <|START_OF_TURN_TOKEN|>{{ message.role | replace("user", "<|USER_TOKEN|>") | replace("assistant", "<|CHATBOT_TOKEN|><|START_RESPONSE|>") | replace("system", "<|SYSTEM_TOKEN|>") }}
29
+ {%- if message.content is defined -%}
30
+ {%- if message.content is string -%}
31
+ {{ message.content }}
32
+ {%- else -%}
33
+ {%- for item in message.content -%}
34
+ {%- if item.type == 'image' -%}
35
+ <|IMG_PATCH|>
36
+ {%- elif item.type == 'text' -%}
37
+ {{ item.text }}
38
+ {%- endif -%}
39
+ {%- endfor -%}
40
+ {%- endif -%}
41
+ {%- elif message.message is defined -%}
42
+ {%- if message.message is string -%}
43
+ {{ message.message }}
44
+ {%- else -%}
45
+ {%- for item in message.message -%}
46
+ {%- if item.type == 'image' -%}
47
+ <|IMG_PATCH|>
48
+ {%- elif item.type == 'text' -%}
49
+ {{ item.text }}
50
+ {%- endif -%}
51
+ {%- endfor -%}
52
+ {%- endif -%}
53
+ {%- endif -%}
54
+ {%- if message.role == "assistant" -%}
55
+ <|END_RESPONSE|>
56
+ {%- endif -%}
57
+ <|END_OF_TURN_TOKEN|>
58
+ {%- endfor -%}
59
+ {%- if add_generation_prompt -%}
60
+ <|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
61
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "adapter_layer_norm_eps": 1e-06,
3
+ "add_cross_attention": false,
4
+ "alignment_activation_fn": "swiglu",
5
+ "alignment_intermediate_size": 36864,
6
+ "architectures": [
7
+ "Cohere2VisionForConditionalGeneration"
8
+ ],
9
+ "bad_words_ids": null,
10
+ "begin_suppress_tokens": null,
11
+ "bos_token_id": null,
12
+ "chunk_size_feed_forward": 0,
13
+ "cross_attention_hidden_size": null,
14
+ "decoder_start_token_id": null,
15
+ "diversity_penalty": 0.0,
16
+ "do_sample": false,
17
+ "downsample_factor": 2,
18
+ "early_stopping": false,
19
+ "enable_adapter_layer_norm": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "exponential_decay_length_penalty": null,
23
+ "finetuning_task": null,
24
+ "forced_bos_token_id": null,
25
+ "forced_eos_token_id": null,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1"
29
+ },
30
+ "image_token": 255036,
31
+ "image_token_id": 255036,
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "max_splits_per_img": 12,
41
+ "min_length": 0,
42
+ "model_type": "cohere2_vision",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_beam_groups": 1,
45
+ "num_beams": 1,
46
+ "num_return_sequences": 1,
47
+ "output_attentions": false,
48
+ "output_hidden_states": false,
49
+ "output_scores": false,
50
+ "pad_token_id": null,
51
+ "prefix": null,
52
+ "problem_type": null,
53
+ "pruned_heads": {},
54
+ "quantization": {
55
+ "group_size": 64,
56
+ "bits": 4
57
+ },
58
+ "quantization_config": {
59
+ "group_size": 64,
60
+ "bits": 4
61
+ },
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "text_config": {
71
+ "vocab_size": 256000,
72
+ "max_position_embeddings": 500000,
73
+ "hidden_size": 12288,
74
+ "logit_scale": 1.0,
75
+ "intermediate_size": 36864,
76
+ "num_hidden_layers": 64,
77
+ "num_attention_heads": 96,
78
+ "num_key_value_heads": 8,
79
+ "hidden_act": "silu",
80
+ "initializer_range": 0.02,
81
+ "layer_norm_eps": 1e-05,
82
+ "use_cache": true,
83
+ "rope_theta": 50000,
84
+ "rope_scaling": null,
85
+ "attention_bias": false,
86
+ "attention_dropout": 0.0,
87
+ "sliding_window": 4096,
88
+ "layer_types": [
89
+ "sliding_attention",
90
+ "sliding_attention",
91
+ "sliding_attention",
92
+ "full_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "full_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "full_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "full_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "full_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "full_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "full_attention",
121
+ "sliding_attention",
122
+ "sliding_attention",
123
+ "sliding_attention",
124
+ "full_attention",
125
+ "sliding_attention",
126
+ "sliding_attention",
127
+ "sliding_attention",
128
+ "full_attention",
129
+ "sliding_attention",
130
+ "sliding_attention",
131
+ "sliding_attention",
132
+ "full_attention",
133
+ "sliding_attention",
134
+ "sliding_attention",
135
+ "sliding_attention",
136
+ "full_attention",
137
+ "sliding_attention",
138
+ "sliding_attention",
139
+ "sliding_attention",
140
+ "full_attention",
141
+ "sliding_attention",
142
+ "sliding_attention",
143
+ "sliding_attention",
144
+ "full_attention",
145
+ "sliding_attention",
146
+ "sliding_attention",
147
+ "sliding_attention",
148
+ "full_attention",
149
+ "sliding_attention",
150
+ "sliding_attention",
151
+ "sliding_attention",
152
+ "full_attention"
153
+ ],
154
+ "head_dim": 128,
155
+ "return_dict": true,
156
+ "output_hidden_states": false,
157
+ "torchscript": false,
158
+ "torch_dtype": null,
159
+ "pruned_heads": {},
160
+ "tie_word_embeddings": true,
161
+ "chunk_size_feed_forward": 0,
162
+ "is_encoder_decoder": false,
163
+ "is_decoder": false,
164
+ "cross_attention_hidden_size": null,
165
+ "add_cross_attention": false,
166
+ "tie_encoder_decoder": false,
167
+ "architectures": [
168
+ "Cohere2ForCausalLM"
169
+ ],
170
+ "finetuning_task": null,
171
+ "id2label": {
172
+ "0": "LABEL_0",
173
+ "1": "LABEL_1"
174
+ },
175
+ "label2id": {
176
+ "LABEL_0": 0,
177
+ "LABEL_1": 1
178
+ },
179
+ "task_specific_params": null,
180
+ "problem_type": null,
181
+ "tokenizer_class": null,
182
+ "prefix": null,
183
+ "bos_token_id": 5,
184
+ "pad_token_id": 0,
185
+ "eos_token_id": 255001,
186
+ "sep_token_id": null,
187
+ "decoder_start_token_id": null,
188
+ "max_length": 20,
189
+ "min_length": 0,
190
+ "do_sample": false,
191
+ "early_stopping": false,
192
+ "num_beams": 1,
193
+ "num_beam_groups": 1,
194
+ "diversity_penalty": 0.0,
195
+ "temperature": 1.0,
196
+ "top_k": 50,
197
+ "top_p": 1.0,
198
+ "typical_p": 1.0,
199
+ "repetition_penalty": 1.0,
200
+ "length_penalty": 1.0,
201
+ "no_repeat_ngram_size": 0,
202
+ "encoder_no_repeat_ngram_size": 0,
203
+ "bad_words_ids": null,
204
+ "num_return_sequences": 1,
205
+ "output_scores": false,
206
+ "return_dict_in_generate": false,
207
+ "forced_bos_token_id": null,
208
+ "forced_eos_token_id": null,
209
+ "remove_invalid_values": false,
210
+ "exponential_decay_length_penalty": null,
211
+ "suppress_tokens": null,
212
+ "begin_suppress_tokens": null,
213
+ "_name_or_path": "",
214
+ "_sliding_window_pattern": 4,
215
+ "cache_implementation": "hybrid",
216
+ "layer_switch": 4,
217
+ "model_type": "cohere2",
218
+ "order_of_interleaved_layers": "local_attn_first",
219
+ "position_embedding_type": "rope_gptj",
220
+ "rotary_pct": 1.0,
221
+ "use_embedding_sharing": true,
222
+ "use_gated_activation": true,
223
+ "use_parallel_block": true,
224
+ "use_parallel_embedding": true,
225
+ "use_qk_norm": false,
226
+ "tf_legacy_loss": false,
227
+ "use_bfloat16": false,
228
+ "output_attentions": false
229
+ },
230
+ "tf_legacy_loss": false,
231
+ "tie_encoder_decoder": false,
232
+ "tie_word_embeddings": true,
233
+ "tokenizer_class": null,
234
+ "top_k": 50,
235
+ "top_p": 1.0,
236
+ "torchscript": false,
237
+ "transformers_version": "4.55.2",
238
+ "typical_p": 1.0,
239
+ "use_bfloat16": false,
240
+ "vision_config": {
241
+ "return_dict": true,
242
+ "output_hidden_states": false,
243
+ "torchscript": false,
244
+ "torch_dtype": null,
245
+ "pruned_heads": {},
246
+ "tie_word_embeddings": true,
247
+ "chunk_size_feed_forward": 0,
248
+ "is_encoder_decoder": false,
249
+ "is_decoder": false,
250
+ "cross_attention_hidden_size": null,
251
+ "add_cross_attention": false,
252
+ "tie_encoder_decoder": false,
253
+ "architectures": null,
254
+ "finetuning_task": null,
255
+ "id2label": {
256
+ "0": "LABEL_0",
257
+ "1": "LABEL_1"
258
+ },
259
+ "label2id": {
260
+ "LABEL_0": 0,
261
+ "LABEL_1": 1
262
+ },
263
+ "task_specific_params": null,
264
+ "problem_type": null,
265
+ "tokenizer_class": null,
266
+ "prefix": null,
267
+ "bos_token_id": null,
268
+ "pad_token_id": null,
269
+ "eos_token_id": null,
270
+ "sep_token_id": null,
271
+ "decoder_start_token_id": null,
272
+ "max_length": 20,
273
+ "min_length": 0,
274
+ "do_sample": false,
275
+ "early_stopping": false,
276
+ "num_beams": 1,
277
+ "num_beam_groups": 1,
278
+ "diversity_penalty": 0.0,
279
+ "temperature": 1.0,
280
+ "top_k": 50,
281
+ "top_p": 1.0,
282
+ "typical_p": 1.0,
283
+ "repetition_penalty": 1.0,
284
+ "length_penalty": 1.0,
285
+ "no_repeat_ngram_size": 0,
286
+ "encoder_no_repeat_ngram_size": 0,
287
+ "bad_words_ids": null,
288
+ "num_return_sequences": 1,
289
+ "output_scores": false,
290
+ "return_dict_in_generate": false,
291
+ "forced_bos_token_id": null,
292
+ "forced_eos_token_id": null,
293
+ "remove_invalid_values": false,
294
+ "exponential_decay_length_penalty": null,
295
+ "suppress_tokens": null,
296
+ "begin_suppress_tokens": null,
297
+ "_name_or_path": "",
298
+ "model_type": "siglip_vision_model",
299
+ "vision_use_head": false,
300
+ "tf_legacy_loss": false,
301
+ "use_bfloat16": false,
302
+ "hidden_size": 1152,
303
+ "intermediate_size": 4304,
304
+ "num_hidden_layers": 27,
305
+ "num_attention_heads": 16,
306
+ "num_channels": 3,
307
+ "patch_size": 16,
308
+ "image_size": 512,
309
+ "attention_dropout": 0.0,
310
+ "layer_norm_eps": 1e-06,
311
+ "hidden_act": "gelu_pytorch_tanh",
312
+ "output_attentions": false
313
+ },
314
+ "vision_feature_layer": -1,
315
+ "vision_feature_select_strategy": "full"
316
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 5,
4
+ "cache_implementation": "hybrid",
5
+ "eos_token_id": 255001,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.54.0.dev0",
8
+ "do_sample": true,
9
+ "temperature": 0.3,
10
+ "top_p": 0.75
11
+ }
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa779c55e949b329b9eb0ab1f2ff21ed733fd6ab75c582390898f9dcf9c50556
3
+ size 5187165354
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99995f68cd207fdff71b069e88a8c61fa3fe8953e1021e1add5195a4e61bc9a6
3
+ size 5181177720
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a73e55635fe46aa054c90a70dc6123f81e5bb64006507acce98c81a95d609fe
3
+ size 5251930831
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09c87402747177ee1b8f1635f8c7a8fbe67b3fba43e31a6da1fbbc355a0a6a1
3
+ size 5181177868
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dbcdc366777d70e2ec1e20c0b4e1fa6f527f86f0ce9d29bdacec1177dc9ad74
3
+ size 5251930845
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:508bd34c43f478f15127db03aae25c4b0b35558abb5f7ea397e1a735be387cac
3
+ size 5181177880
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4058d27d83900cff45e26a3b8dcb166f592eeea8b8db9d57d7a174c7f925897
3
+ size 5251930853
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6e06138a992e760d033b23dc527827b4e97436c54c87c350fc8ec013aded1f
3
+ size 5181177874
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70d182e6d4faacabf18f06d1ea4aec97a6298ffe5b7e4a757b84dbc0d420776
3
+ size 5251930885
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b97d6cca648f83a2699ab3d6d56129b3b6ee44853687d56e81d59cfe0e7ff8
3
+ size 5181177850
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9961478e36ae1eae0a138c0deaead01f6cfa13e0771221ca3a47261b65a3a9
3
+ size 5251930867
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f1263082f5bdbe9900a0f1ee010949d705aab4cbc8e73dec6323218bde05c0
3
+ size 5181177856
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709cb24acb8f656cf73c22bebb149c4329b6edf37c2e245640d54400e95fb56b
3
+ size 987515121
model.safetensors.index.json ADDED
@@ -0,0 +1,963 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 111867525360,
4
+ "total_size": 223735050720
5
+ },
6
+ "weight_map": {
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00050.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00002-of-00050.safetensors",
9
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00002-of-00050.safetensors",
10
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00002-of-00050.safetensors",
11
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00002-of-00050.safetensors",
12
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
13
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00002-of-00050.safetensors",
14
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
15
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
16
+ "model.language_model.layers.1.input_layernorm.weight": "model-00003-of-00050.safetensors",
17
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00003-of-00050.safetensors",
18
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00003-of-00050.safetensors",
19
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00003-of-00050.safetensors",
20
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00003-of-00050.safetensors",
21
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00003-of-00050.safetensors",
22
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00003-of-00050.safetensors",
23
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00003-of-00050.safetensors",
24
+ "model.language_model.layers.10.input_layernorm.weight": "model-00010-of-00050.safetensors",
25
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00010-of-00050.safetensors",
26
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00009-of-00050.safetensors",
27
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00010-of-00050.safetensors",
28
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00009-of-00050.safetensors",
29
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00009-of-00050.safetensors",
30
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00009-of-00050.safetensors",
31
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00009-of-00050.safetensors",
32
+ "model.language_model.layers.11.input_layernorm.weight": "model-00011-of-00050.safetensors",
33
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00011-of-00050.safetensors",
34
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00010-of-00050.safetensors",
35
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00010-of-00050.safetensors",
36
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00010-of-00050.safetensors",
37
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00010-of-00050.safetensors",
38
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00010-of-00050.safetensors",
39
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00010-of-00050.safetensors",
40
+ "model.language_model.layers.12.input_layernorm.weight": "model-00011-of-00050.safetensors",
41
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00011-of-00050.safetensors",
42
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00011-of-00050.safetensors",
43
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00011-of-00050.safetensors",
44
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00011-of-00050.safetensors",
45
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00011-of-00050.safetensors",
46
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00011-of-00050.safetensors",
47
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00011-of-00050.safetensors",
48
+ "model.language_model.layers.13.input_layernorm.weight": "model-00012-of-00050.safetensors",
49
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00012-of-00050.safetensors",
50
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00012-of-00050.safetensors",
51
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00012-of-00050.safetensors",
52
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00011-of-00050.safetensors",
53
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00011-of-00050.safetensors",
54
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00011-of-00050.safetensors",
55
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00011-of-00050.safetensors",
56
+ "model.language_model.layers.14.input_layernorm.weight": "model-00013-of-00050.safetensors",
57
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00013-of-00050.safetensors",
58
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00012-of-00050.safetensors",
59
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00013-of-00050.safetensors",
60
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00012-of-00050.safetensors",
61
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00012-of-00050.safetensors",
62
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00012-of-00050.safetensors",
63
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00012-of-00050.safetensors",
64
+ "model.language_model.layers.15.input_layernorm.weight": "model-00014-of-00050.safetensors",
65
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00014-of-00050.safetensors",
66
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00013-of-00050.safetensors",
67
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00013-of-00050.safetensors",
68
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00013-of-00050.safetensors",
69
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00013-of-00050.safetensors",
70
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00013-of-00050.safetensors",
71
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00013-of-00050.safetensors",
72
+ "model.language_model.layers.16.input_layernorm.weight": "model-00014-of-00050.safetensors",
73
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00014-of-00050.safetensors",
74
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00014-of-00050.safetensors",
75
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00014-of-00050.safetensors",
76
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00014-of-00050.safetensors",
77
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00014-of-00050.safetensors",
78
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00014-of-00050.safetensors",
79
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00014-of-00050.safetensors",
80
+ "model.language_model.layers.17.input_layernorm.weight": "model-00015-of-00050.safetensors",
81
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00015-of-00050.safetensors",
82
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00015-of-00050.safetensors",
83
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00015-of-00050.safetensors",
84
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00014-of-00050.safetensors",
85
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00014-of-00050.safetensors",
86
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00014-of-00050.safetensors",
87
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00014-of-00050.safetensors",
88
+ "model.language_model.layers.18.input_layernorm.weight": "model-00016-of-00050.safetensors",
89
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00016-of-00050.safetensors",
90
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00015-of-00050.safetensors",
91
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00016-of-00050.safetensors",
92
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00015-of-00050.safetensors",
93
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00015-of-00050.safetensors",
94
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00015-of-00050.safetensors",
95
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00015-of-00050.safetensors",
96
+ "model.language_model.layers.19.input_layernorm.weight": "model-00017-of-00050.safetensors",
97
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00017-of-00050.safetensors",
98
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00016-of-00050.safetensors",
99
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00016-of-00050.safetensors",
100
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00016-of-00050.safetensors",
101
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00016-of-00050.safetensors",
102
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00016-of-00050.safetensors",
103
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00016-of-00050.safetensors",
104
+ "model.language_model.layers.2.input_layernorm.weight": "model-00004-of-00050.safetensors",
105
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00004-of-00050.safetensors",
106
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00003-of-00050.safetensors",
107
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00004-of-00050.safetensors",
108
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00003-of-00050.safetensors",
109
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00003-of-00050.safetensors",
110
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00003-of-00050.safetensors",
111
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00003-of-00050.safetensors",
112
+ "model.language_model.layers.20.input_layernorm.weight": "model-00017-of-00050.safetensors",
113
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00017-of-00050.safetensors",
114
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00017-of-00050.safetensors",
115
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00017-of-00050.safetensors",
116
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00017-of-00050.safetensors",
117
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00017-of-00050.safetensors",
118
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00017-of-00050.safetensors",
119
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00017-of-00050.safetensors",
120
+ "model.language_model.layers.21.input_layernorm.weight": "model-00018-of-00050.safetensors",
121
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00018-of-00050.safetensors",
122
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00018-of-00050.safetensors",
123
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00018-of-00050.safetensors",
124
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00017-of-00050.safetensors",
125
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00017-of-00050.safetensors",
126
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00017-of-00050.safetensors",
127
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00017-of-00050.safetensors",
128
+ "model.language_model.layers.22.input_layernorm.weight": "model-00019-of-00050.safetensors",
129
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00019-of-00050.safetensors",
130
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00018-of-00050.safetensors",
131
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00019-of-00050.safetensors",
132
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00018-of-00050.safetensors",
133
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00018-of-00050.safetensors",
134
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00018-of-00050.safetensors",
135
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00018-of-00050.safetensors",
136
+ "model.language_model.layers.23.input_layernorm.weight": "model-00020-of-00050.safetensors",
137
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00020-of-00050.safetensors",
138
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00019-of-00050.safetensors",
139
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00019-of-00050.safetensors",
140
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00019-of-00050.safetensors",
141
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00019-of-00050.safetensors",
142
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00019-of-00050.safetensors",
143
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00019-of-00050.safetensors",
144
+ "model.language_model.layers.24.input_layernorm.weight": "model-00020-of-00050.safetensors",
145
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00020-of-00050.safetensors",
146
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00020-of-00050.safetensors",
147
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00020-of-00050.safetensors",
148
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00020-of-00050.safetensors",
149
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00020-of-00050.safetensors",
150
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00020-of-00050.safetensors",
151
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00020-of-00050.safetensors",
152
+ "model.language_model.layers.25.input_layernorm.weight": "model-00021-of-00050.safetensors",
153
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00021-of-00050.safetensors",
154
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00021-of-00050.safetensors",
155
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00021-of-00050.safetensors",
156
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00020-of-00050.safetensors",
157
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00020-of-00050.safetensors",
158
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00020-of-00050.safetensors",
159
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00020-of-00050.safetensors",
160
+ "model.language_model.layers.26.input_layernorm.weight": "model-00022-of-00050.safetensors",
161
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00022-of-00050.safetensors",
162
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00021-of-00050.safetensors",
163
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00022-of-00050.safetensors",
164
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00021-of-00050.safetensors",
165
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00021-of-00050.safetensors",
166
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00021-of-00050.safetensors",
167
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00021-of-00050.safetensors",
168
+ "model.language_model.layers.27.input_layernorm.weight": "model-00023-of-00050.safetensors",
169
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00023-of-00050.safetensors",
170
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00022-of-00050.safetensors",
171
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00022-of-00050.safetensors",
172
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00022-of-00050.safetensors",
173
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00022-of-00050.safetensors",
174
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00022-of-00050.safetensors",
175
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00022-of-00050.safetensors",
176
+ "model.language_model.layers.28.input_layernorm.weight": "model-00023-of-00050.safetensors",
177
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00023-of-00050.safetensors",
178
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00023-of-00050.safetensors",
179
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00023-of-00050.safetensors",
180
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00023-of-00050.safetensors",
181
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00023-of-00050.safetensors",
182
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00023-of-00050.safetensors",
183
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00023-of-00050.safetensors",
184
+ "model.language_model.layers.29.input_layernorm.weight": "model-00024-of-00050.safetensors",
185
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00024-of-00050.safetensors",
186
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00024-of-00050.safetensors",
187
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00024-of-00050.safetensors",
188
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00023-of-00050.safetensors",
189
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00023-of-00050.safetensors",
190
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00023-of-00050.safetensors",
191
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00023-of-00050.safetensors",
192
+ "model.language_model.layers.3.input_layernorm.weight": "model-00005-of-00050.safetensors",
193
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00005-of-00050.safetensors",
194
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00004-of-00050.safetensors",
195
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00004-of-00050.safetensors",
196
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00004-of-00050.safetensors",
197
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00004-of-00050.safetensors",
198
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00004-of-00050.safetensors",
199
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00004-of-00050.safetensors",
200
+ "model.language_model.layers.30.input_layernorm.weight": "model-00025-of-00050.safetensors",
201
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00025-of-00050.safetensors",
202
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00024-of-00050.safetensors",
203
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00025-of-00050.safetensors",
204
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00024-of-00050.safetensors",
205
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00024-of-00050.safetensors",
206
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00024-of-00050.safetensors",
207
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00024-of-00050.safetensors",
208
+ "model.language_model.layers.31.input_layernorm.weight": "model-00026-of-00050.safetensors",
209
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00026-of-00050.safetensors",
210
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00025-of-00050.safetensors",
211
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00025-of-00050.safetensors",
212
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00025-of-00050.safetensors",
213
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00025-of-00050.safetensors",
214
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00025-of-00050.safetensors",
215
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00025-of-00050.safetensors",
216
+ "model.language_model.layers.32.input_layernorm.weight": "model-00026-of-00050.safetensors",
217
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00026-of-00050.safetensors",
218
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00026-of-00050.safetensors",
219
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00026-of-00050.safetensors",
220
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00026-of-00050.safetensors",
221
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00026-of-00050.safetensors",
222
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00026-of-00050.safetensors",
223
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00026-of-00050.safetensors",
224
+ "model.language_model.layers.33.input_layernorm.weight": "model-00027-of-00050.safetensors",
225
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00027-of-00050.safetensors",
226
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00027-of-00050.safetensors",
227
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00027-of-00050.safetensors",
228
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00026-of-00050.safetensors",
229
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00026-of-00050.safetensors",
230
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00026-of-00050.safetensors",
231
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00026-of-00050.safetensors",
232
+ "model.language_model.layers.34.input_layernorm.weight": "model-00028-of-00050.safetensors",
233
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00028-of-00050.safetensors",
234
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00027-of-00050.safetensors",
235
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00028-of-00050.safetensors",
236
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00027-of-00050.safetensors",
237
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00027-of-00050.safetensors",
238
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00027-of-00050.safetensors",
239
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00027-of-00050.safetensors",
240
+ "model.language_model.layers.35.input_layernorm.weight": "model-00029-of-00050.safetensors",
241
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00029-of-00050.safetensors",
242
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00028-of-00050.safetensors",
243
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00028-of-00050.safetensors",
244
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00028-of-00050.safetensors",
245
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00028-of-00050.safetensors",
246
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00028-of-00050.safetensors",
247
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00028-of-00050.safetensors",
248
+ "model.language_model.layers.36.input_layernorm.weight": "model-00029-of-00050.safetensors",
249
+ "model.language_model.layers.36.mlp.down_proj.weight": "model-00029-of-00050.safetensors",
250
+ "model.language_model.layers.36.mlp.gate_proj.weight": "model-00029-of-00050.safetensors",
251
+ "model.language_model.layers.36.mlp.up_proj.weight": "model-00029-of-00050.safetensors",
252
+ "model.language_model.layers.36.self_attn.k_proj.weight": "model-00029-of-00050.safetensors",
253
+ "model.language_model.layers.36.self_attn.o_proj.weight": "model-00029-of-00050.safetensors",
254
+ "model.language_model.layers.36.self_attn.q_proj.weight": "model-00029-of-00050.safetensors",
255
+ "model.language_model.layers.36.self_attn.v_proj.weight": "model-00029-of-00050.safetensors",
256
+ "model.language_model.layers.37.input_layernorm.weight": "model-00030-of-00050.safetensors",
257
+ "model.language_model.layers.37.mlp.down_proj.weight": "model-00030-of-00050.safetensors",
258
+ "model.language_model.layers.37.mlp.gate_proj.weight": "model-00030-of-00050.safetensors",
259
+ "model.language_model.layers.37.mlp.up_proj.weight": "model-00030-of-00050.safetensors",
260
+ "model.language_model.layers.37.self_attn.k_proj.weight": "model-00029-of-00050.safetensors",
261
+ "model.language_model.layers.37.self_attn.o_proj.weight": "model-00029-of-00050.safetensors",
262
+ "model.language_model.layers.37.self_attn.q_proj.weight": "model-00029-of-00050.safetensors",
263
+ "model.language_model.layers.37.self_attn.v_proj.weight": "model-00029-of-00050.safetensors",
264
+ "model.language_model.layers.38.input_layernorm.weight": "model-00031-of-00050.safetensors",
265
+ "model.language_model.layers.38.mlp.down_proj.weight": "model-00031-of-00050.safetensors",
266
+ "model.language_model.layers.38.mlp.gate_proj.weight": "model-00030-of-00050.safetensors",
267
+ "model.language_model.layers.38.mlp.up_proj.weight": "model-00031-of-00050.safetensors",
268
+ "model.language_model.layers.38.self_attn.k_proj.weight": "model-00030-of-00050.safetensors",
269
+ "model.language_model.layers.38.self_attn.o_proj.weight": "model-00030-of-00050.safetensors",
270
+ "model.language_model.layers.38.self_attn.q_proj.weight": "model-00030-of-00050.safetensors",
271
+ "model.language_model.layers.38.self_attn.v_proj.weight": "model-00030-of-00050.safetensors",
272
+ "model.language_model.layers.39.input_layernorm.weight": "model-00032-of-00050.safetensors",
273
+ "model.language_model.layers.39.mlp.down_proj.weight": "model-00032-of-00050.safetensors",
274
+ "model.language_model.layers.39.mlp.gate_proj.weight": "model-00031-of-00050.safetensors",
275
+ "model.language_model.layers.39.mlp.up_proj.weight": "model-00031-of-00050.safetensors",
276
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00031-of-00050.safetensors",
277
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00031-of-00050.safetensors",
278
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00031-of-00050.safetensors",
279
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00031-of-00050.safetensors",
280
+ "model.language_model.layers.4.input_layernorm.weight": "model-00005-of-00050.safetensors",
281
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00005-of-00050.safetensors",
282
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00005-of-00050.safetensors",
283
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00005-of-00050.safetensors",
284
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00005-of-00050.safetensors",
285
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00005-of-00050.safetensors",
286
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00005-of-00050.safetensors",
287
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00005-of-00050.safetensors",
288
+ "model.language_model.layers.40.input_layernorm.weight": "model-00032-of-00050.safetensors",
289
+ "model.language_model.layers.40.mlp.down_proj.weight": "model-00032-of-00050.safetensors",
290
+ "model.language_model.layers.40.mlp.gate_proj.weight": "model-00032-of-00050.safetensors",
291
+ "model.language_model.layers.40.mlp.up_proj.weight": "model-00032-of-00050.safetensors",
292
+ "model.language_model.layers.40.self_attn.k_proj.weight": "model-00032-of-00050.safetensors",
293
+ "model.language_model.layers.40.self_attn.o_proj.weight": "model-00032-of-00050.safetensors",
294
+ "model.language_model.layers.40.self_attn.q_proj.weight": "model-00032-of-00050.safetensors",
295
+ "model.language_model.layers.40.self_attn.v_proj.weight": "model-00032-of-00050.safetensors",
296
+ "model.language_model.layers.41.input_layernorm.weight": "model-00033-of-00050.safetensors",
297
+ "model.language_model.layers.41.mlp.down_proj.weight": "model-00033-of-00050.safetensors",
298
+ "model.language_model.layers.41.mlp.gate_proj.weight": "model-00033-of-00050.safetensors",
299
+ "model.language_model.layers.41.mlp.up_proj.weight": "model-00033-of-00050.safetensors",
300
+ "model.language_model.layers.41.self_attn.k_proj.weight": "model-00032-of-00050.safetensors",
301
+ "model.language_model.layers.41.self_attn.o_proj.weight": "model-00032-of-00050.safetensors",
302
+ "model.language_model.layers.41.self_attn.q_proj.weight": "model-00032-of-00050.safetensors",
303
+ "model.language_model.layers.41.self_attn.v_proj.weight": "model-00032-of-00050.safetensors",
304
+ "model.language_model.layers.42.input_layernorm.weight": "model-00034-of-00050.safetensors",
305
+ "model.language_model.layers.42.mlp.down_proj.weight": "model-00034-of-00050.safetensors",
306
+ "model.language_model.layers.42.mlp.gate_proj.weight": "model-00033-of-00050.safetensors",
307
+ "model.language_model.layers.42.mlp.up_proj.weight": "model-00034-of-00050.safetensors",
308
+ "model.language_model.layers.42.self_attn.k_proj.weight": "model-00033-of-00050.safetensors",
309
+ "model.language_model.layers.42.self_attn.o_proj.weight": "model-00033-of-00050.safetensors",
310
+ "model.language_model.layers.42.self_attn.q_proj.weight": "model-00033-of-00050.safetensors",
311
+ "model.language_model.layers.42.self_attn.v_proj.weight": "model-00033-of-00050.safetensors",
312
+ "model.language_model.layers.43.input_layernorm.weight": "model-00035-of-00050.safetensors",
313
+ "model.language_model.layers.43.mlp.down_proj.weight": "model-00035-of-00050.safetensors",
314
+ "model.language_model.layers.43.mlp.gate_proj.weight": "model-00034-of-00050.safetensors",
315
+ "model.language_model.layers.43.mlp.up_proj.weight": "model-00034-of-00050.safetensors",
316
+ "model.language_model.layers.43.self_attn.k_proj.weight": "model-00034-of-00050.safetensors",
317
+ "model.language_model.layers.43.self_attn.o_proj.weight": "model-00034-of-00050.safetensors",
318
+ "model.language_model.layers.43.self_attn.q_proj.weight": "model-00034-of-00050.safetensors",
319
+ "model.language_model.layers.43.self_attn.v_proj.weight": "model-00034-of-00050.safetensors",
320
+ "model.language_model.layers.44.input_layernorm.weight": "model-00035-of-00050.safetensors",
321
+ "model.language_model.layers.44.mlp.down_proj.weight": "model-00035-of-00050.safetensors",
322
+ "model.language_model.layers.44.mlp.gate_proj.weight": "model-00035-of-00050.safetensors",
323
+ "model.language_model.layers.44.mlp.up_proj.weight": "model-00035-of-00050.safetensors",
324
+ "model.language_model.layers.44.self_attn.k_proj.weight": "model-00035-of-00050.safetensors",
325
+ "model.language_model.layers.44.self_attn.o_proj.weight": "model-00035-of-00050.safetensors",
326
+ "model.language_model.layers.44.self_attn.q_proj.weight": "model-00035-of-00050.safetensors",
327
+ "model.language_model.layers.44.self_attn.v_proj.weight": "model-00035-of-00050.safetensors",
328
+ "model.language_model.layers.45.input_layernorm.weight": "model-00036-of-00050.safetensors",
329
+ "model.language_model.layers.45.mlp.down_proj.weight": "model-00036-of-00050.safetensors",
330
+ "model.language_model.layers.45.mlp.gate_proj.weight": "model-00036-of-00050.safetensors",
331
+ "model.language_model.layers.45.mlp.up_proj.weight": "model-00036-of-00050.safetensors",
332
+ "model.language_model.layers.45.self_attn.k_proj.weight": "model-00035-of-00050.safetensors",
333
+ "model.language_model.layers.45.self_attn.o_proj.weight": "model-00035-of-00050.safetensors",
334
+ "model.language_model.layers.45.self_attn.q_proj.weight": "model-00035-of-00050.safetensors",
335
+ "model.language_model.layers.45.self_attn.v_proj.weight": "model-00035-of-00050.safetensors",
336
+ "model.language_model.layers.46.input_layernorm.weight": "model-00037-of-00050.safetensors",
337
+ "model.language_model.layers.46.mlp.down_proj.weight": "model-00037-of-00050.safetensors",
338
+ "model.language_model.layers.46.mlp.gate_proj.weight": "model-00036-of-00050.safetensors",
339
+ "model.language_model.layers.46.mlp.up_proj.weight": "model-00037-of-00050.safetensors",
340
+ "model.language_model.layers.46.self_attn.k_proj.weight": "model-00036-of-00050.safetensors",
341
+ "model.language_model.layers.46.self_attn.o_proj.weight": "model-00036-of-00050.safetensors",
342
+ "model.language_model.layers.46.self_attn.q_proj.weight": "model-00036-of-00050.safetensors",
343
+ "model.language_model.layers.46.self_attn.v_proj.weight": "model-00036-of-00050.safetensors",
344
+ "model.language_model.layers.47.input_layernorm.weight": "model-00038-of-00050.safetensors",
345
+ "model.language_model.layers.47.mlp.down_proj.weight": "model-00038-of-00050.safetensors",
346
+ "model.language_model.layers.47.mlp.gate_proj.weight": "model-00037-of-00050.safetensors",
347
+ "model.language_model.layers.47.mlp.up_proj.weight": "model-00037-of-00050.safetensors",
348
+ "model.language_model.layers.47.self_attn.k_proj.weight": "model-00037-of-00050.safetensors",
349
+ "model.language_model.layers.47.self_attn.o_proj.weight": "model-00037-of-00050.safetensors",
350
+ "model.language_model.layers.47.self_attn.q_proj.weight": "model-00037-of-00050.safetensors",
351
+ "model.language_model.layers.47.self_attn.v_proj.weight": "model-00037-of-00050.safetensors",
352
+ "model.language_model.layers.48.input_layernorm.weight": "model-00038-of-00050.safetensors",
353
+ "model.language_model.layers.48.mlp.down_proj.weight": "model-00038-of-00050.safetensors",
354
+ "model.language_model.layers.48.mlp.gate_proj.weight": "model-00038-of-00050.safetensors",
355
+ "model.language_model.layers.48.mlp.up_proj.weight": "model-00038-of-00050.safetensors",
356
+ "model.language_model.layers.48.self_attn.k_proj.weight": "model-00038-of-00050.safetensors",
357
+ "model.language_model.layers.48.self_attn.o_proj.weight": "model-00038-of-00050.safetensors",
358
+ "model.language_model.layers.48.self_attn.q_proj.weight": "model-00038-of-00050.safetensors",
359
+ "model.language_model.layers.48.self_attn.v_proj.weight": "model-00038-of-00050.safetensors",
360
+ "model.language_model.layers.49.input_layernorm.weight": "model-00039-of-00050.safetensors",
361
+ "model.language_model.layers.49.mlp.down_proj.weight": "model-00039-of-00050.safetensors",
362
+ "model.language_model.layers.49.mlp.gate_proj.weight": "model-00039-of-00050.safetensors",
363
+ "model.language_model.layers.49.mlp.up_proj.weight": "model-00039-of-00050.safetensors",
364
+ "model.language_model.layers.49.self_attn.k_proj.weight": "model-00038-of-00050.safetensors",
365
+ "model.language_model.layers.49.self_attn.o_proj.weight": "model-00038-of-00050.safetensors",
366
+ "model.language_model.layers.49.self_attn.q_proj.weight": "model-00038-of-00050.safetensors",
367
+ "model.language_model.layers.49.self_attn.v_proj.weight": "model-00038-of-00050.safetensors",
368
+ "model.language_model.layers.5.input_layernorm.weight": "model-00006-of-00050.safetensors",
369
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00006-of-00050.safetensors",
370
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00006-of-00050.safetensors",
371
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00006-of-00050.safetensors",
372
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00005-of-00050.safetensors",
373
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00005-of-00050.safetensors",
374
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00005-of-00050.safetensors",
375
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00005-of-00050.safetensors",
376
+ "model.language_model.layers.50.input_layernorm.weight": "model-00040-of-00050.safetensors",
377
+ "model.language_model.layers.50.mlp.down_proj.weight": "model-00040-of-00050.safetensors",
378
+ "model.language_model.layers.50.mlp.gate_proj.weight": "model-00039-of-00050.safetensors",
379
+ "model.language_model.layers.50.mlp.up_proj.weight": "model-00040-of-00050.safetensors",
380
+ "model.language_model.layers.50.self_attn.k_proj.weight": "model-00039-of-00050.safetensors",
381
+ "model.language_model.layers.50.self_attn.o_proj.weight": "model-00039-of-00050.safetensors",
382
+ "model.language_model.layers.50.self_attn.q_proj.weight": "model-00039-of-00050.safetensors",
383
+ "model.language_model.layers.50.self_attn.v_proj.weight": "model-00039-of-00050.safetensors",
384
+ "model.language_model.layers.51.input_layernorm.weight": "model-00041-of-00050.safetensors",
385
+ "model.language_model.layers.51.mlp.down_proj.weight": "model-00041-of-00050.safetensors",
386
+ "model.language_model.layers.51.mlp.gate_proj.weight": "model-00040-of-00050.safetensors",
387
+ "model.language_model.layers.51.mlp.up_proj.weight": "model-00040-of-00050.safetensors",
388
+ "model.language_model.layers.51.self_attn.k_proj.weight": "model-00040-of-00050.safetensors",
389
+ "model.language_model.layers.51.self_attn.o_proj.weight": "model-00040-of-00050.safetensors",
390
+ "model.language_model.layers.51.self_attn.q_proj.weight": "model-00040-of-00050.safetensors",
391
+ "model.language_model.layers.51.self_attn.v_proj.weight": "model-00040-of-00050.safetensors",
392
+ "model.language_model.layers.52.input_layernorm.weight": "model-00041-of-00050.safetensors",
393
+ "model.language_model.layers.52.mlp.down_proj.weight": "model-00041-of-00050.safetensors",
394
+ "model.language_model.layers.52.mlp.gate_proj.weight": "model-00041-of-00050.safetensors",
395
+ "model.language_model.layers.52.mlp.up_proj.weight": "model-00041-of-00050.safetensors",
396
+ "model.language_model.layers.52.self_attn.k_proj.weight": "model-00041-of-00050.safetensors",
397
+ "model.language_model.layers.52.self_attn.o_proj.weight": "model-00041-of-00050.safetensors",
398
+ "model.language_model.layers.52.self_attn.q_proj.weight": "model-00041-of-00050.safetensors",
399
+ "model.language_model.layers.52.self_attn.v_proj.weight": "model-00041-of-00050.safetensors",
400
+ "model.language_model.layers.53.input_layernorm.weight": "model-00042-of-00050.safetensors",
401
+ "model.language_model.layers.53.mlp.down_proj.weight": "model-00042-of-00050.safetensors",
402
+ "model.language_model.layers.53.mlp.gate_proj.weight": "model-00042-of-00050.safetensors",
403
+ "model.language_model.layers.53.mlp.up_proj.weight": "model-00042-of-00050.safetensors",
404
+ "model.language_model.layers.53.self_attn.k_proj.weight": "model-00041-of-00050.safetensors",
405
+ "model.language_model.layers.53.self_attn.o_proj.weight": "model-00041-of-00050.safetensors",
406
+ "model.language_model.layers.53.self_attn.q_proj.weight": "model-00041-of-00050.safetensors",
407
+ "model.language_model.layers.53.self_attn.v_proj.weight": "model-00041-of-00050.safetensors",
408
+ "model.language_model.layers.54.input_layernorm.weight": "model-00043-of-00050.safetensors",
409
+ "model.language_model.layers.54.mlp.down_proj.weight": "model-00043-of-00050.safetensors",
410
+ "model.language_model.layers.54.mlp.gate_proj.weight": "model-00042-of-00050.safetensors",
411
+ "model.language_model.layers.54.mlp.up_proj.weight": "model-00043-of-00050.safetensors",
412
+ "model.language_model.layers.54.self_attn.k_proj.weight": "model-00042-of-00050.safetensors",
413
+ "model.language_model.layers.54.self_attn.o_proj.weight": "model-00042-of-00050.safetensors",
414
+ "model.language_model.layers.54.self_attn.q_proj.weight": "model-00042-of-00050.safetensors",
415
+ "model.language_model.layers.54.self_attn.v_proj.weight": "model-00042-of-00050.safetensors",
416
+ "model.language_model.layers.55.input_layernorm.weight": "model-00044-of-00050.safetensors",
417
+ "model.language_model.layers.55.mlp.down_proj.weight": "model-00044-of-00050.safetensors",
418
+ "model.language_model.layers.55.mlp.gate_proj.weight": "model-00043-of-00050.safetensors",
419
+ "model.language_model.layers.55.mlp.up_proj.weight": "model-00043-of-00050.safetensors",
420
+ "model.language_model.layers.55.self_attn.k_proj.weight": "model-00043-of-00050.safetensors",
421
+ "model.language_model.layers.55.self_attn.o_proj.weight": "model-00043-of-00050.safetensors",
422
+ "model.language_model.layers.55.self_attn.q_proj.weight": "model-00043-of-00050.safetensors",
423
+ "model.language_model.layers.55.self_attn.v_proj.weight": "model-00043-of-00050.safetensors",
424
+ "model.language_model.layers.56.input_layernorm.weight": "model-00044-of-00050.safetensors",
425
+ "model.language_model.layers.56.mlp.down_proj.weight": "model-00044-of-00050.safetensors",
426
+ "model.language_model.layers.56.mlp.gate_proj.weight": "model-00044-of-00050.safetensors",
427
+ "model.language_model.layers.56.mlp.up_proj.weight": "model-00044-of-00050.safetensors",
428
+ "model.language_model.layers.56.self_attn.k_proj.weight": "model-00044-of-00050.safetensors",
429
+ "model.language_model.layers.56.self_attn.o_proj.weight": "model-00044-of-00050.safetensors",
430
+ "model.language_model.layers.56.self_attn.q_proj.weight": "model-00044-of-00050.safetensors",
431
+ "model.language_model.layers.56.self_attn.v_proj.weight": "model-00044-of-00050.safetensors",
432
+ "model.language_model.layers.57.input_layernorm.weight": "model-00045-of-00050.safetensors",
433
+ "model.language_model.layers.57.mlp.down_proj.weight": "model-00045-of-00050.safetensors",
434
+ "model.language_model.layers.57.mlp.gate_proj.weight": "model-00045-of-00050.safetensors",
435
+ "model.language_model.layers.57.mlp.up_proj.weight": "model-00045-of-00050.safetensors",
436
+ "model.language_model.layers.57.self_attn.k_proj.weight": "model-00044-of-00050.safetensors",
437
+ "model.language_model.layers.57.self_attn.o_proj.weight": "model-00044-of-00050.safetensors",
438
+ "model.language_model.layers.57.self_attn.q_proj.weight": "model-00044-of-00050.safetensors",
439
+ "model.language_model.layers.57.self_attn.v_proj.weight": "model-00044-of-00050.safetensors",
440
+ "model.language_model.layers.58.input_layernorm.weight": "model-00046-of-00050.safetensors",
441
+ "model.language_model.layers.58.mlp.down_proj.weight": "model-00046-of-00050.safetensors",
442
+ "model.language_model.layers.58.mlp.gate_proj.weight": "model-00045-of-00050.safetensors",
443
+ "model.language_model.layers.58.mlp.up_proj.weight": "model-00046-of-00050.safetensors",
444
+ "model.language_model.layers.58.self_attn.k_proj.weight": "model-00045-of-00050.safetensors",
445
+ "model.language_model.layers.58.self_attn.o_proj.weight": "model-00045-of-00050.safetensors",
446
+ "model.language_model.layers.58.self_attn.q_proj.weight": "model-00045-of-00050.safetensors",
447
+ "model.language_model.layers.58.self_attn.v_proj.weight": "model-00045-of-00050.safetensors",
448
+ "model.language_model.layers.59.input_layernorm.weight": "model-00047-of-00050.safetensors",
449
+ "model.language_model.layers.59.mlp.down_proj.weight": "model-00047-of-00050.safetensors",
450
+ "model.language_model.layers.59.mlp.gate_proj.weight": "model-00046-of-00050.safetensors",
451
+ "model.language_model.layers.59.mlp.up_proj.weight": "model-00046-of-00050.safetensors",
452
+ "model.language_model.layers.59.self_attn.k_proj.weight": "model-00046-of-00050.safetensors",
453
+ "model.language_model.layers.59.self_attn.o_proj.weight": "model-00046-of-00050.safetensors",
454
+ "model.language_model.layers.59.self_attn.q_proj.weight": "model-00046-of-00050.safetensors",
455
+ "model.language_model.layers.59.self_attn.v_proj.weight": "model-00046-of-00050.safetensors",
456
+ "model.language_model.layers.6.input_layernorm.weight": "model-00007-of-00050.safetensors",
457
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00007-of-00050.safetensors",
458
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00006-of-00050.safetensors",
459
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00007-of-00050.safetensors",
460
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00006-of-00050.safetensors",
461
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00006-of-00050.safetensors",
462
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00006-of-00050.safetensors",
463
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00006-of-00050.safetensors",
464
+ "model.language_model.layers.60.input_layernorm.weight": "model-00047-of-00050.safetensors",
465
+ "model.language_model.layers.60.mlp.down_proj.weight": "model-00047-of-00050.safetensors",
466
+ "model.language_model.layers.60.mlp.gate_proj.weight": "model-00047-of-00050.safetensors",
467
+ "model.language_model.layers.60.mlp.up_proj.weight": "model-00047-of-00050.safetensors",
468
+ "model.language_model.layers.60.self_attn.k_proj.weight": "model-00047-of-00050.safetensors",
469
+ "model.language_model.layers.60.self_attn.o_proj.weight": "model-00047-of-00050.safetensors",
470
+ "model.language_model.layers.60.self_attn.q_proj.weight": "model-00047-of-00050.safetensors",
471
+ "model.language_model.layers.60.self_attn.v_proj.weight": "model-00047-of-00050.safetensors",
472
+ "model.language_model.layers.61.input_layernorm.weight": "model-00048-of-00050.safetensors",
473
+ "model.language_model.layers.61.mlp.down_proj.weight": "model-00048-of-00050.safetensors",
474
+ "model.language_model.layers.61.mlp.gate_proj.weight": "model-00048-of-00050.safetensors",
475
+ "model.language_model.layers.61.mlp.up_proj.weight": "model-00048-of-00050.safetensors",
476
+ "model.language_model.layers.61.self_attn.k_proj.weight": "model-00047-of-00050.safetensors",
477
+ "model.language_model.layers.61.self_attn.o_proj.weight": "model-00047-of-00050.safetensors",
478
+ "model.language_model.layers.61.self_attn.q_proj.weight": "model-00047-of-00050.safetensors",
479
+ "model.language_model.layers.61.self_attn.v_proj.weight": "model-00047-of-00050.safetensors",
480
+ "model.language_model.layers.62.input_layernorm.weight": "model-00049-of-00050.safetensors",
481
+ "model.language_model.layers.62.mlp.down_proj.weight": "model-00049-of-00050.safetensors",
482
+ "model.language_model.layers.62.mlp.gate_proj.weight": "model-00048-of-00050.safetensors",
483
+ "model.language_model.layers.62.mlp.up_proj.weight": "model-00049-of-00050.safetensors",
484
+ "model.language_model.layers.62.self_attn.k_proj.weight": "model-00048-of-00050.safetensors",
485
+ "model.language_model.layers.62.self_attn.o_proj.weight": "model-00048-of-00050.safetensors",
486
+ "model.language_model.layers.62.self_attn.q_proj.weight": "model-00048-of-00050.safetensors",
487
+ "model.language_model.layers.62.self_attn.v_proj.weight": "model-00048-of-00050.safetensors",
488
+ "model.language_model.layers.63.input_layernorm.weight": "model-00050-of-00050.safetensors",
489
+ "model.language_model.layers.63.mlp.down_proj.weight": "model-00050-of-00050.safetensors",
490
+ "model.language_model.layers.63.mlp.gate_proj.weight": "model-00049-of-00050.safetensors",
491
+ "model.language_model.layers.63.mlp.up_proj.weight": "model-00049-of-00050.safetensors",
492
+ "model.language_model.layers.63.self_attn.k_proj.weight": "model-00049-of-00050.safetensors",
493
+ "model.language_model.layers.63.self_attn.o_proj.weight": "model-00049-of-00050.safetensors",
494
+ "model.language_model.layers.63.self_attn.q_proj.weight": "model-00049-of-00050.safetensors",
495
+ "model.language_model.layers.63.self_attn.v_proj.weight": "model-00049-of-00050.safetensors",
496
+ "model.language_model.layers.7.input_layernorm.weight": "model-00008-of-00050.safetensors",
497
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00008-of-00050.safetensors",
498
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00007-of-00050.safetensors",
499
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00007-of-00050.safetensors",
500
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00007-of-00050.safetensors",
501
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00007-of-00050.safetensors",
502
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00007-of-00050.safetensors",
503
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00007-of-00050.safetensors",
504
+ "model.language_model.layers.8.input_layernorm.weight": "model-00008-of-00050.safetensors",
505
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00008-of-00050.safetensors",
506
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00008-of-00050.safetensors",
507
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00008-of-00050.safetensors",
508
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00008-of-00050.safetensors",
509
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00008-of-00050.safetensors",
510
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00008-of-00050.safetensors",
511
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00008-of-00050.safetensors",
512
+ "model.language_model.layers.9.input_layernorm.weight": "model-00009-of-00050.safetensors",
513
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00009-of-00050.safetensors",
514
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00009-of-00050.safetensors",
515
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00009-of-00050.safetensors",
516
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00008-of-00050.safetensors",
517
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00008-of-00050.safetensors",
518
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00008-of-00050.safetensors",
519
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00008-of-00050.safetensors",
520
+ "model.language_model.norm.weight": "model-00050-of-00050.safetensors",
521
+ "model.multi_modal_projector.linear_1.bias": "model-00002-of-00050.safetensors",
522
+ "model.multi_modal_projector.linear_1.weight": "model-00002-of-00050.safetensors",
523
+ "model.multi_modal_projector.linear_2.bias": "model-00002-of-00050.safetensors",
524
+ "model.multi_modal_projector.linear_2.weight": "model-00002-of-00050.safetensors",
525
+ "model.vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00002-of-00050.safetensors",
526
+ "model.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00002-of-00050.safetensors",
527
+ "model.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00002-of-00050.safetensors",
528
+ "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00002-of-00050.safetensors",
529
+ "model.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00002-of-00050.safetensors",
530
+ "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00002-of-00050.safetensors",
531
+ "model.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00002-of-00050.safetensors",
532
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00002-of-00050.safetensors",
533
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00002-of-00050.safetensors",
534
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00002-of-00050.safetensors",
535
+ "model.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00002-of-00050.safetensors",
536
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
537
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
538
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
539
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
540
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
541
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
542
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
543
+ "model.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
544
+ "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00002-of-00050.safetensors",
545
+ "model.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00002-of-00050.safetensors",
546
+ "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00002-of-00050.safetensors",
547
+ "model.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00002-of-00050.safetensors",
548
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00002-of-00050.safetensors",
549
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00002-of-00050.safetensors",
550
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00002-of-00050.safetensors",
551
+ "model.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00002-of-00050.safetensors",
552
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
553
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
554
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
555
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
556
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
557
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
558
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
559
+ "model.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
560
+ "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00002-of-00050.safetensors",
561
+ "model.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00002-of-00050.safetensors",
562
+ "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00002-of-00050.safetensors",
563
+ "model.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00002-of-00050.safetensors",
564
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00002-of-00050.safetensors",
565
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00002-of-00050.safetensors",
566
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00002-of-00050.safetensors",
567
+ "model.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00002-of-00050.safetensors",
568
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
569
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
570
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
571
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
572
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
573
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
574
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
575
+ "model.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
576
+ "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00002-of-00050.safetensors",
577
+ "model.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00002-of-00050.safetensors",
578
+ "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00002-of-00050.safetensors",
579
+ "model.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00002-of-00050.safetensors",
580
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00002-of-00050.safetensors",
581
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00002-of-00050.safetensors",
582
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00002-of-00050.safetensors",
583
+ "model.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00002-of-00050.safetensors",
584
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
585
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
586
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
587
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
588
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
589
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
590
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
591
+ "model.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
592
+ "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00002-of-00050.safetensors",
593
+ "model.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00002-of-00050.safetensors",
594
+ "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00002-of-00050.safetensors",
595
+ "model.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00002-of-00050.safetensors",
596
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00002-of-00050.safetensors",
597
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00002-of-00050.safetensors",
598
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00002-of-00050.safetensors",
599
+ "model.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00002-of-00050.safetensors",
600
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
601
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
602
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
603
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
604
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
605
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
606
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
607
+ "model.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
608
+ "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00002-of-00050.safetensors",
609
+ "model.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00002-of-00050.safetensors",
610
+ "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00002-of-00050.safetensors",
611
+ "model.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00002-of-00050.safetensors",
612
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00002-of-00050.safetensors",
613
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00002-of-00050.safetensors",
614
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00002-of-00050.safetensors",
615
+ "model.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00002-of-00050.safetensors",
616
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
617
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
618
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
619
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
620
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
621
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
622
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
623
+ "model.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
624
+ "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00002-of-00050.safetensors",
625
+ "model.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00002-of-00050.safetensors",
626
+ "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00002-of-00050.safetensors",
627
+ "model.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00002-of-00050.safetensors",
628
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00002-of-00050.safetensors",
629
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00002-of-00050.safetensors",
630
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00002-of-00050.safetensors",
631
+ "model.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00002-of-00050.safetensors",
632
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
633
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
634
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
635
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
636
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
637
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
638
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
639
+ "model.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
640
+ "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00002-of-00050.safetensors",
641
+ "model.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00002-of-00050.safetensors",
642
+ "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00002-of-00050.safetensors",
643
+ "model.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00002-of-00050.safetensors",
644
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00002-of-00050.safetensors",
645
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00002-of-00050.safetensors",
646
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00002-of-00050.safetensors",
647
+ "model.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00002-of-00050.safetensors",
648
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
649
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
650
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
651
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
652
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
653
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
654
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
655
+ "model.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
656
+ "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00002-of-00050.safetensors",
657
+ "model.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00002-of-00050.safetensors",
658
+ "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00002-of-00050.safetensors",
659
+ "model.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00002-of-00050.safetensors",
660
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00002-of-00050.safetensors",
661
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00002-of-00050.safetensors",
662
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00002-of-00050.safetensors",
663
+ "model.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00002-of-00050.safetensors",
664
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
665
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
666
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
667
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
668
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
669
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
670
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
671
+ "model.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
672
+ "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00002-of-00050.safetensors",
673
+ "model.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00002-of-00050.safetensors",
674
+ "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00002-of-00050.safetensors",
675
+ "model.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00002-of-00050.safetensors",
676
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00002-of-00050.safetensors",
677
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00002-of-00050.safetensors",
678
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00002-of-00050.safetensors",
679
+ "model.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00002-of-00050.safetensors",
680
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
681
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
682
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
683
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
684
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
685
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
686
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
687
+ "model.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
688
+ "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00002-of-00050.safetensors",
689
+ "model.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00002-of-00050.safetensors",
690
+ "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00002-of-00050.safetensors",
691
+ "model.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00002-of-00050.safetensors",
692
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00002-of-00050.safetensors",
693
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00002-of-00050.safetensors",
694
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00002-of-00050.safetensors",
695
+ "model.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00002-of-00050.safetensors",
696
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
697
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
698
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
699
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
700
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
701
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
702
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
703
+ "model.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
704
+ "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00002-of-00050.safetensors",
705
+ "model.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00002-of-00050.safetensors",
706
+ "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00002-of-00050.safetensors",
707
+ "model.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00002-of-00050.safetensors",
708
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00002-of-00050.safetensors",
709
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00002-of-00050.safetensors",
710
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00002-of-00050.safetensors",
711
+ "model.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00002-of-00050.safetensors",
712
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
713
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
714
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
715
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
716
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
717
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
718
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
719
+ "model.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
720
+ "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00002-of-00050.safetensors",
721
+ "model.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00002-of-00050.safetensors",
722
+ "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00002-of-00050.safetensors",
723
+ "model.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00002-of-00050.safetensors",
724
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00002-of-00050.safetensors",
725
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00002-of-00050.safetensors",
726
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00002-of-00050.safetensors",
727
+ "model.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00002-of-00050.safetensors",
728
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
729
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
730
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
731
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
732
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
733
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
734
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
735
+ "model.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
736
+ "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00002-of-00050.safetensors",
737
+ "model.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00002-of-00050.safetensors",
738
+ "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00002-of-00050.safetensors",
739
+ "model.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00002-of-00050.safetensors",
740
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00050.safetensors",
741
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00050.safetensors",
742
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00050.safetensors",
743
+ "model.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00050.safetensors",
744
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
745
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
746
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
747
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
748
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
749
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
750
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
751
+ "model.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
752
+ "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00002-of-00050.safetensors",
753
+ "model.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00002-of-00050.safetensors",
754
+ "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00002-of-00050.safetensors",
755
+ "model.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00002-of-00050.safetensors",
756
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00050.safetensors",
757
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00050.safetensors",
758
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00050.safetensors",
759
+ "model.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00050.safetensors",
760
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
761
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
762
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
763
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
764
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
765
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
766
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
767
+ "model.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
768
+ "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00002-of-00050.safetensors",
769
+ "model.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00002-of-00050.safetensors",
770
+ "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00002-of-00050.safetensors",
771
+ "model.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00002-of-00050.safetensors",
772
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00050.safetensors",
773
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00050.safetensors",
774
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00050.safetensors",
775
+ "model.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00050.safetensors",
776
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
777
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
778
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
779
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
780
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
781
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
782
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
783
+ "model.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
784
+ "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00002-of-00050.safetensors",
785
+ "model.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00002-of-00050.safetensors",
786
+ "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00002-of-00050.safetensors",
787
+ "model.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00002-of-00050.safetensors",
788
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00050.safetensors",
789
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00050.safetensors",
790
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00050.safetensors",
791
+ "model.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00050.safetensors",
792
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
793
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
794
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
795
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
796
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
797
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
798
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
799
+ "model.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
800
+ "model.vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00002-of-00050.safetensors",
801
+ "model.vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00002-of-00050.safetensors",
802
+ "model.vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00002-of-00050.safetensors",
803
+ "model.vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00002-of-00050.safetensors",
804
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00050.safetensors",
805
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00050.safetensors",
806
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00050.safetensors",
807
+ "model.vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00050.safetensors",
808
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
809
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
810
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
811
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
812
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
813
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
814
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
815
+ "model.vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
816
+ "model.vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00002-of-00050.safetensors",
817
+ "model.vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00002-of-00050.safetensors",
818
+ "model.vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00002-of-00050.safetensors",
819
+ "model.vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00002-of-00050.safetensors",
820
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00050.safetensors",
821
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00050.safetensors",
822
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00050.safetensors",
823
+ "model.vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00050.safetensors",
824
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
825
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
826
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
827
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
828
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
829
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
830
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
831
+ "model.vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
832
+ "model.vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00002-of-00050.safetensors",
833
+ "model.vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00002-of-00050.safetensors",
834
+ "model.vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00002-of-00050.safetensors",
835
+ "model.vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00002-of-00050.safetensors",
836
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00050.safetensors",
837
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00050.safetensors",
838
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00050.safetensors",
839
+ "model.vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00050.safetensors",
840
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
841
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
842
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
843
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
844
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
845
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
846
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
847
+ "model.vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
848
+ "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00002-of-00050.safetensors",
849
+ "model.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00002-of-00050.safetensors",
850
+ "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00002-of-00050.safetensors",
851
+ "model.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00002-of-00050.safetensors",
852
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00002-of-00050.safetensors",
853
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00002-of-00050.safetensors",
854
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00002-of-00050.safetensors",
855
+ "model.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00002-of-00050.safetensors",
856
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
857
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
858
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
859
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
860
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
861
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
862
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
863
+ "model.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
864
+ "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00002-of-00050.safetensors",
865
+ "model.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00002-of-00050.safetensors",
866
+ "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00002-of-00050.safetensors",
867
+ "model.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00002-of-00050.safetensors",
868
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00002-of-00050.safetensors",
869
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00002-of-00050.safetensors",
870
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00002-of-00050.safetensors",
871
+ "model.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00002-of-00050.safetensors",
872
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
873
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
874
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
875
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
876
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
877
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
878
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
879
+ "model.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
880
+ "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00002-of-00050.safetensors",
881
+ "model.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00002-of-00050.safetensors",
882
+ "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00002-of-00050.safetensors",
883
+ "model.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00002-of-00050.safetensors",
884
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00002-of-00050.safetensors",
885
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00002-of-00050.safetensors",
886
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00002-of-00050.safetensors",
887
+ "model.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00002-of-00050.safetensors",
888
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
889
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
890
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
891
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
892
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
893
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
894
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
895
+ "model.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
896
+ "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00002-of-00050.safetensors",
897
+ "model.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00002-of-00050.safetensors",
898
+ "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00002-of-00050.safetensors",
899
+ "model.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00002-of-00050.safetensors",
900
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00002-of-00050.safetensors",
901
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00002-of-00050.safetensors",
902
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00002-of-00050.safetensors",
903
+ "model.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00002-of-00050.safetensors",
904
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
905
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
906
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
907
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
908
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
909
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
910
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
911
+ "model.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
912
+ "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00002-of-00050.safetensors",
913
+ "model.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00002-of-00050.safetensors",
914
+ "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00002-of-00050.safetensors",
915
+ "model.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00002-of-00050.safetensors",
916
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00002-of-00050.safetensors",
917
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00002-of-00050.safetensors",
918
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00002-of-00050.safetensors",
919
+ "model.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00002-of-00050.safetensors",
920
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
921
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
922
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
923
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
924
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
925
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
926
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
927
+ "model.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
928
+ "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00002-of-00050.safetensors",
929
+ "model.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00002-of-00050.safetensors",
930
+ "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00002-of-00050.safetensors",
931
+ "model.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00002-of-00050.safetensors",
932
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00002-of-00050.safetensors",
933
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00002-of-00050.safetensors",
934
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00002-of-00050.safetensors",
935
+ "model.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00002-of-00050.safetensors",
936
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
937
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
938
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
939
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
940
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
941
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
942
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
943
+ "model.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
944
+ "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00002-of-00050.safetensors",
945
+ "model.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00002-of-00050.safetensors",
946
+ "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00002-of-00050.safetensors",
947
+ "model.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00002-of-00050.safetensors",
948
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00002-of-00050.safetensors",
949
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00002-of-00050.safetensors",
950
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00002-of-00050.safetensors",
951
+ "model.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00002-of-00050.safetensors",
952
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00002-of-00050.safetensors",
953
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00050.safetensors",
954
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00002-of-00050.safetensors",
955
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00050.safetensors",
956
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00002-of-00050.safetensors",
957
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
958
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00002-of-00050.safetensors",
959
+ "model.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
960
+ "model.vision_tower.vision_model.post_layernorm.bias": "model-00002-of-00050.safetensors",
961
+ "model.vision_tower.vision_model.post_layernorm.weight": "model-00002-of-00050.safetensors"
962
+ }
963
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "crop_to_patches": true,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "disable_grouping": null,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "downsample_factor": 2,
14
+ "end_of_img_token": "<|END_OF_IMG|>",
15
+ "image_mean": [
16
+ 0.5,
17
+ 0.5,
18
+ 0.5
19
+ ],
20
+ "image_processor_type": "Cohere2VisionImageProcessorFast",
21
+ "image_std": [
22
+ 0.5,
23
+ 0.5,
24
+ 0.5
25
+ ],
26
+ "img_line_break_token": "<|IMG_LINE_BREAK|>",
27
+ "img_patch_token": "<|IMG_PATCH|>",
28
+ "img_size": 512,
29
+ "input_data_format": null,
30
+ "max_patches": 12,
31
+ "min_patches": 1,
32
+ "patch_size": 16,
33
+ "processor_class": "Cohere2VisionProcessor",
34
+ "resample": 3,
35
+ "rescale_factor": 0.00392156862745098,
36
+ "return_tensors": null,
37
+ "size": {
38
+ "height": 512,
39
+ "width": 512
40
+ },
41
+ "start_of_img_token": "<|START_OF_IMG|>"
42
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|START_RESPONSE|>",
4
+ "<|END_RESPONSE|>"
5
+ ],
6
+ "boi_token": "<|START_OF_IMG|>",
7
+ "bos_token": {
8
+ "content": "<BOS_TOKEN>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eoi_token": "<|END_OF_IMG|>",
15
+ "eos_token": {
16
+ "content": "<|END_OF_TURN_TOKEN|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "image_token": "<|IMG_PATCH|>",
23
+ "img_line_break_token": "<|IMG_LINE_BREAK|>",
24
+ "pad_token": {
25
+ "content": "<PAD>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<UNK>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22a9a0f4ebeea673bc56f836c0ccb462a4daf1441316a93b3197ef615a46ec8
3
+ size 20125691
tokenizer_config.json ADDED
@@ -0,0 +1,395 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<PAD>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<UNK>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<CLS>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "3": {
31
+ "content": "<SEP>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "4": {
39
+ "content": "<MASK_TOKEN>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "5": {
47
+ "content": "<BOS_TOKEN>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "6": {
55
+ "content": "<EOS_TOKEN>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "7": {
63
+ "content": "<EOP_TOKEN>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "255000": {
71
+ "content": "<|START_OF_TURN_TOKEN|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "255001": {
79
+ "content": "<|END_OF_TURN_TOKEN|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "255002": {
87
+ "content": "<|YES_TOKEN|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "255003": {
95
+ "content": "<|NO_TOKEN|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "255004": {
103
+ "content": "<|GOOD_TOKEN|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "255005": {
111
+ "content": "<|BAD_TOKEN|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "255006": {
119
+ "content": "<|USER_TOKEN|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "255007": {
127
+ "content": "<|CHATBOT_TOKEN|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "255008": {
135
+ "content": "<|SYSTEM_TOKEN|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "255009": {
143
+ "content": "<|USER_0_TOKEN|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "255010": {
151
+ "content": "<|USER_1_TOKEN|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "255011": {
159
+ "content": "<|USER_2_TOKEN|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "255012": {
167
+ "content": "<|USER_3_TOKEN|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "255013": {
175
+ "content": "<|USER_4_TOKEN|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "255014": {
183
+ "content": "<|USER_5_TOKEN|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "255015": {
191
+ "content": "<|USER_6_TOKEN|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "255016": {
199
+ "content": "<|USER_7_TOKEN|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "255017": {
207
+ "content": "<|USER_8_TOKEN|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "255018": {
215
+ "content": "<|USER_9_TOKEN|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": false
221
+ },
222
+ "255019": {
223
+ "content": "<|START_THINKING|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": false
229
+ },
230
+ "255020": {
231
+ "content": "<|END_THINKING|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": false
237
+ },
238
+ "255021": {
239
+ "content": "<|START_RESPONSE|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "255022": {
247
+ "content": "<|END_RESPONSE|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "255023": {
255
+ "content": "<|START_ACTION|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": false
261
+ },
262
+ "255024": {
263
+ "content": "<|END_ACTION|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": false
269
+ },
270
+ "255025": {
271
+ "content": "<|START_TOOL_RESULT|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": false
277
+ },
278
+ "255026": {
279
+ "content": "<|END_TOOL_RESULT|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": false
285
+ },
286
+ "255027": {
287
+ "content": "<|EXTRA_8_TOKEN|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": false
293
+ },
294
+ "255028": {
295
+ "content": "<|NEW_FILE|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "255029": {
303
+ "content": "<|BEGINNING_OF_PREFIX_FIM_TOKEN|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": false
309
+ },
310
+ "255030": {
311
+ "content": "<|BEGINNING_OF_MIDDLE_FIM_TOKEN|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": false
317
+ },
318
+ "255031": {
319
+ "content": "<|BEGINNING_OF_SUFFIX_FIM_TOKEN|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": false
325
+ },
326
+ "255032": {
327
+ "content": "<|END_OF_MIDDLE_FIM_TOKEN|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": false
333
+ },
334
+ "255033": {
335
+ "content": "<|START_OF_IMG|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "255034": {
343
+ "content": "<|END_OF_IMG|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "255035": {
351
+ "content": "<|IMG_LINE_BREAK|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "255036": {
359
+ "content": "<|IMG_PATCH|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ }
366
+ },
367
+ "additional_special_tokens": [
368
+ "<|START_RESPONSE|>",
369
+ "<|END_RESPONSE|>"
370
+ ],
371
+ "boi_token": "<|START_OF_IMG|>",
372
+ "bos_token": "<BOS_TOKEN>",
373
+ "clean_up_tokenization_spaces": false,
374
+ "eoi_token": "<|END_OF_IMG|>",
375
+ "eos_token": "<|END_OF_TURN_TOKEN|>",
376
+ "extra_special_tokens": {
377
+ "boi_token": "<|START_OF_IMG|>",
378
+ "eoi_token": "<|END_OF_IMG|>",
379
+ "image_token": "<|IMG_PATCH|>",
380
+ "img_line_break_token": "<|IMG_LINE_BREAK|>"
381
+ },
382
+ "image_token": "<|IMG_PATCH|>",
383
+ "img_line_break_token": "<|IMG_LINE_BREAK|>",
384
+ "legacy": true,
385
+ "merges_file": null,
386
+ "model_max_length": 1000000000000000019884624838656,
387
+ "pad_token": "<PAD>",
388
+ "processor_class": "Cohere2VisionProcessor",
389
+ "sp_model_kwargs": {},
390
+ "spaces_between_special_tokens": false,
391
+ "tokenizer_class": "CohereTokenizer",
392
+ "unk_token": "<UNK>",
393
+ "use_default_system_prompt": false,
394
+ "vocab_file": null
395
+ }