Hugging Face's logo

starkdmi
/
SmolVLM2-500M-Video-Instruct-mlx-8bit

Safetensors
smolvlm
8-bit precision
Model card Files
xet
 Community
starkdmi commited on
Commit
b416d00
·
verified ·
1 Parent(s): a523c2c

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. added_tokens.json +130 -0
  2. chat_template.jinja +2 -0
  3. chat_template.json +3 -0
  4. config.json +338 -0
  5. model.safetensors +3 -0
  6. model.safetensors.index.json +950 -0
  7. preprocessor_config.json +35 -0
  8. processor_config.json +80 -0
  9. special_tokens_map.json +39 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +31 -0
  12. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 49279,
3
+ "<fake_token_around_image>": 49189,
4
+ "<global-img>": 49152,
5
+ "<image>": 49190,
6
+ "<row_1_col_1>": 49153,
7
+ "<row_1_col_2>": 49154,
8
+ "<row_1_col_3>": 49155,
9
+ "<row_1_col_4>": 49156,
10
+ "<row_1_col_5>": 49157,
11
+ "<row_1_col_6>": 49158,
12
+ "<row_2_col_1>": 49159,
13
+ "<row_2_col_2>": 49160,
14
+ "<row_2_col_3>": 49161,
15
+ "<row_2_col_4>": 49162,
16
+ "<row_2_col_5>": 49163,
17
+ "<row_2_col_6>": 49164,
18
+ "<row_3_col_1>": 49165,
19
+ "<row_3_col_2>": 49166,
20
+ "<row_3_col_3>": 49167,
21
+ "<row_3_col_4>": 49168,
22
+ "<row_3_col_5>": 49169,
23
+ "<row_3_col_6>": 49170,
24
+ "<row_4_col_1>": 49171,
25
+ "<row_4_col_2>": 49172,
26
+ "<row_4_col_3>": 49173,
27
+ "<row_4_col_4>": 49174,
28
+ "<row_4_col_5>": 49175,
29
+ "<row_4_col_6>": 49176,
30
+ "<row_5_col_1>": 49177,
31
+ "<row_5_col_2>": 49178,
32
+ "<row_5_col_3>": 49179,
33
+ "<row_5_col_4>": 49180,
34
+ "<row_5_col_5>": 49181,
35
+ "<row_5_col_6>": 49182,
36
+ "<row_6_col_1>": 49183,
37
+ "<row_6_col_2>": 49184,
38
+ "<row_6_col_3>": 49185,
39
+ "<row_6_col_4>": 49186,
40
+ "<row_6_col_5>": 49187,
41
+ "<row_6_col_6>": 49188,
42
+ "<|reserved_special_token_0|>": 49191,
43
+ "<|reserved_special_token_10|>": 49201,
44
+ "<|reserved_special_token_11|>": 49202,
45
+ "<|reserved_special_token_12|>": 49203,
46
+ "<|reserved_special_token_13|>": 49204,
47
+ "<|reserved_special_token_14|>": 49205,
48
+ "<|reserved_special_token_15|>": 49206,
49
+ "<|reserved_special_token_16|>": 49207,
50
+ "<|reserved_special_token_17|>": 49208,
51
+ "<|reserved_special_token_18|>": 49209,
52
+ "<|reserved_special_token_19|>": 49210,
53
+ "<|reserved_special_token_1|>": 49192,
54
+ "<|reserved_special_token_20|>": 49211,
55
+ "<|reserved_special_token_21|>": 49212,
56
+ "<|reserved_special_token_22|>": 49213,
57
+ "<|reserved_special_token_23|>": 49214,
58
+ "<|reserved_special_token_24|>": 49215,
59
+ "<|reserved_special_token_25|>": 49216,
60
+ "<|reserved_special_token_26|>": 49217,
61
+ "<|reserved_special_token_27|>": 49218,
62
+ "<|reserved_special_token_28|>": 49219,
63
+ "<|reserved_special_token_29|>": 49220,
64
+ "<|reserved_special_token_2|>": 49193,
65
+ "<|reserved_special_token_30|>": 49221,
66
+ "<|reserved_special_token_31|>": 49222,
67
+ "<|reserved_special_token_32|>": 49223,
68
+ "<|reserved_special_token_33|>": 49224,
69
+ "<|reserved_special_token_34|>": 49225,
70
+ "<|reserved_special_token_35|>": 49226,
71
+ "<|reserved_special_token_36|>": 49227,
72
+ "<|reserved_special_token_37|>": 49228,
73
+ "<|reserved_special_token_38|>": 49229,
74
+ "<|reserved_special_token_39|>": 49230,
75
+ "<|reserved_special_token_3|>": 49194,
76
+ "<|reserved_special_token_40|>": 49231,
77
+ "<|reserved_special_token_41|>": 49232,
78
+ "<|reserved_special_token_42|>": 49233,
79
+ "<|reserved_special_token_43|>": 49234,
80
+ "<|reserved_special_token_44|>": 49235,
81
+ "<|reserved_special_token_45|>": 49236,
82
+ "<|reserved_special_token_46|>": 49237,
83
+ "<|reserved_special_token_47|>": 49238,
84
+ "<|reserved_special_token_48|>": 49239,
85
+ "<|reserved_special_token_49|>": 49240,
86
+ "<|reserved_special_token_4|>": 49195,
87
+ "<|reserved_special_token_50|>": 49241,
88
+ "<|reserved_special_token_51|>": 49242,
89
+ "<|reserved_special_token_52|>": 49243,
90
+ "<|reserved_special_token_53|>": 49244,
91
+ "<|reserved_special_token_54|>": 49245,
92
+ "<|reserved_special_token_55|>": 49246,
93
+ "<|reserved_special_token_56|>": 49247,
94
+ "<|reserved_special_token_57|>": 49248,
95
+ "<|reserved_special_token_58|>": 49249,
96
+ "<|reserved_special_token_59|>": 49250,
97
+ "<|reserved_special_token_5|>": 49196,
98
+ "<|reserved_special_token_60|>": 49251,
99
+ "<|reserved_special_token_61|>": 49252,
100
+ "<|reserved_special_token_62|>": 49253,
101
+ "<|reserved_special_token_63|>": 49254,
102
+ "<|reserved_special_token_64|>": 49255,
103
+ "<|reserved_special_token_65|>": 49256,
104
+ "<|reserved_special_token_66|>": 49257,
105
+ "<|reserved_special_token_67|>": 49258,
106
+ "<|reserved_special_token_68|>": 49259,
107
+ "<|reserved_special_token_69|>": 49260,
108
+ "<|reserved_special_token_6|>": 49197,
109
+ "<|reserved_special_token_70|>": 49261,
110
+ "<|reserved_special_token_71|>": 49262,
111
+ "<|reserved_special_token_72|>": 49263,
112
+ "<|reserved_special_token_73|>": 49264,
113
+ "<|reserved_special_token_74|>": 49265,
114
+ "<|reserved_special_token_75|>": 49266,
115
+ "<|reserved_special_token_76|>": 49267,
116
+ "<|reserved_special_token_77|>": 49268,
117
+ "<|reserved_special_token_78|>": 49269,
118
+ "<|reserved_special_token_79|>": 49270,
119
+ "<|reserved_special_token_7|>": 49198,
120
+ "<|reserved_special_token_80|>": 49271,
121
+ "<|reserved_special_token_81|>": 49272,
122
+ "<|reserved_special_token_82|>": 49273,
123
+ "<|reserved_special_token_83|>": 49274,
124
+ "<|reserved_special_token_84|>": 49275,
125
+ "<|reserved_special_token_85|>": 49276,
126
+ "<|reserved_special_token_86|>": 49277,
127
+ "<|reserved_special_token_87|>": 49278,
128
+ "<|reserved_special_token_8|>": 49199,
129
+ "<|reserved_special_token_9|>": 49200
130
+ }
chat_template.jinja ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ <|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2
+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "SmolVLMForConditionalGeneration"
6
+ ],
7
+ "bad_words_ids": null,
8
+ "begin_suppress_tokens": null,
9
+ "bos_token_id": null,
10
+ "chunk_size_feed_forward": 0,
11
+ "cross_attention_hidden_size": null,
12
+ "decoder_start_token_id": null,
13
+ "diversity_penalty": 0.0,
14
+ "do_sample": false,
15
+ "early_stopping": false,
16
+ "encoder_no_repeat_ngram_size": 0,
17
+ "eos_token_id": null,
18
+ "exponential_decay_length_penalty": null,
19
+ "finetuning_task": null,
20
+ "forced_bos_token_id": null,
21
+ "forced_eos_token_id": null,
22
+ "id2label": {
23
+ "0": "LABEL_0",
24
+ "1": "LABEL_1"
25
+ },
26
+ "image_token_id": 49190,
27
+ "is_decoder": false,
28
+ "is_encoder_decoder": false,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1
32
+ },
33
+ "length_penalty": 1.0,
34
+ "max_length": 20,
35
+ "min_length": 0,
36
+ "model_type": "smolvlm",
37
+ "no_repeat_ngram_size": 0,
38
+ "num_beam_groups": 1,
39
+ "num_beams": 1,
40
+ "num_return_sequences": 1,
41
+ "output_attentions": false,
42
+ "output_hidden_states": false,
43
+ "output_scores": false,
44
+ "pad_token_id": 128002,
45
+ "prefix": null,
46
+ "problem_type": null,
47
+ "pruned_heads": {},
48
+ "quantization": {
49
+ "group_size": 64,
50
+ "bits": 8,
51
+ "mode": "affine"
52
+ },
53
+ "quantization_config": {
54
+ "group_size": 64,
55
+ "bits": 8,
56
+ "mode": "affine"
57
+ },
58
+ "remove_invalid_values": false,
59
+ "repetition_penalty": 1.0,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "scale_factor": 4,
63
+ "sep_token_id": null,
64
+ "suppress_tokens": null,
65
+ "task_specific_params": null,
66
+ "temperature": 1.0,
67
+ "text_config": {
68
+ "vocab_size": 49280,
69
+ "max_position_embeddings": 8192,
70
+ "hidden_size": 960,
71
+ "intermediate_size": 2560,
72
+ "num_hidden_layers": 32,
73
+ "num_attention_heads": 15,
74
+ "num_key_value_heads": 5,
75
+ "hidden_act": "silu",
76
+ "initializer_range": 0.02,
77
+ "rms_norm_eps": 1e-05,
78
+ "pretraining_tp": 1,
79
+ "use_cache": true,
80
+ "rope_theta": 100000,
81
+ "rope_scaling": null,
82
+ "attention_bias": false,
83
+ "attention_dropout": 0.0,
84
+ "mlp_bias": false,
85
+ "head_dim": 64,
86
+ "return_dict": true,
87
+ "output_hidden_states": false,
88
+ "output_attentions": false,
89
+ "torchscript": false,
90
+ "torch_dtype": "bfloat16",
91
+ "use_bfloat16": false,
92
+ "tf_legacy_loss": false,
93
+ "pruned_heads": {},
94
+ "tie_word_embeddings": false,
95
+ "chunk_size_feed_forward": 0,
96
+ "is_encoder_decoder": false,
97
+ "is_decoder": false,
98
+ "cross_attention_hidden_size": null,
99
+ "add_cross_attention": false,
100
+ "tie_encoder_decoder": false,
101
+ "max_length": 20,
102
+ "min_length": 0,
103
+ "do_sample": false,
104
+ "early_stopping": false,
105
+ "num_beams": 1,
106
+ "num_beam_groups": 1,
107
+ "diversity_penalty": 0.0,
108
+ "temperature": 1.0,
109
+ "top_k": 50,
110
+ "top_p": 1.0,
111
+ "typical_p": 1.0,
112
+ "repetition_penalty": 1.0,
113
+ "length_penalty": 1.0,
114
+ "no_repeat_ngram_size": 0,
115
+ "encoder_no_repeat_ngram_size": 0,
116
+ "bad_words_ids": null,
117
+ "num_return_sequences": 1,
118
+ "output_scores": false,
119
+ "return_dict_in_generate": false,
120
+ "forced_bos_token_id": null,
121
+ "forced_eos_token_id": null,
122
+ "remove_invalid_values": false,
123
+ "exponential_decay_length_penalty": null,
124
+ "suppress_tokens": null,
125
+ "begin_suppress_tokens": null,
126
+ "architectures": [
127
+ "VLlama3ForCausalLM"
128
+ ],
129
+ "finetuning_task": null,
130
+ "id2label": {
131
+ "0": "LABEL_0",
132
+ "1": "LABEL_1"
133
+ },
134
+ "label2id": {
135
+ "LABEL_0": 0,
136
+ "LABEL_1": 1
137
+ },
138
+ "tokenizer_class": null,
139
+ "prefix": null,
140
+ "bos_token_id": 1,
141
+ "pad_token_id": 2,
142
+ "eos_token_id": 2,
143
+ "sep_token_id": null,
144
+ "decoder_start_token_id": null,
145
+ "task_specific_params": null,
146
+ "problem_type": null,
147
+ "_name_or_path": "None",
148
+ "_attn_implementation_autoset": false,
149
+ "_flash_attn_2_enabled": true,
150
+ "is_llama_config": true,
151
+ "model_type": "llama",
152
+ "neftune_noise_alpha": 0.0,
153
+ "perceiver_config": {
154
+ "_attn_implementation_autoset": false,
155
+ "_name_or_path": "",
156
+ "add_cross_attention": false,
157
+ "architectures": null,
158
+ "attention_dropout": 0.0,
159
+ "bad_words_ids": null,
160
+ "begin_suppress_tokens": null,
161
+ "bos_token_id": null,
162
+ "chunk_size_feed_forward": 0,
163
+ "cross_attention_hidden_size": null,
164
+ "decoder_start_token_id": null,
165
+ "diversity_penalty": 0.0,
166
+ "do_sample": false,
167
+ "early_stopping": false,
168
+ "encoder_no_repeat_ngram_size": 0,
169
+ "eos_token_id": null,
170
+ "exponential_decay_length_penalty": null,
171
+ "finetuning_task": null,
172
+ "forced_bos_token_id": null,
173
+ "forced_eos_token_id": null,
174
+ "hidden_act": "silu",
175
+ "id2label": {
176
+ "0": "LABEL_0",
177
+ "1": "LABEL_1"
178
+ },
179
+ "is_decoder": false,
180
+ "is_encoder_decoder": false,
181
+ "label2id": {
182
+ "LABEL_0": 0,
183
+ "LABEL_1": 1
184
+ },
185
+ "length_penalty": 1.0,
186
+ "max_length": 20,
187
+ "min_length": 0,
188
+ "model_type": "vllama3",
189
+ "no_repeat_ngram_size": 0,
190
+ "num_beam_groups": 1,
191
+ "num_beams": 1,
192
+ "num_key_value_heads": 1,
193
+ "num_return_sequences": 1,
194
+ "output_attentions": false,
195
+ "output_hidden_states": false,
196
+ "output_scores": false,
197
+ "pad_token_id": null,
198
+ "prefix": null,
199
+ "problem_type": null,
200
+ "pruned_heads": {},
201
+ "qk_layer_norms_perceiver": false,
202
+ "remove_invalid_values": false,
203
+ "repetition_penalty": 1.0,
204
+ "resampler_depth": 6,
205
+ "resampler_head_dim": 96,
206
+ "resampler_n_heads": 16,
207
+ "resampler_n_latents": 64,
208
+ "return_dict": true,
209
+ "return_dict_in_generate": false,
210
+ "sep_token_id": null,
211
+ "suppress_tokens": null,
212
+ "task_specific_params": null,
213
+ "temperature": 1.0,
214
+ "tf_legacy_loss": false,
215
+ "tie_encoder_decoder": false,
216
+ "tie_word_embeddings": true,
217
+ "tokenizer_class": null,
218
+ "top_k": 50,
219
+ "top_p": 1.0,
220
+ "torch_dtype": null,
221
+ "torchscript": false,
222
+ "transformers_version": "4.46.0",
223
+ "typical_p": 1.0,
224
+ "use_bfloat16": false
225
+ },
226
+ "pixel_shuffle_factor": 4,
227
+ "qk_layer_norms": false,
228
+ "rope_interleaved": false,
229
+ "transformers.js_config": {
230
+ "kv_cache_dtype": {
231
+ "fp16": "float16",
232
+ "q4f16": "float16"
233
+ }
234
+ },
235
+ "use_resampler": false
236
+ },
237
+ "tf_legacy_loss": false,
238
+ "tie_encoder_decoder": false,
239
+ "tie_word_embeddings": false,
240
+ "tokenizer_class": null,
241
+ "top_k": 50,
242
+ "top_p": 1.0,
243
+ "torchscript": false,
244
+ "transformers.js_config": {
245
+ "kv_cache_dtype": {
246
+ "fp16": "float16",
247
+ "q4f16": "float16"
248
+ }
249
+ },
250
+ "transformers_version": "4.49.0.dev0",
251
+ "typical_p": 1.0,
252
+ "use_bfloat16": false,
253
+ "use_cache": false,
254
+ "use_reentrant_checkpointing": false,
255
+ "vision_config": {
256
+ "return_dict": true,
257
+ "output_hidden_states": false,
258
+ "output_attentions": false,
259
+ "torchscript": false,
260
+ "torch_dtype": null,
261
+ "use_bfloat16": false,
262
+ "tf_legacy_loss": false,
263
+ "pruned_heads": {},
264
+ "tie_word_embeddings": false,
265
+ "chunk_size_feed_forward": 0,
266
+ "is_encoder_decoder": false,
267
+ "is_decoder": false,
268
+ "cross_attention_hidden_size": null,
269
+ "add_cross_attention": false,
270
+ "tie_encoder_decoder": false,
271
+ "max_length": 20,
272
+ "min_length": 0,
273
+ "do_sample": false,
274
+ "early_stopping": false,
275
+ "num_beams": 1,
276
+ "num_beam_groups": 1,
277
+ "diversity_penalty": 0.0,
278
+ "temperature": 1.0,
279
+ "top_k": 50,
280
+ "top_p": 1.0,
281
+ "typical_p": 1.0,
282
+ "repetition_penalty": 1.0,
283
+ "length_penalty": 1.0,
284
+ "no_repeat_ngram_size": 0,
285
+ "encoder_no_repeat_ngram_size": 0,
286
+ "bad_words_ids": null,
287
+ "num_return_sequences": 1,
288
+ "output_scores": false,
289
+ "return_dict_in_generate": false,
290
+ "forced_bos_token_id": null,
291
+ "forced_eos_token_id": null,
292
+ "remove_invalid_values": false,
293
+ "exponential_decay_length_penalty": null,
294
+ "suppress_tokens": null,
295
+ "begin_suppress_tokens": null,
296
+ "architectures": null,
297
+ "finetuning_task": null,
298
+ "id2label": {
299
+ "0": "LABEL_0",
300
+ "1": "LABEL_1"
301
+ },
302
+ "label2id": {
303
+ "LABEL_0": 0,
304
+ "LABEL_1": 1
305
+ },
306
+ "tokenizer_class": null,
307
+ "prefix": null,
308
+ "bos_token_id": null,
309
+ "pad_token_id": null,
310
+ "eos_token_id": null,
311
+ "sep_token_id": null,
312
+ "decoder_start_token_id": null,
313
+ "task_specific_params": null,
314
+ "problem_type": null,
315
+ "_name_or_path": "",
316
+ "_attn_implementation_autoset": false,
317
+ "max_image_size": {
318
+ "longest_edge": 512
319
+ },
320
+ "model_type": "smolvlm_vision",
321
+ "size": {
322
+ "longest_edge": 2048
323
+ },
324
+ "use_base_siglip": false,
325
+ "hidden_size": 768,
326
+ "intermediate_size": 3072,
327
+ "num_hidden_layers": 12,
328
+ "num_attention_heads": 12,
329
+ "num_channels": 3,
330
+ "patch_size": 16,
331
+ "image_size": 512,
332
+ "attention_dropout": 0.0,
333
+ "layer_norm_eps": 1e-06,
334
+ "hidden_act": "gelu_pytorch_tanh",
335
+ "initializer_range": 0.02
336
+ },
337
+ "vocab_size": 49280
338
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461674f917bd9150cd0cebb19668b19270b2d8c306a10e52e13dd53028b094e1
3
+ size 620402844
model.safetensors.index.json ADDED
@@ -0,0 +1,950 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 620289408
4
+ },
5
+ "weight_map": {
6
+ "connector.modality_projection.proj.biases": "model.safetensors",
7
+ "connector.modality_projection.proj.scales": "model.safetensors",
8
+ "connector.modality_projection.proj.weight": "model.safetensors",
9
+ "language_model.embed_tokens.biases": "model.safetensors",
10
+ "language_model.embed_tokens.scales": "model.safetensors",
11
+ "language_model.embed_tokens.weight": "model.safetensors",
12
+ "language_model.layers.0.input_layernorm.weight": "model.safetensors",
13
+ "language_model.layers.0.mlp.down_proj.biases": "model.safetensors",
14
+ "language_model.layers.0.mlp.down_proj.scales": "model.safetensors",
15
+ "language_model.layers.0.mlp.down_proj.weight": "model.safetensors",
16
+ "language_model.layers.0.mlp.gate_proj.biases": "model.safetensors",
17
+ "language_model.layers.0.mlp.gate_proj.scales": "model.safetensors",
18
+ "language_model.layers.0.mlp.gate_proj.weight": "model.safetensors",
19
+ "language_model.layers.0.mlp.up_proj.biases": "model.safetensors",
20
+ "language_model.layers.0.mlp.up_proj.scales": "model.safetensors",
21
+ "language_model.layers.0.mlp.up_proj.weight": "model.safetensors",
22
+ "language_model.layers.0.post_attention_layernorm.weight": "model.safetensors",
23
+ "language_model.layers.0.self_attn.k_proj.biases": "model.safetensors",
24
+ "language_model.layers.0.self_attn.k_proj.scales": "model.safetensors",
25
+ "language_model.layers.0.self_attn.k_proj.weight": "model.safetensors",
26
+ "language_model.layers.0.self_attn.o_proj.biases": "model.safetensors",
27
+ "language_model.layers.0.self_attn.o_proj.scales": "model.safetensors",
28
+ "language_model.layers.0.self_attn.o_proj.weight": "model.safetensors",
29
+ "language_model.layers.0.self_attn.q_proj.biases": "model.safetensors",
30
+ "language_model.layers.0.self_attn.q_proj.scales": "model.safetensors",
31
+ "language_model.layers.0.self_attn.q_proj.weight": "model.safetensors",
32
+ "language_model.layers.0.self_attn.v_proj.biases": "model.safetensors",
33
+ "language_model.layers.0.self_attn.v_proj.scales": "model.safetensors",
34
+ "language_model.layers.0.self_attn.v_proj.weight": "model.safetensors",
35
+ "language_model.layers.1.input_layernorm.weight": "model.safetensors",
36
+ "language_model.layers.1.mlp.down_proj.biases": "model.safetensors",
37
+ "language_model.layers.1.mlp.down_proj.scales": "model.safetensors",
38
+ "language_model.layers.1.mlp.down_proj.weight": "model.safetensors",
39
+ "language_model.layers.1.mlp.gate_proj.biases": "model.safetensors",
40
+ "language_model.layers.1.mlp.gate_proj.scales": "model.safetensors",
41
+ "language_model.layers.1.mlp.gate_proj.weight": "model.safetensors",
42
+ "language_model.layers.1.mlp.up_proj.biases": "model.safetensors",
43
+ "language_model.layers.1.mlp.up_proj.scales": "model.safetensors",
44
+ "language_model.layers.1.mlp.up_proj.weight": "model.safetensors",
45
+ "language_model.layers.1.post_attention_layernorm.weight": "model.safetensors",
46
+ "language_model.layers.1.self_attn.k_proj.biases": "model.safetensors",
47
+ "language_model.layers.1.self_attn.k_proj.scales": "model.safetensors",
48
+ "language_model.layers.1.self_attn.k_proj.weight": "model.safetensors",
49
+ "language_model.layers.1.self_attn.o_proj.biases": "model.safetensors",
50
+ "language_model.layers.1.self_attn.o_proj.scales": "model.safetensors",
51
+ "language_model.layers.1.self_attn.o_proj.weight": "model.safetensors",
52
+ "language_model.layers.1.self_attn.q_proj.biases": "model.safetensors",
53
+ "language_model.layers.1.self_attn.q_proj.scales": "model.safetensors",
54
+ "language_model.layers.1.self_attn.q_proj.weight": "model.safetensors",
55
+ "language_model.layers.1.self_attn.v_proj.biases": "model.safetensors",
56
+ "language_model.layers.1.self_attn.v_proj.scales": "model.safetensors",
57
+ "language_model.layers.1.self_attn.v_proj.weight": "model.safetensors",
58
+ "language_model.layers.10.input_layernorm.weight": "model.safetensors",
59
+ "language_model.layers.10.mlp.down_proj.biases": "model.safetensors",
60
+ "language_model.layers.10.mlp.down_proj.scales": "model.safetensors",
61
+ "language_model.layers.10.mlp.down_proj.weight": "model.safetensors",
62
+ "language_model.layers.10.mlp.gate_proj.biases": "model.safetensors",
63
+ "language_model.layers.10.mlp.gate_proj.scales": "model.safetensors",
64
+ "language_model.layers.10.mlp.gate_proj.weight": "model.safetensors",
65
+ "language_model.layers.10.mlp.up_proj.biases": "model.safetensors",
66
+ "language_model.layers.10.mlp.up_proj.scales": "model.safetensors",
67
+ "language_model.layers.10.mlp.up_proj.weight": "model.safetensors",
68
+ "language_model.layers.10.post_attention_layernorm.weight": "model.safetensors",
69
+ "language_model.layers.10.self_attn.k_proj.biases": "model.safetensors",
70
+ "language_model.layers.10.self_attn.k_proj.scales": "model.safetensors",
71
+ "language_model.layers.10.self_attn.k_proj.weight": "model.safetensors",
72
+ "language_model.layers.10.self_attn.o_proj.biases": "model.safetensors",
73
+ "language_model.layers.10.self_attn.o_proj.scales": "model.safetensors",
74
+ "language_model.layers.10.self_attn.o_proj.weight": "model.safetensors",
75
+ "language_model.layers.10.self_attn.q_proj.biases": "model.safetensors",
76
+ "language_model.layers.10.self_attn.q_proj.scales": "model.safetensors",
77
+ "language_model.layers.10.self_attn.q_proj.weight": "model.safetensors",
78
+ "language_model.layers.10.self_attn.v_proj.biases": "model.safetensors",
79
+ "language_model.layers.10.self_attn.v_proj.scales": "model.safetensors",
80
+ "language_model.layers.10.self_attn.v_proj.weight": "model.safetensors",
81
+ "language_model.layers.11.input_layernorm.weight": "model.safetensors",
82
+ "language_model.layers.11.mlp.down_proj.biases": "model.safetensors",
83
+ "language_model.layers.11.mlp.down_proj.scales": "model.safetensors",
84
+ "language_model.layers.11.mlp.down_proj.weight": "model.safetensors",
85
+ "language_model.layers.11.mlp.gate_proj.biases": "model.safetensors",
86
+ "language_model.layers.11.mlp.gate_proj.scales": "model.safetensors",
87
+ "language_model.layers.11.mlp.gate_proj.weight": "model.safetensors",
88
+ "language_model.layers.11.mlp.up_proj.biases": "model.safetensors",
89
+ "language_model.layers.11.mlp.up_proj.scales": "model.safetensors",
90
+ "language_model.layers.11.mlp.up_proj.weight": "model.safetensors",
91
+ "language_model.layers.11.post_attention_layernorm.weight": "model.safetensors",
92
+ "language_model.layers.11.self_attn.k_proj.biases": "model.safetensors",
93
+ "language_model.layers.11.self_attn.k_proj.scales": "model.safetensors",
94
+ "language_model.layers.11.self_attn.k_proj.weight": "model.safetensors",
95
+ "language_model.layers.11.self_attn.o_proj.biases": "model.safetensors",
96
+ "language_model.layers.11.self_attn.o_proj.scales": "model.safetensors",
97
+ "language_model.layers.11.self_attn.o_proj.weight": "model.safetensors",
98
+ "language_model.layers.11.self_attn.q_proj.biases": "model.safetensors",
99
+ "language_model.layers.11.self_attn.q_proj.scales": "model.safetensors",
100
+ "language_model.layers.11.self_attn.q_proj.weight": "model.safetensors",
101
+ "language_model.layers.11.self_attn.v_proj.biases": "model.safetensors",
102
+ "language_model.layers.11.self_attn.v_proj.scales": "model.safetensors",
103
+ "language_model.layers.11.self_attn.v_proj.weight": "model.safetensors",
104
+ "language_model.layers.12.input_layernorm.weight": "model.safetensors",
105
+ "language_model.layers.12.mlp.down_proj.biases": "model.safetensors",
106
+ "language_model.layers.12.mlp.down_proj.scales": "model.safetensors",
107
+ "language_model.layers.12.mlp.down_proj.weight": "model.safetensors",
108
+ "language_model.layers.12.mlp.gate_proj.biases": "model.safetensors",
109
+ "language_model.layers.12.mlp.gate_proj.scales": "model.safetensors",
110
+ "language_model.layers.12.mlp.gate_proj.weight": "model.safetensors",
111
+ "language_model.layers.12.mlp.up_proj.biases": "model.safetensors",
112
+ "language_model.layers.12.mlp.up_proj.scales": "model.safetensors",
113
+ "language_model.layers.12.mlp.up_proj.weight": "model.safetensors",
114
+ "language_model.layers.12.post_attention_layernorm.weight": "model.safetensors",
115
+ "language_model.layers.12.self_attn.k_proj.biases": "model.safetensors",
116
+ "language_model.layers.12.self_attn.k_proj.scales": "model.safetensors",
117
+ "language_model.layers.12.self_attn.k_proj.weight": "model.safetensors",
118
+ "language_model.layers.12.self_attn.o_proj.biases": "model.safetensors",
119
+ "language_model.layers.12.self_attn.o_proj.scales": "model.safetensors",
120
+ "language_model.layers.12.self_attn.o_proj.weight": "model.safetensors",
121
+ "language_model.layers.12.self_attn.q_proj.biases": "model.safetensors",
122
+ "language_model.layers.12.self_attn.q_proj.scales": "model.safetensors",
123
+ "language_model.layers.12.self_attn.q_proj.weight": "model.safetensors",
124
+ "language_model.layers.12.self_attn.v_proj.biases": "model.safetensors",
125
+ "language_model.layers.12.self_attn.v_proj.scales": "model.safetensors",
126
+ "language_model.layers.12.self_attn.v_proj.weight": "model.safetensors",
127
+ "language_model.layers.13.input_layernorm.weight": "model.safetensors",
128
+ "language_model.layers.13.mlp.down_proj.biases": "model.safetensors",
129
+ "language_model.layers.13.mlp.down_proj.scales": "model.safetensors",
130
+ "language_model.layers.13.mlp.down_proj.weight": "model.safetensors",
131
+ "language_model.layers.13.mlp.gate_proj.biases": "model.safetensors",
132
+ "language_model.layers.13.mlp.gate_proj.scales": "model.safetensors",
133
+ "language_model.layers.13.mlp.gate_proj.weight": "model.safetensors",
134
+ "language_model.layers.13.mlp.up_proj.biases": "model.safetensors",
135
+ "language_model.layers.13.mlp.up_proj.scales": "model.safetensors",
136
+ "language_model.layers.13.mlp.up_proj.weight": "model.safetensors",
137
+ "language_model.layers.13.post_attention_layernorm.weight": "model.safetensors",
138
+ "language_model.layers.13.self_attn.k_proj.biases": "model.safetensors",
139
+ "language_model.layers.13.self_attn.k_proj.scales": "model.safetensors",
140
+ "language_model.layers.13.self_attn.k_proj.weight": "model.safetensors",
141
+ "language_model.layers.13.self_attn.o_proj.biases": "model.safetensors",
142
+ "language_model.layers.13.self_attn.o_proj.scales": "model.safetensors",
143
+ "language_model.layers.13.self_attn.o_proj.weight": "model.safetensors",
144
+ "language_model.layers.13.self_attn.q_proj.biases": "model.safetensors",
145
+ "language_model.layers.13.self_attn.q_proj.scales": "model.safetensors",
146
+ "language_model.layers.13.self_attn.q_proj.weight": "model.safetensors",
147
+ "language_model.layers.13.self_attn.v_proj.biases": "model.safetensors",
148
+ "language_model.layers.13.self_attn.v_proj.scales": "model.safetensors",
149
+ "language_model.layers.13.self_attn.v_proj.weight": "model.safetensors",
150
+ "language_model.layers.14.input_layernorm.weight": "model.safetensors",
151
+ "language_model.layers.14.mlp.down_proj.biases": "model.safetensors",
152
+ "language_model.layers.14.mlp.down_proj.scales": "model.safetensors",
153
+ "language_model.layers.14.mlp.down_proj.weight": "model.safetensors",
154
+ "language_model.layers.14.mlp.gate_proj.biases": "model.safetensors",
155
+ "language_model.layers.14.mlp.gate_proj.scales": "model.safetensors",
156
+ "language_model.layers.14.mlp.gate_proj.weight": "model.safetensors",
157
+ "language_model.layers.14.mlp.up_proj.biases": "model.safetensors",
158
+ "language_model.layers.14.mlp.up_proj.scales": "model.safetensors",
159
+ "language_model.layers.14.mlp.up_proj.weight": "model.safetensors",
160
+ "language_model.layers.14.post_attention_layernorm.weight": "model.safetensors",
161
+ "language_model.layers.14.self_attn.k_proj.biases": "model.safetensors",
162
+ "language_model.layers.14.self_attn.k_proj.scales": "model.safetensors",
163
+ "language_model.layers.14.self_attn.k_proj.weight": "model.safetensors",
164
+ "language_model.layers.14.self_attn.o_proj.biases": "model.safetensors",
165
+ "language_model.layers.14.self_attn.o_proj.scales": "model.safetensors",
166
+ "language_model.layers.14.self_attn.o_proj.weight": "model.safetensors",
167
+ "language_model.layers.14.self_attn.q_proj.biases": "model.safetensors",
168
+ "language_model.layers.14.self_attn.q_proj.scales": "model.safetensors",
169
+ "language_model.layers.14.self_attn.q_proj.weight": "model.safetensors",
170
+ "language_model.layers.14.self_attn.v_proj.biases": "model.safetensors",
171
+ "language_model.layers.14.self_attn.v_proj.scales": "model.safetensors",
172
+ "language_model.layers.14.self_attn.v_proj.weight": "model.safetensors",
173
+ "language_model.layers.15.input_layernorm.weight": "model.safetensors",
174
+ "language_model.layers.15.mlp.down_proj.biases": "model.safetensors",
175
+ "language_model.layers.15.mlp.down_proj.scales": "model.safetensors",
176
+ "language_model.layers.15.mlp.down_proj.weight": "model.safetensors",
177
+ "language_model.layers.15.mlp.gate_proj.biases": "model.safetensors",
178
+ "language_model.layers.15.mlp.gate_proj.scales": "model.safetensors",
179
+ "language_model.layers.15.mlp.gate_proj.weight": "model.safetensors",
180
+ "language_model.layers.15.mlp.up_proj.biases": "model.safetensors",
181
+ "language_model.layers.15.mlp.up_proj.scales": "model.safetensors",
182
+ "language_model.layers.15.mlp.up_proj.weight": "model.safetensors",
183
+ "language_model.layers.15.post_attention_layernorm.weight": "model.safetensors",
184
+ "language_model.layers.15.self_attn.k_proj.biases": "model.safetensors",
185
+ "language_model.layers.15.self_attn.k_proj.scales": "model.safetensors",
186
+ "language_model.layers.15.self_attn.k_proj.weight": "model.safetensors",
187
+ "language_model.layers.15.self_attn.o_proj.biases": "model.safetensors",
188
+ "language_model.layers.15.self_attn.o_proj.scales": "model.safetensors",
189
+ "language_model.layers.15.self_attn.o_proj.weight": "model.safetensors",
190
+ "language_model.layers.15.self_attn.q_proj.biases": "model.safetensors",
191
+ "language_model.layers.15.self_attn.q_proj.scales": "model.safetensors",
192
+ "language_model.layers.15.self_attn.q_proj.weight": "model.safetensors",
193
+ "language_model.layers.15.self_attn.v_proj.biases": "model.safetensors",
194
+ "language_model.layers.15.self_attn.v_proj.scales": "model.safetensors",
195
+ "language_model.layers.15.self_attn.v_proj.weight": "model.safetensors",
196
+ "language_model.layers.16.input_layernorm.weight": "model.safetensors",
197
+ "language_model.layers.16.mlp.down_proj.biases": "model.safetensors",
198
+ "language_model.layers.16.mlp.down_proj.scales": "model.safetensors",
199
+ "language_model.layers.16.mlp.down_proj.weight": "model.safetensors",
200
+ "language_model.layers.16.mlp.gate_proj.biases": "model.safetensors",
201
+ "language_model.layers.16.mlp.gate_proj.scales": "model.safetensors",
202
+ "language_model.layers.16.mlp.gate_proj.weight": "model.safetensors",
203
+ "language_model.layers.16.mlp.up_proj.biases": "model.safetensors",
204
+ "language_model.layers.16.mlp.up_proj.scales": "model.safetensors",
205
+ "language_model.layers.16.mlp.up_proj.weight": "model.safetensors",
206
+ "language_model.layers.16.post_attention_layernorm.weight": "model.safetensors",
207
+ "language_model.layers.16.self_attn.k_proj.biases": "model.safetensors",
208
+ "language_model.layers.16.self_attn.k_proj.scales": "model.safetensors",
209
+ "language_model.layers.16.self_attn.k_proj.weight": "model.safetensors",
210
+ "language_model.layers.16.self_attn.o_proj.biases": "model.safetensors",
211
+ "language_model.layers.16.self_attn.o_proj.scales": "model.safetensors",
212
+ "language_model.layers.16.self_attn.o_proj.weight": "model.safetensors",
213
+ "language_model.layers.16.self_attn.q_proj.biases": "model.safetensors",
214
+ "language_model.layers.16.self_attn.q_proj.scales": "model.safetensors",
215
+ "language_model.layers.16.self_attn.q_proj.weight": "model.safetensors",
216
+ "language_model.layers.16.self_attn.v_proj.biases": "model.safetensors",
217
+ "language_model.layers.16.self_attn.v_proj.scales": "model.safetensors",
218
+ "language_model.layers.16.self_attn.v_proj.weight": "model.safetensors",
219
+ "language_model.layers.17.input_layernorm.weight": "model.safetensors",
220
+ "language_model.layers.17.mlp.down_proj.biases": "model.safetensors",
221
+ "language_model.layers.17.mlp.down_proj.scales": "model.safetensors",
222
+ "language_model.layers.17.mlp.down_proj.weight": "model.safetensors",
223
+ "language_model.layers.17.mlp.gate_proj.biases": "model.safetensors",
224
+ "language_model.layers.17.mlp.gate_proj.scales": "model.safetensors",
225
+ "language_model.layers.17.mlp.gate_proj.weight": "model.safetensors",
226
+ "language_model.layers.17.mlp.up_proj.biases": "model.safetensors",
227
+ "language_model.layers.17.mlp.up_proj.scales": "model.safetensors",
228
+ "language_model.layers.17.mlp.up_proj.weight": "model.safetensors",
229
+ "language_model.layers.17.post_attention_layernorm.weight": "model.safetensors",
230
+ "language_model.layers.17.self_attn.k_proj.biases": "model.safetensors",
231
+ "language_model.layers.17.self_attn.k_proj.scales": "model.safetensors",
232
+ "language_model.layers.17.self_attn.k_proj.weight": "model.safetensors",
233
+ "language_model.layers.17.self_attn.o_proj.biases": "model.safetensors",
234
+ "language_model.layers.17.self_attn.o_proj.scales": "model.safetensors",
235
+ "language_model.layers.17.self_attn.o_proj.weight": "model.safetensors",
236
+ "language_model.layers.17.self_attn.q_proj.biases": "model.safetensors",
237
+ "language_model.layers.17.self_attn.q_proj.scales": "model.safetensors",
238
+ "language_model.layers.17.self_attn.q_proj.weight": "model.safetensors",
239
+ "language_model.layers.17.self_attn.v_proj.biases": "model.safetensors",
240
+ "language_model.layers.17.self_attn.v_proj.scales": "model.safetensors",
241
+ "language_model.layers.17.self_attn.v_proj.weight": "model.safetensors",
242
+ "language_model.layers.18.input_layernorm.weight": "model.safetensors",
243
+ "language_model.layers.18.mlp.down_proj.biases": "model.safetensors",
244
+ "language_model.layers.18.mlp.down_proj.scales": "model.safetensors",
245
+ "language_model.layers.18.mlp.down_proj.weight": "model.safetensors",
246
+ "language_model.layers.18.mlp.gate_proj.biases": "model.safetensors",
247
+ "language_model.layers.18.mlp.gate_proj.scales": "model.safetensors",
248
+ "language_model.layers.18.mlp.gate_proj.weight": "model.safetensors",
249
+ "language_model.layers.18.mlp.up_proj.biases": "model.safetensors",
250
+ "language_model.layers.18.mlp.up_proj.scales": "model.safetensors",
251
+ "language_model.layers.18.mlp.up_proj.weight": "model.safetensors",
252
+ "language_model.layers.18.post_attention_layernorm.weight": "model.safetensors",
253
+ "language_model.layers.18.self_attn.k_proj.biases": "model.safetensors",
254
+ "language_model.layers.18.self_attn.k_proj.scales": "model.safetensors",
255
+ "language_model.layers.18.self_attn.k_proj.weight": "model.safetensors",
256
+ "language_model.layers.18.self_attn.o_proj.biases": "model.safetensors",
257
+ "language_model.layers.18.self_attn.o_proj.scales": "model.safetensors",
258
+ "language_model.layers.18.self_attn.o_proj.weight": "model.safetensors",
259
+ "language_model.layers.18.self_attn.q_proj.biases": "model.safetensors",
260
+ "language_model.layers.18.self_attn.q_proj.scales": "model.safetensors",
261
+ "language_model.layers.18.self_attn.q_proj.weight": "model.safetensors",
262
+ "language_model.layers.18.self_attn.v_proj.biases": "model.safetensors",
263
+ "language_model.layers.18.self_attn.v_proj.scales": "model.safetensors",
264
+ "language_model.layers.18.self_attn.v_proj.weight": "model.safetensors",
265
+ "language_model.layers.19.input_layernorm.weight": "model.safetensors",
266
+ "language_model.layers.19.mlp.down_proj.biases": "model.safetensors",
267
+ "language_model.layers.19.mlp.down_proj.scales": "model.safetensors",
268
+ "language_model.layers.19.mlp.down_proj.weight": "model.safetensors",
269
+ "language_model.layers.19.mlp.gate_proj.biases": "model.safetensors",
270
+ "language_model.layers.19.mlp.gate_proj.scales": "model.safetensors",
271
+ "language_model.layers.19.mlp.gate_proj.weight": "model.safetensors",
272
+ "language_model.layers.19.mlp.up_proj.biases": "model.safetensors",
273
+ "language_model.layers.19.mlp.up_proj.scales": "model.safetensors",
274
+ "language_model.layers.19.mlp.up_proj.weight": "model.safetensors",
275
+ "language_model.layers.19.post_attention_layernorm.weight": "model.safetensors",
276
+ "language_model.layers.19.self_attn.k_proj.biases": "model.safetensors",
277
+ "language_model.layers.19.self_attn.k_proj.scales": "model.safetensors",
278
+ "language_model.layers.19.self_attn.k_proj.weight": "model.safetensors",
279
+ "language_model.layers.19.self_attn.o_proj.biases": "model.safetensors",
280
+ "language_model.layers.19.self_attn.o_proj.scales": "model.safetensors",
281
+ "language_model.layers.19.self_attn.o_proj.weight": "model.safetensors",
282
+ "language_model.layers.19.self_attn.q_proj.biases": "model.safetensors",
283
+ "language_model.layers.19.self_attn.q_proj.scales": "model.safetensors",
284
+ "language_model.layers.19.self_attn.q_proj.weight": "model.safetensors",
285
+ "language_model.layers.19.self_attn.v_proj.biases": "model.safetensors",
286
+ "language_model.layers.19.self_attn.v_proj.scales": "model.safetensors",
287
+ "language_model.layers.19.self_attn.v_proj.weight": "model.safetensors",
288
+ "language_model.layers.2.input_layernorm.weight": "model.safetensors",
289
+ "language_model.layers.2.mlp.down_proj.biases": "model.safetensors",
290
+ "language_model.layers.2.mlp.down_proj.scales": "model.safetensors",
291
+ "language_model.layers.2.mlp.down_proj.weight": "model.safetensors",
292
+ "language_model.layers.2.mlp.gate_proj.biases": "model.safetensors",
293
+ "language_model.layers.2.mlp.gate_proj.scales": "model.safetensors",
294
+ "language_model.layers.2.mlp.gate_proj.weight": "model.safetensors",
295
+ "language_model.layers.2.mlp.up_proj.biases": "model.safetensors",
296
+ "language_model.layers.2.mlp.up_proj.scales": "model.safetensors",
297
+ "language_model.layers.2.mlp.up_proj.weight": "model.safetensors",
298
+ "language_model.layers.2.post_attention_layernorm.weight": "model.safetensors",
299
+ "language_model.layers.2.self_attn.k_proj.biases": "model.safetensors",
300
+ "language_model.layers.2.self_attn.k_proj.scales": "model.safetensors",
301
+ "language_model.layers.2.self_attn.k_proj.weight": "model.safetensors",
302
+ "language_model.layers.2.self_attn.o_proj.biases": "model.safetensors",
303
+ "language_model.layers.2.self_attn.o_proj.scales": "model.safetensors",
304
+ "language_model.layers.2.self_attn.o_proj.weight": "model.safetensors",
305
+ "language_model.layers.2.self_attn.q_proj.biases": "model.safetensors",
306
+ "language_model.layers.2.self_attn.q_proj.scales": "model.safetensors",
307
+ "language_model.layers.2.self_attn.q_proj.weight": "model.safetensors",
308
+ "language_model.layers.2.self_attn.v_proj.biases": "model.safetensors",
309
+ "language_model.layers.2.self_attn.v_proj.scales": "model.safetensors",
310
+ "language_model.layers.2.self_attn.v_proj.weight": "model.safetensors",
311
+ "language_model.layers.20.input_layernorm.weight": "model.safetensors",
312
+ "language_model.layers.20.mlp.down_proj.biases": "model.safetensors",
313
+ "language_model.layers.20.mlp.down_proj.scales": "model.safetensors",
314
+ "language_model.layers.20.mlp.down_proj.weight": "model.safetensors",
315
+ "language_model.layers.20.mlp.gate_proj.biases": "model.safetensors",
316
+ "language_model.layers.20.mlp.gate_proj.scales": "model.safetensors",
317
+ "language_model.layers.20.mlp.gate_proj.weight": "model.safetensors",
318
+ "language_model.layers.20.mlp.up_proj.biases": "model.safetensors",
319
+ "language_model.layers.20.mlp.up_proj.scales": "model.safetensors",
320
+ "language_model.layers.20.mlp.up_proj.weight": "model.safetensors",
321
+ "language_model.layers.20.post_attention_layernorm.weight": "model.safetensors",
322
+ "language_model.layers.20.self_attn.k_proj.biases": "model.safetensors",
323
+ "language_model.layers.20.self_attn.k_proj.scales": "model.safetensors",
324
+ "language_model.layers.20.self_attn.k_proj.weight": "model.safetensors",
325
+ "language_model.layers.20.self_attn.o_proj.biases": "model.safetensors",
326
+ "language_model.layers.20.self_attn.o_proj.scales": "model.safetensors",
327
+ "language_model.layers.20.self_attn.o_proj.weight": "model.safetensors",
328
+ "language_model.layers.20.self_attn.q_proj.biases": "model.safetensors",
329
+ "language_model.layers.20.self_attn.q_proj.scales": "model.safetensors",
330
+ "language_model.layers.20.self_attn.q_proj.weight": "model.safetensors",
331
+ "language_model.layers.20.self_attn.v_proj.biases": "model.safetensors",
332
+ "language_model.layers.20.self_attn.v_proj.scales": "model.safetensors",
333
+ "language_model.layers.20.self_attn.v_proj.weight": "model.safetensors",
334
+ "language_model.layers.21.input_layernorm.weight": "model.safetensors",
335
+ "language_model.layers.21.mlp.down_proj.biases": "model.safetensors",
336
+ "language_model.layers.21.mlp.down_proj.scales": "model.safetensors",
337
+ "language_model.layers.21.mlp.down_proj.weight": "model.safetensors",
338
+ "language_model.layers.21.mlp.gate_proj.biases": "model.safetensors",
339
+ "language_model.layers.21.mlp.gate_proj.scales": "model.safetensors",
340
+ "language_model.layers.21.mlp.gate_proj.weight": "model.safetensors",
341
+ "language_model.layers.21.mlp.up_proj.biases": "model.safetensors",
342
+ "language_model.layers.21.mlp.up_proj.scales": "model.safetensors",
343
+ "language_model.layers.21.mlp.up_proj.weight": "model.safetensors",
344
+ "language_model.layers.21.post_attention_layernorm.weight": "model.safetensors",
345
+ "language_model.layers.21.self_attn.k_proj.biases": "model.safetensors",
346
+ "language_model.layers.21.self_attn.k_proj.scales": "model.safetensors",
347
+ "language_model.layers.21.self_attn.k_proj.weight": "model.safetensors",
348
+ "language_model.layers.21.self_attn.o_proj.biases": "model.safetensors",
349
+ "language_model.layers.21.self_attn.o_proj.scales": "model.safetensors",
350
+ "language_model.layers.21.self_attn.o_proj.weight": "model.safetensors",
351
+ "language_model.layers.21.self_attn.q_proj.biases": "model.safetensors",
352
+ "language_model.layers.21.self_attn.q_proj.scales": "model.safetensors",
353
+ "language_model.layers.21.self_attn.q_proj.weight": "model.safetensors",
354
+ "language_model.layers.21.self_attn.v_proj.biases": "model.safetensors",
355
+ "language_model.layers.21.self_attn.v_proj.scales": "model.safetensors",
356
+ "language_model.layers.21.self_attn.v_proj.weight": "model.safetensors",
357
+ "language_model.layers.22.input_layernorm.weight": "model.safetensors",
358
+ "language_model.layers.22.mlp.down_proj.biases": "model.safetensors",
359
+ "language_model.layers.22.mlp.down_proj.scales": "model.safetensors",
360
+ "language_model.layers.22.mlp.down_proj.weight": "model.safetensors",
361
+ "language_model.layers.22.mlp.gate_proj.biases": "model.safetensors",
362
+ "language_model.layers.22.mlp.gate_proj.scales": "model.safetensors",
363
+ "language_model.layers.22.mlp.gate_proj.weight": "model.safetensors",
364
+ "language_model.layers.22.mlp.up_proj.biases": "model.safetensors",
365
+ "language_model.layers.22.mlp.up_proj.scales": "model.safetensors",
366
+ "language_model.layers.22.mlp.up_proj.weight": "model.safetensors",
367
+ "language_model.layers.22.post_attention_layernorm.weight": "model.safetensors",
368
+ "language_model.layers.22.self_attn.k_proj.biases": "model.safetensors",
369
+ "language_model.layers.22.self_attn.k_proj.scales": "model.safetensors",
370
+ "language_model.layers.22.self_attn.k_proj.weight": "model.safetensors",
371
+ "language_model.layers.22.self_attn.o_proj.biases": "model.safetensors",
372
+ "language_model.layers.22.self_attn.o_proj.scales": "model.safetensors",
373
+ "language_model.layers.22.self_attn.o_proj.weight": "model.safetensors",
374
+ "language_model.layers.22.self_attn.q_proj.biases": "model.safetensors",
375
+ "language_model.layers.22.self_attn.q_proj.scales": "model.safetensors",
376
+ "language_model.layers.22.self_attn.q_proj.weight": "model.safetensors",
377
+ "language_model.layers.22.self_attn.v_proj.biases": "model.safetensors",
378
+ "language_model.layers.22.self_attn.v_proj.scales": "model.safetensors",
379
+ "language_model.layers.22.self_attn.v_proj.weight": "model.safetensors",
380
+ "language_model.layers.23.input_layernorm.weight": "model.safetensors",
381
+ "language_model.layers.23.mlp.down_proj.biases": "model.safetensors",
382
+ "language_model.layers.23.mlp.down_proj.scales": "model.safetensors",
383
+ "language_model.layers.23.mlp.down_proj.weight": "model.safetensors",
384
+ "language_model.layers.23.mlp.gate_proj.biases": "model.safetensors",
385
+ "language_model.layers.23.mlp.gate_proj.scales": "model.safetensors",
386
+ "language_model.layers.23.mlp.gate_proj.weight": "model.safetensors",
387
+ "language_model.layers.23.mlp.up_proj.biases": "model.safetensors",
388
+ "language_model.layers.23.mlp.up_proj.scales": "model.safetensors",
389
+ "language_model.layers.23.mlp.up_proj.weight": "model.safetensors",
390
+ "language_model.layers.23.post_attention_layernorm.weight": "model.safetensors",
391
+ "language_model.layers.23.self_attn.k_proj.biases": "model.safetensors",
392
+ "language_model.layers.23.self_attn.k_proj.scales": "model.safetensors",
393
+ "language_model.layers.23.self_attn.k_proj.weight": "model.safetensors",
394
+ "language_model.layers.23.self_attn.o_proj.biases": "model.safetensors",
395
+ "language_model.layers.23.self_attn.o_proj.scales": "model.safetensors",
396
+ "language_model.layers.23.self_attn.o_proj.weight": "model.safetensors",
397
+ "language_model.layers.23.self_attn.q_proj.biases": "model.safetensors",
398
+ "language_model.layers.23.self_attn.q_proj.scales": "model.safetensors",
399
+ "language_model.layers.23.self_attn.q_proj.weight": "model.safetensors",
400
+ "language_model.layers.23.self_attn.v_proj.biases": "model.safetensors",
401
+ "language_model.layers.23.self_attn.v_proj.scales": "model.safetensors",
402
+ "language_model.layers.23.self_attn.v_proj.weight": "model.safetensors",
403
+ "language_model.layers.24.input_layernorm.weight": "model.safetensors",
404
+ "language_model.layers.24.mlp.down_proj.biases": "model.safetensors",
405
+ "language_model.layers.24.mlp.down_proj.scales": "model.safetensors",
406
+ "language_model.layers.24.mlp.down_proj.weight": "model.safetensors",
407
+ "language_model.layers.24.mlp.gate_proj.biases": "model.safetensors",
408
+ "language_model.layers.24.mlp.gate_proj.scales": "model.safetensors",
409
+ "language_model.layers.24.mlp.gate_proj.weight": "model.safetensors",
410
+ "language_model.layers.24.mlp.up_proj.biases": "model.safetensors",
411
+ "language_model.layers.24.mlp.up_proj.scales": "model.safetensors",
412
+ "language_model.layers.24.mlp.up_proj.weight": "model.safetensors",
413
+ "language_model.layers.24.post_attention_layernorm.weight": "model.safetensors",
414
+ "language_model.layers.24.self_attn.k_proj.biases": "model.safetensors",
415
+ "language_model.layers.24.self_attn.k_proj.scales": "model.safetensors",
416
+ "language_model.layers.24.self_attn.k_proj.weight": "model.safetensors",
417
+ "language_model.layers.24.self_attn.o_proj.biases": "model.safetensors",
418
+ "language_model.layers.24.self_attn.o_proj.scales": "model.safetensors",
419
+ "language_model.layers.24.self_attn.o_proj.weight": "model.safetensors",
420
+ "language_model.layers.24.self_attn.q_proj.biases": "model.safetensors",
421
+ "language_model.layers.24.self_attn.q_proj.scales": "model.safetensors",
422
+ "language_model.layers.24.self_attn.q_proj.weight": "model.safetensors",
423
+ "language_model.layers.24.self_attn.v_proj.biases": "model.safetensors",
424
+ "language_model.layers.24.self_attn.v_proj.scales": "model.safetensors",
425
+ "language_model.layers.24.self_attn.v_proj.weight": "model.safetensors",
426
+ "language_model.layers.25.input_layernorm.weight": "model.safetensors",
427
+ "language_model.layers.25.mlp.down_proj.biases": "model.safetensors",
428
+ "language_model.layers.25.mlp.down_proj.scales": "model.safetensors",
429
+ "language_model.layers.25.mlp.down_proj.weight": "model.safetensors",
430
+ "language_model.layers.25.mlp.gate_proj.biases": "model.safetensors",
431
+ "language_model.layers.25.mlp.gate_proj.scales": "model.safetensors",
432
+ "language_model.layers.25.mlp.gate_proj.weight": "model.safetensors",
433
+ "language_model.layers.25.mlp.up_proj.biases": "model.safetensors",
434
+ "language_model.layers.25.mlp.up_proj.scales": "model.safetensors",
435
+ "language_model.layers.25.mlp.up_proj.weight": "model.safetensors",
436
+ "language_model.layers.25.post_attention_layernorm.weight": "model.safetensors",
437
+ "language_model.layers.25.self_attn.k_proj.biases": "model.safetensors",
438
+ "language_model.layers.25.self_attn.k_proj.scales": "model.safetensors",
439
+ "language_model.layers.25.self_attn.k_proj.weight": "model.safetensors",
440
+ "language_model.layers.25.self_attn.o_proj.biases": "model.safetensors",
441
+ "language_model.layers.25.self_attn.o_proj.scales": "model.safetensors",
442
+ "language_model.layers.25.self_attn.o_proj.weight": "model.safetensors",
443
+ "language_model.layers.25.self_attn.q_proj.biases": "model.safetensors",
444
+ "language_model.layers.25.self_attn.q_proj.scales": "model.safetensors",
445
+ "language_model.layers.25.self_attn.q_proj.weight": "model.safetensors",
446
+ "language_model.layers.25.self_attn.v_proj.biases": "model.safetensors",
447
+ "language_model.layers.25.self_attn.v_proj.scales": "model.safetensors",
448
+ "language_model.layers.25.self_attn.v_proj.weight": "model.safetensors",
449
+ "language_model.layers.26.input_layernorm.weight": "model.safetensors",
450
+ "language_model.layers.26.mlp.down_proj.biases": "model.safetensors",
451
+ "language_model.layers.26.mlp.down_proj.scales": "model.safetensors",
452
+ "language_model.layers.26.mlp.down_proj.weight": "model.safetensors",
453
+ "language_model.layers.26.mlp.gate_proj.biases": "model.safetensors",
454
+ "language_model.layers.26.mlp.gate_proj.scales": "model.safetensors",
455
+ "language_model.layers.26.mlp.gate_proj.weight": "model.safetensors",
456
+ "language_model.layers.26.mlp.up_proj.biases": "model.safetensors",
457
+ "language_model.layers.26.mlp.up_proj.scales": "model.safetensors",
458
+ "language_model.layers.26.mlp.up_proj.weight": "model.safetensors",
459
+ "language_model.layers.26.post_attention_layernorm.weight": "model.safetensors",
460
+ "language_model.layers.26.self_attn.k_proj.biases": "model.safetensors",
461
+ "language_model.layers.26.self_attn.k_proj.scales": "model.safetensors",
462
+ "language_model.layers.26.self_attn.k_proj.weight": "model.safetensors",
463
+ "language_model.layers.26.self_attn.o_proj.biases": "model.safetensors",
464
+ "language_model.layers.26.self_attn.o_proj.scales": "model.safetensors",
465
+ "language_model.layers.26.self_attn.o_proj.weight": "model.safetensors",
466
+ "language_model.layers.26.self_attn.q_proj.biases": "model.safetensors",
467
+ "language_model.layers.26.self_attn.q_proj.scales": "model.safetensors",
468
+ "language_model.layers.26.self_attn.q_proj.weight": "model.safetensors",
469
+ "language_model.layers.26.self_attn.v_proj.biases": "model.safetensors",
470
+ "language_model.layers.26.self_attn.v_proj.scales": "model.safetensors",
471
+ "language_model.layers.26.self_attn.v_proj.weight": "model.safetensors",
472
+ "language_model.layers.27.input_layernorm.weight": "model.safetensors",
473
+ "language_model.layers.27.mlp.down_proj.biases": "model.safetensors",
474
+ "language_model.layers.27.mlp.down_proj.scales": "model.safetensors",
475
+ "language_model.layers.27.mlp.down_proj.weight": "model.safetensors",
476
+ "language_model.layers.27.mlp.gate_proj.biases": "model.safetensors",
477
+ "language_model.layers.27.mlp.gate_proj.scales": "model.safetensors",
478
+ "language_model.layers.27.mlp.gate_proj.weight": "model.safetensors",
479
+ "language_model.layers.27.mlp.up_proj.biases": "model.safetensors",
480
+ "language_model.layers.27.mlp.up_proj.scales": "model.safetensors",
481
+ "language_model.layers.27.mlp.up_proj.weight": "model.safetensors",
482
+ "language_model.layers.27.post_attention_layernorm.weight": "model.safetensors",
483
+ "language_model.layers.27.self_attn.k_proj.biases": "model.safetensors",
484
+ "language_model.layers.27.self_attn.k_proj.scales": "model.safetensors",
485
+ "language_model.layers.27.self_attn.k_proj.weight": "model.safetensors",
486
+ "language_model.layers.27.self_attn.o_proj.biases": "model.safetensors",
487
+ "language_model.layers.27.self_attn.o_proj.scales": "model.safetensors",
488
+ "language_model.layers.27.self_attn.o_proj.weight": "model.safetensors",
489
+ "language_model.layers.27.self_attn.q_proj.biases": "model.safetensors",
490
+ "language_model.layers.27.self_attn.q_proj.scales": "model.safetensors",
491
+ "language_model.layers.27.self_attn.q_proj.weight": "model.safetensors",
492
+ "language_model.layers.27.self_attn.v_proj.biases": "model.safetensors",
493
+ "language_model.layers.27.self_attn.v_proj.scales": "model.safetensors",
494
+ "language_model.layers.27.self_attn.v_proj.weight": "model.safetensors",
495
+ "language_model.layers.28.input_layernorm.weight": "model.safetensors",
496
+ "language_model.layers.28.mlp.down_proj.biases": "model.safetensors",
497
+ "language_model.layers.28.mlp.down_proj.scales": "model.safetensors",
498
+ "language_model.layers.28.mlp.down_proj.weight": "model.safetensors",
499
+ "language_model.layers.28.mlp.gate_proj.biases": "model.safetensors",
500
+ "language_model.layers.28.mlp.gate_proj.scales": "model.safetensors",
501
+ "language_model.layers.28.mlp.gate_proj.weight": "model.safetensors",
502
+ "language_model.layers.28.mlp.up_proj.biases": "model.safetensors",
503
+ "language_model.layers.28.mlp.up_proj.scales": "model.safetensors",
504
+ "language_model.layers.28.mlp.up_proj.weight": "model.safetensors",
505
+ "language_model.layers.28.post_attention_layernorm.weight": "model.safetensors",
506
+ "language_model.layers.28.self_attn.k_proj.biases": "model.safetensors",
507
+ "language_model.layers.28.self_attn.k_proj.scales": "model.safetensors",
508
+ "language_model.layers.28.self_attn.k_proj.weight": "model.safetensors",
509
+ "language_model.layers.28.self_attn.o_proj.biases": "model.safetensors",
510
+ "language_model.layers.28.self_attn.o_proj.scales": "model.safetensors",
511
+ "language_model.layers.28.self_attn.o_proj.weight": "model.safetensors",
512
+ "language_model.layers.28.self_attn.q_proj.biases": "model.safetensors",
513
+ "language_model.layers.28.self_attn.q_proj.scales": "model.safetensors",
514
+ "language_model.layers.28.self_attn.q_proj.weight": "model.safetensors",
515
+ "language_model.layers.28.self_attn.v_proj.biases": "model.safetensors",
516
+ "language_model.layers.28.self_attn.v_proj.scales": "model.safetensors",
517
+ "language_model.layers.28.self_attn.v_proj.weight": "model.safetensors",
518
+ "language_model.layers.29.input_layernorm.weight": "model.safetensors",
519
+ "language_model.layers.29.mlp.down_proj.biases": "model.safetensors",
520
+ "language_model.layers.29.mlp.down_proj.scales": "model.safetensors",
521
+ "language_model.layers.29.mlp.down_proj.weight": "model.safetensors",
522
+ "language_model.layers.29.mlp.gate_proj.biases": "model.safetensors",
523
+ "language_model.layers.29.mlp.gate_proj.scales": "model.safetensors",
524
+ "language_model.layers.29.mlp.gate_proj.weight": "model.safetensors",
525
+ "language_model.layers.29.mlp.up_proj.biases": "model.safetensors",
526
+ "language_model.layers.29.mlp.up_proj.scales": "model.safetensors",
527
+ "language_model.layers.29.mlp.up_proj.weight": "model.safetensors",
528
+ "language_model.layers.29.post_attention_layernorm.weight": "model.safetensors",
529
+ "language_model.layers.29.self_attn.k_proj.biases": "model.safetensors",
530
+ "language_model.layers.29.self_attn.k_proj.scales": "model.safetensors",
531
+ "language_model.layers.29.self_attn.k_proj.weight": "model.safetensors",
532
+ "language_model.layers.29.self_attn.o_proj.biases": "model.safetensors",
533
+ "language_model.layers.29.self_attn.o_proj.scales": "model.safetensors",
534
+ "language_model.layers.29.self_attn.o_proj.weight": "model.safetensors",
535
+ "language_model.layers.29.self_attn.q_proj.biases": "model.safetensors",
536
+ "language_model.layers.29.self_attn.q_proj.scales": "model.safetensors",
537
+ "language_model.layers.29.self_attn.q_proj.weight": "model.safetensors",
538
+ "language_model.layers.29.self_attn.v_proj.biases": "model.safetensors",
539
+ "language_model.layers.29.self_attn.v_proj.scales": "model.safetensors",
540
+ "language_model.layers.29.self_attn.v_proj.weight": "model.safetensors",
541
+ "language_model.layers.3.input_layernorm.weight": "model.safetensors",
542
+ "language_model.layers.3.mlp.down_proj.biases": "model.safetensors",
543
+ "language_model.layers.3.mlp.down_proj.scales": "model.safetensors",
544
+ "language_model.layers.3.mlp.down_proj.weight": "model.safetensors",
545
+ "language_model.layers.3.mlp.gate_proj.biases": "model.safetensors",
546
+ "language_model.layers.3.mlp.gate_proj.scales": "model.safetensors",
547
+ "language_model.layers.3.mlp.gate_proj.weight": "model.safetensors",
548
+ "language_model.layers.3.mlp.up_proj.biases": "model.safetensors",
549
+ "language_model.layers.3.mlp.up_proj.scales": "model.safetensors",
550
+ "language_model.layers.3.mlp.up_proj.weight": "model.safetensors",
551
+ "language_model.layers.3.post_attention_layernorm.weight": "model.safetensors",
552
+ "language_model.layers.3.self_attn.k_proj.biases": "model.safetensors",
553
+ "language_model.layers.3.self_attn.k_proj.scales": "model.safetensors",
554
+ "language_model.layers.3.self_attn.k_proj.weight": "model.safetensors",
555
+ "language_model.layers.3.self_attn.o_proj.biases": "model.safetensors",
556
+ "language_model.layers.3.self_attn.o_proj.scales": "model.safetensors",
557
+ "language_model.layers.3.self_attn.o_proj.weight": "model.safetensors",
558
+ "language_model.layers.3.self_attn.q_proj.biases": "model.safetensors",
559
+ "language_model.layers.3.self_attn.q_proj.scales": "model.safetensors",
560
+ "language_model.layers.3.self_attn.q_proj.weight": "model.safetensors",
561
+ "language_model.layers.3.self_attn.v_proj.biases": "model.safetensors",
562
+ "language_model.layers.3.self_attn.v_proj.scales": "model.safetensors",
563
+ "language_model.layers.3.self_attn.v_proj.weight": "model.safetensors",
564
+ "language_model.layers.30.input_layernorm.weight": "model.safetensors",
565
+ "language_model.layers.30.mlp.down_proj.biases": "model.safetensors",
566
+ "language_model.layers.30.mlp.down_proj.scales": "model.safetensors",
567
+ "language_model.layers.30.mlp.down_proj.weight": "model.safetensors",
568
+ "language_model.layers.30.mlp.gate_proj.biases": "model.safetensors",
569
+ "language_model.layers.30.mlp.gate_proj.scales": "model.safetensors",
570
+ "language_model.layers.30.mlp.gate_proj.weight": "model.safetensors",
571
+ "language_model.layers.30.mlp.up_proj.biases": "model.safetensors",
572
+ "language_model.layers.30.mlp.up_proj.scales": "model.safetensors",
573
+ "language_model.layers.30.mlp.up_proj.weight": "model.safetensors",
574
+ "language_model.layers.30.post_attention_layernorm.weight": "model.safetensors",
575
+ "language_model.layers.30.self_attn.k_proj.biases": "model.safetensors",
576
+ "language_model.layers.30.self_attn.k_proj.scales": "model.safetensors",
577
+ "language_model.layers.30.self_attn.k_proj.weight": "model.safetensors",
578
+ "language_model.layers.30.self_attn.o_proj.biases": "model.safetensors",
579
+ "language_model.layers.30.self_attn.o_proj.scales": "model.safetensors",
580
+ "language_model.layers.30.self_attn.o_proj.weight": "model.safetensors",
581
+ "language_model.layers.30.self_attn.q_proj.biases": "model.safetensors",
582
+ "language_model.layers.30.self_attn.q_proj.scales": "model.safetensors",
583
+ "language_model.layers.30.self_attn.q_proj.weight": "model.safetensors",
584
+ "language_model.layers.30.self_attn.v_proj.biases": "model.safetensors",
585
+ "language_model.layers.30.self_attn.v_proj.scales": "model.safetensors",
586
+ "language_model.layers.30.self_attn.v_proj.weight": "model.safetensors",
587
+ "language_model.layers.31.input_layernorm.weight": "model.safetensors",
588
+ "language_model.layers.31.mlp.down_proj.biases": "model.safetensors",
589
+ "language_model.layers.31.mlp.down_proj.scales": "model.safetensors",
590
+ "language_model.layers.31.mlp.down_proj.weight": "model.safetensors",
591
+ "language_model.layers.31.mlp.gate_proj.biases": "model.safetensors",
592
+ "language_model.layers.31.mlp.gate_proj.scales": "model.safetensors",
593
+ "language_model.layers.31.mlp.gate_proj.weight": "model.safetensors",
594
+ "language_model.layers.31.mlp.up_proj.biases": "model.safetensors",
595
+ "language_model.layers.31.mlp.up_proj.scales": "model.safetensors",
596
+ "language_model.layers.31.mlp.up_proj.weight": "model.safetensors",
597
+ "language_model.layers.31.post_attention_layernorm.weight": "model.safetensors",
598
+ "language_model.layers.31.self_attn.k_proj.biases": "model.safetensors",
599
+ "language_model.layers.31.self_attn.k_proj.scales": "model.safetensors",
600
+ "language_model.layers.31.self_attn.k_proj.weight": "model.safetensors",
601
+ "language_model.layers.31.self_attn.o_proj.biases": "model.safetensors",
602
+ "language_model.layers.31.self_attn.o_proj.scales": "model.safetensors",
603
+ "language_model.layers.31.self_attn.o_proj.weight": "model.safetensors",
604
+ "language_model.layers.31.self_attn.q_proj.biases": "model.safetensors",
605
+ "language_model.layers.31.self_attn.q_proj.scales": "model.safetensors",
606
+ "language_model.layers.31.self_attn.q_proj.weight": "model.safetensors",
607
+ "language_model.layers.31.self_attn.v_proj.biases": "model.safetensors",
608
+ "language_model.layers.31.self_attn.v_proj.scales": "model.safetensors",
609
+ "language_model.layers.31.self_attn.v_proj.weight": "model.safetensors",
610
+ "language_model.layers.4.input_layernorm.weight": "model.safetensors",
611
+ "language_model.layers.4.mlp.down_proj.biases": "model.safetensors",
612
+ "language_model.layers.4.mlp.down_proj.scales": "model.safetensors",
613
+ "language_model.layers.4.mlp.down_proj.weight": "model.safetensors",
614
+ "language_model.layers.4.mlp.gate_proj.biases": "model.safetensors",
615
+ "language_model.layers.4.mlp.gate_proj.scales": "model.safetensors",
616
+ "language_model.layers.4.mlp.gate_proj.weight": "model.safetensors",
617
+ "language_model.layers.4.mlp.up_proj.biases": "model.safetensors",
618
+ "language_model.layers.4.mlp.up_proj.scales": "model.safetensors",
619
+ "language_model.layers.4.mlp.up_proj.weight": "model.safetensors",
620
+ "language_model.layers.4.post_attention_layernorm.weight": "model.safetensors",
621
+ "language_model.layers.4.self_attn.k_proj.biases": "model.safetensors",
622
+ "language_model.layers.4.self_attn.k_proj.scales": "model.safetensors",
623
+ "language_model.layers.4.self_attn.k_proj.weight": "model.safetensors",
624
+ "language_model.layers.4.self_attn.o_proj.biases": "model.safetensors",
625
+ "language_model.layers.4.self_attn.o_proj.scales": "model.safetensors",
626
+ "language_model.layers.4.self_attn.o_proj.weight": "model.safetensors",
627
+ "language_model.layers.4.self_attn.q_proj.biases": "model.safetensors",
628
+ "language_model.layers.4.self_attn.q_proj.scales": "model.safetensors",
629
+ "language_model.layers.4.self_attn.q_proj.weight": "model.safetensors",
630
+ "language_model.layers.4.self_attn.v_proj.biases": "model.safetensors",
631
+ "language_model.layers.4.self_attn.v_proj.scales": "model.safetensors",
632
+ "language_model.layers.4.self_attn.v_proj.weight": "model.safetensors",
633
+ "language_model.layers.5.input_layernorm.weight": "model.safetensors",
634
+ "language_model.layers.5.mlp.down_proj.biases": "model.safetensors",
635
+ "language_model.layers.5.mlp.down_proj.scales": "model.safetensors",
636
+ "language_model.layers.5.mlp.down_proj.weight": "model.safetensors",
637
+ "language_model.layers.5.mlp.gate_proj.biases": "model.safetensors",
638
+ "language_model.layers.5.mlp.gate_proj.scales": "model.safetensors",
639
+ "language_model.layers.5.mlp.gate_proj.weight": "model.safetensors",
640
+ "language_model.layers.5.mlp.up_proj.biases": "model.safetensors",
641
+ "language_model.layers.5.mlp.up_proj.scales": "model.safetensors",
642
+ "language_model.layers.5.mlp.up_proj.weight": "model.safetensors",
643
+ "language_model.layers.5.post_attention_layernorm.weight": "model.safetensors",
644
+ "language_model.layers.5.self_attn.k_proj.biases": "model.safetensors",
645
+ "language_model.layers.5.self_attn.k_proj.scales": "model.safetensors",
646
+ "language_model.layers.5.self_attn.k_proj.weight": "model.safetensors",
647
+ "language_model.layers.5.self_attn.o_proj.biases": "model.safetensors",
648
+ "language_model.layers.5.self_attn.o_proj.scales": "model.safetensors",
649
+ "language_model.layers.5.self_attn.o_proj.weight": "model.safetensors",
650
+ "language_model.layers.5.self_attn.q_proj.biases": "model.safetensors",
651
+ "language_model.layers.5.self_attn.q_proj.scales": "model.safetensors",
652
+ "language_model.layers.5.self_attn.q_proj.weight": "model.safetensors",
653
+ "language_model.layers.5.self_attn.v_proj.biases": "model.safetensors",
654
+ "language_model.layers.5.self_attn.v_proj.scales": "model.safetensors",
655
+ "language_model.layers.5.self_attn.v_proj.weight": "model.safetensors",
656
+ "language_model.layers.6.input_layernorm.weight": "model.safetensors",
657
+ "language_model.layers.6.mlp.down_proj.biases": "model.safetensors",
658
+ "language_model.layers.6.mlp.down_proj.scales": "model.safetensors",
659
+ "language_model.layers.6.mlp.down_proj.weight": "model.safetensors",
660
+ "language_model.layers.6.mlp.gate_proj.biases": "model.safetensors",
661
+ "language_model.layers.6.mlp.gate_proj.scales": "model.safetensors",
662
+ "language_model.layers.6.mlp.gate_proj.weight": "model.safetensors",
663
+ "language_model.layers.6.mlp.up_proj.biases": "model.safetensors",
664
+ "language_model.layers.6.mlp.up_proj.scales": "model.safetensors",
665
+ "language_model.layers.6.mlp.up_proj.weight": "model.safetensors",
666
+ "language_model.layers.6.post_attention_layernorm.weight": "model.safetensors",
667
+ "language_model.layers.6.self_attn.k_proj.biases": "model.safetensors",
668
+ "language_model.layers.6.self_attn.k_proj.scales": "model.safetensors",
669
+ "language_model.layers.6.self_attn.k_proj.weight": "model.safetensors",
670
+ "language_model.layers.6.self_attn.o_proj.biases": "model.safetensors",
671
+ "language_model.layers.6.self_attn.o_proj.scales": "model.safetensors",
672
+ "language_model.layers.6.self_attn.o_proj.weight": "model.safetensors",
673
+ "language_model.layers.6.self_attn.q_proj.biases": "model.safetensors",
674
+ "language_model.layers.6.self_attn.q_proj.scales": "model.safetensors",
675
+ "language_model.layers.6.self_attn.q_proj.weight": "model.safetensors",
676
+ "language_model.layers.6.self_attn.v_proj.biases": "model.safetensors",
677
+ "language_model.layers.6.self_attn.v_proj.scales": "model.safetensors",
678
+ "language_model.layers.6.self_attn.v_proj.weight": "model.safetensors",
679
+ "language_model.layers.7.input_layernorm.weight": "model.safetensors",
680
+ "language_model.layers.7.mlp.down_proj.biases": "model.safetensors",
681
+ "language_model.layers.7.mlp.down_proj.scales": "model.safetensors",
682
+ "language_model.layers.7.mlp.down_proj.weight": "model.safetensors",
683
+ "language_model.layers.7.mlp.gate_proj.biases": "model.safetensors",
684
+ "language_model.layers.7.mlp.gate_proj.scales": "model.safetensors",
685
+ "language_model.layers.7.mlp.gate_proj.weight": "model.safetensors",
686
+ "language_model.layers.7.mlp.up_proj.biases": "model.safetensors",
687
+ "language_model.layers.7.mlp.up_proj.scales": "model.safetensors",
688
+ "language_model.layers.7.mlp.up_proj.weight": "model.safetensors",
689
+ "language_model.layers.7.post_attention_layernorm.weight": "model.safetensors",
690
+ "language_model.layers.7.self_attn.k_proj.biases": "model.safetensors",
691
+ "language_model.layers.7.self_attn.k_proj.scales": "model.safetensors",
692
+ "language_model.layers.7.self_attn.k_proj.weight": "model.safetensors",
693
+ "language_model.layers.7.self_attn.o_proj.biases": "model.safetensors",
694
+ "language_model.layers.7.self_attn.o_proj.scales": "model.safetensors",
695
+ "language_model.layers.7.self_attn.o_proj.weight": "model.safetensors",
696
+ "language_model.layers.7.self_attn.q_proj.biases": "model.safetensors",
697
+ "language_model.layers.7.self_attn.q_proj.scales": "model.safetensors",
698
+ "language_model.layers.7.self_attn.q_proj.weight": "model.safetensors",
699
+ "language_model.layers.7.self_attn.v_proj.biases": "model.safetensors",
700
+ "language_model.layers.7.self_attn.v_proj.scales": "model.safetensors",
701
+ "language_model.layers.7.self_attn.v_proj.weight": "model.safetensors",
702
+ "language_model.layers.8.input_layernorm.weight": "model.safetensors",
703
+ "language_model.layers.8.mlp.down_proj.biases": "model.safetensors",
704
+ "language_model.layers.8.mlp.down_proj.scales": "model.safetensors",
705
+ "language_model.layers.8.mlp.down_proj.weight": "model.safetensors",
706
+ "language_model.layers.8.mlp.gate_proj.biases": "model.safetensors",
707
+ "language_model.layers.8.mlp.gate_proj.scales": "model.safetensors",
708
+ "language_model.layers.8.mlp.gate_proj.weight": "model.safetensors",
709
+ "language_model.layers.8.mlp.up_proj.biases": "model.safetensors",
710
+ "language_model.layers.8.mlp.up_proj.scales": "model.safetensors",
711
+ "language_model.layers.8.mlp.up_proj.weight": "model.safetensors",
712
+ "language_model.layers.8.post_attention_layernorm.weight": "model.safetensors",
713
+ "language_model.layers.8.self_attn.k_proj.biases": "model.safetensors",
714
+ "language_model.layers.8.self_attn.k_proj.scales": "model.safetensors",
715
+ "language_model.layers.8.self_attn.k_proj.weight": "model.safetensors",
716
+ "language_model.layers.8.self_attn.o_proj.biases": "model.safetensors",
717
+ "language_model.layers.8.self_attn.o_proj.scales": "model.safetensors",
718
+ "language_model.layers.8.self_attn.o_proj.weight": "model.safetensors",
719
+ "language_model.layers.8.self_attn.q_proj.biases": "model.safetensors",
720
+ "language_model.layers.8.self_attn.q_proj.scales": "model.safetensors",
721
+ "language_model.layers.8.self_attn.q_proj.weight": "model.safetensors",
722
+ "language_model.layers.8.self_attn.v_proj.biases": "model.safetensors",
723
+ "language_model.layers.8.self_attn.v_proj.scales": "model.safetensors",
724
+ "language_model.layers.8.self_attn.v_proj.weight": "model.safetensors",
725
+ "language_model.layers.9.input_layernorm.weight": "model.safetensors",
726
+ "language_model.layers.9.mlp.down_proj.biases": "model.safetensors",
727
+ "language_model.layers.9.mlp.down_proj.scales": "model.safetensors",
728
+ "language_model.layers.9.mlp.down_proj.weight": "model.safetensors",
729
+ "language_model.layers.9.mlp.gate_proj.biases": "model.safetensors",
730
+ "language_model.layers.9.mlp.gate_proj.scales": "model.safetensors",
731
+ "language_model.layers.9.mlp.gate_proj.weight": "model.safetensors",
732
+ "language_model.layers.9.mlp.up_proj.biases": "model.safetensors",
733
+ "language_model.layers.9.mlp.up_proj.scales": "model.safetensors",
734
+ "language_model.layers.9.mlp.up_proj.weight": "model.safetensors",
735
+ "language_model.layers.9.post_attention_layernorm.weight": "model.safetensors",
736
+ "language_model.layers.9.self_attn.k_proj.biases": "model.safetensors",
737
+ "language_model.layers.9.self_attn.k_proj.scales": "model.safetensors",
738
+ "language_model.layers.9.self_attn.k_proj.weight": "model.safetensors",
739
+ "language_model.layers.9.self_attn.o_proj.biases": "model.safetensors",
740
+ "language_model.layers.9.self_attn.o_proj.scales": "model.safetensors",
741
+ "language_model.layers.9.self_attn.o_proj.weight": "model.safetensors",
742
+ "language_model.layers.9.self_attn.q_proj.biases": "model.safetensors",
743
+ "language_model.layers.9.self_attn.q_proj.scales": "model.safetensors",
744
+ "language_model.layers.9.self_attn.q_proj.weight": "model.safetensors",
745
+ "language_model.layers.9.self_attn.v_proj.biases": "model.safetensors",
746
+ "language_model.layers.9.self_attn.v_proj.scales": "model.safetensors",
747
+ "language_model.layers.9.self_attn.v_proj.weight": "model.safetensors",
748
+ "language_model.lm_head.biases": "model.safetensors",
749
+ "language_model.lm_head.scales": "model.safetensors",
750
+ "language_model.lm_head.weight": "model.safetensors",
751
+ "language_model.norm.weight": "model.safetensors",
752
+ "vision_model.embeddings.patch_embedding.bias": "model.safetensors",
753
+ "vision_model.embeddings.patch_embedding.weight": "model.safetensors",
754
+ "vision_model.embeddings.position_embedding.weight": "model.safetensors",
755
+ "vision_model.encoder.layers.0.layer_norm1.bias": "model.safetensors",
756
+ "vision_model.encoder.layers.0.layer_norm1.weight": "model.safetensors",
757
+ "vision_model.encoder.layers.0.layer_norm2.bias": "model.safetensors",
758
+ "vision_model.encoder.layers.0.layer_norm2.weight": "model.safetensors",
759
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model.safetensors",
760
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model.safetensors",
761
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model.safetensors",
762
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model.safetensors",
763
+ "vision_model.encoder.layers.0.self_attn.k_proj.bias": "model.safetensors",
764
+ "vision_model.encoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
765
+ "vision_model.encoder.layers.0.self_attn.out_proj.bias": "model.safetensors",
766
+ "vision_model.encoder.layers.0.self_attn.out_proj.weight": "model.safetensors",
767
+ "vision_model.encoder.layers.0.self_attn.q_proj.bias": "model.safetensors",
768
+ "vision_model.encoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
769
+ "vision_model.encoder.layers.0.self_attn.v_proj.bias": "model.safetensors",
770
+ "vision_model.encoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
771
+ "vision_model.encoder.layers.1.layer_norm1.bias": "model.safetensors",
772
+ "vision_model.encoder.layers.1.layer_norm1.weight": "model.safetensors",
773
+ "vision_model.encoder.layers.1.layer_norm2.bias": "model.safetensors",
774
+ "vision_model.encoder.layers.1.layer_norm2.weight": "model.safetensors",
775
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model.safetensors",
776
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model.safetensors",
777
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model.safetensors",
778
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model.safetensors",
779
+ "vision_model.encoder.layers.1.self_attn.k_proj.bias": "model.safetensors",
780
+ "vision_model.encoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
781
+ "vision_model.encoder.layers.1.self_attn.out_proj.bias": "model.safetensors",
782
+ "vision_model.encoder.layers.1.self_attn.out_proj.weight": "model.safetensors",
783
+ "vision_model.encoder.layers.1.self_attn.q_proj.bias": "model.safetensors",
784
+ "vision_model.encoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
785
+ "vision_model.encoder.layers.1.self_attn.v_proj.bias": "model.safetensors",
786
+ "vision_model.encoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
787
+ "vision_model.encoder.layers.10.layer_norm1.bias": "model.safetensors",
788
+ "vision_model.encoder.layers.10.layer_norm1.weight": "model.safetensors",
789
+ "vision_model.encoder.layers.10.layer_norm2.bias": "model.safetensors",
790
+ "vision_model.encoder.layers.10.layer_norm2.weight": "model.safetensors",
791
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model.safetensors",
792
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model.safetensors",
793
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model.safetensors",
794
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model.safetensors",
795
+ "vision_model.encoder.layers.10.self_attn.k_proj.bias": "model.safetensors",
796
+ "vision_model.encoder.layers.10.self_attn.k_proj.weight": "model.safetensors",
797
+ "vision_model.encoder.layers.10.self_attn.out_proj.bias": "model.safetensors",
798
+ "vision_model.encoder.layers.10.self_attn.out_proj.weight": "model.safetensors",
799
+ "vision_model.encoder.layers.10.self_attn.q_proj.bias": "model.safetensors",
800
+ "vision_model.encoder.layers.10.self_attn.q_proj.weight": "model.safetensors",
801
+ "vision_model.encoder.layers.10.self_attn.v_proj.bias": "model.safetensors",
802
+ "vision_model.encoder.layers.10.self_attn.v_proj.weight": "model.safetensors",
803
+ "vision_model.encoder.layers.11.layer_norm1.bias": "model.safetensors",
804
+ "vision_model.encoder.layers.11.layer_norm1.weight": "model.safetensors",
805
+ "vision_model.encoder.layers.11.layer_norm2.bias": "model.safetensors",
806
+ "vision_model.encoder.layers.11.layer_norm2.weight": "model.safetensors",
807
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model.safetensors",
808
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model.safetensors",
809
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model.safetensors",
810
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model.safetensors",
811
+ "vision_model.encoder.layers.11.self_attn.k_proj.bias": "model.safetensors",
812
+ "vision_model.encoder.layers.11.self_attn.k_proj.weight": "model.safetensors",
813
+ "vision_model.encoder.layers.11.self_attn.out_proj.bias": "model.safetensors",
814
+ "vision_model.encoder.layers.11.self_attn.out_proj.weight": "model.safetensors",
815
+ "vision_model.encoder.layers.11.self_attn.q_proj.bias": "model.safetensors",
816
+ "vision_model.encoder.layers.11.self_attn.q_proj.weight": "model.safetensors",
817
+ "vision_model.encoder.layers.11.self_attn.v_proj.bias": "model.safetensors",
818
+ "vision_model.encoder.layers.11.self_attn.v_proj.weight": "model.safetensors",
819
+ "vision_model.encoder.layers.2.layer_norm1.bias": "model.safetensors",
820
+ "vision_model.encoder.layers.2.layer_norm1.weight": "model.safetensors",
821
+ "vision_model.encoder.layers.2.layer_norm2.bias": "model.safetensors",
822
+ "vision_model.encoder.layers.2.layer_norm2.weight": "model.safetensors",
823
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model.safetensors",
824
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model.safetensors",
825
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model.safetensors",
826
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model.safetensors",
827
+ "vision_model.encoder.layers.2.self_attn.k_proj.bias": "model.safetensors",
828
+ "vision_model.encoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
829
+ "vision_model.encoder.layers.2.self_attn.out_proj.bias": "model.safetensors",
830
+ "vision_model.encoder.layers.2.self_attn.out_proj.weight": "model.safetensors",
831
+ "vision_model.encoder.layers.2.self_attn.q_proj.bias": "model.safetensors",
832
+ "vision_model.encoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
833
+ "vision_model.encoder.layers.2.self_attn.v_proj.bias": "model.safetensors",
834
+ "vision_model.encoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
835
+ "vision_model.encoder.layers.3.layer_norm1.bias": "model.safetensors",
836
+ "vision_model.encoder.layers.3.layer_norm1.weight": "model.safetensors",
837
+ "vision_model.encoder.layers.3.layer_norm2.bias": "model.safetensors",
838
+ "vision_model.encoder.layers.3.layer_norm2.weight": "model.safetensors",
839
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model.safetensors",
840
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model.safetensors",
841
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model.safetensors",
842
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model.safetensors",
843
+ "vision_model.encoder.layers.3.self_attn.k_proj.bias": "model.safetensors",
844
+ "vision_model.encoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
845
+ "vision_model.encoder.layers.3.self_attn.out_proj.bias": "model.safetensors",
846
+ "vision_model.encoder.layers.3.self_attn.out_proj.weight": "model.safetensors",
847
+ "vision_model.encoder.layers.3.self_attn.q_proj.bias": "model.safetensors",
848
+ "vision_model.encoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
849
+ "vision_model.encoder.layers.3.self_attn.v_proj.bias": "model.safetensors",
850
+ "vision_model.encoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
851
+ "vision_model.encoder.layers.4.layer_norm1.bias": "model.safetensors",
852
+ "vision_model.encoder.layers.4.layer_norm1.weight": "model.safetensors",
853
+ "vision_model.encoder.layers.4.layer_norm2.bias": "model.safetensors",
854
+ "vision_model.encoder.layers.4.layer_norm2.weight": "model.safetensors",
855
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model.safetensors",
856
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model.safetensors",
857
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model.safetensors",
858
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model.safetensors",
859
+ "vision_model.encoder.layers.4.self_attn.k_proj.bias": "model.safetensors",
860
+ "vision_model.encoder.layers.4.self_attn.k_proj.weight": "model.safetensors",
861
+ "vision_model.encoder.layers.4.self_attn.out_proj.bias": "model.safetensors",
862
+ "vision_model.encoder.layers.4.self_attn.out_proj.weight": "model.safetensors",
863
+ "vision_model.encoder.layers.4.self_attn.q_proj.bias": "model.safetensors",
864
+ "vision_model.encoder.layers.4.self_attn.q_proj.weight": "model.safetensors",
865
+ "vision_model.encoder.layers.4.self_attn.v_proj.bias": "model.safetensors",
866
+ "vision_model.encoder.layers.4.self_attn.v_proj.weight": "model.safetensors",
867
+ "vision_model.encoder.layers.5.layer_norm1.bias": "model.safetensors",
868
+ "vision_model.encoder.layers.5.layer_norm1.weight": "model.safetensors",
869
+ "vision_model.encoder.layers.5.layer_norm2.bias": "model.safetensors",
870
+ "vision_model.encoder.layers.5.layer_norm2.weight": "model.safetensors",
871
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model.safetensors",
872
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model.safetensors",
873
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model.safetensors",
874
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model.safetensors",
875
+ "vision_model.encoder.layers.5.self_attn.k_proj.bias": "model.safetensors",
876
+ "vision_model.encoder.layers.5.self_attn.k_proj.weight": "model.safetensors",
877
+ "vision_model.encoder.layers.5.self_attn.out_proj.bias": "model.safetensors",
878
+ "vision_model.encoder.layers.5.self_attn.out_proj.weight": "model.safetensors",
879
+ "vision_model.encoder.layers.5.self_attn.q_proj.bias": "model.safetensors",
880
+ "vision_model.encoder.layers.5.self_attn.q_proj.weight": "model.safetensors",
881
+ "vision_model.encoder.layers.5.self_attn.v_proj.bias": "model.safetensors",
882
+ "vision_model.encoder.layers.5.self_attn.v_proj.weight": "model.safetensors",
883
+ "vision_model.encoder.layers.6.layer_norm1.bias": "model.safetensors",
884
+ "vision_model.encoder.layers.6.layer_norm1.weight": "model.safetensors",
885
+ "vision_model.encoder.layers.6.layer_norm2.bias": "model.safetensors",
886
+ "vision_model.encoder.layers.6.layer_norm2.weight": "model.safetensors",
887
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model.safetensors",
888
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model.safetensors",
889
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model.safetensors",
890
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model.safetensors",
891
+ "vision_model.encoder.layers.6.self_attn.k_proj.bias": "model.safetensors",
892
+ "vision_model.encoder.layers.6.self_attn.k_proj.weight": "model.safetensors",
893
+ "vision_model.encoder.layers.6.self_attn.out_proj.bias": "model.safetensors",
894
+ "vision_model.encoder.layers.6.self_attn.out_proj.weight": "model.safetensors",
895
+ "vision_model.encoder.layers.6.self_attn.q_proj.bias": "model.safetensors",
896
+ "vision_model.encoder.layers.6.self_attn.q_proj.weight": "model.safetensors",
897
+ "vision_model.encoder.layers.6.self_attn.v_proj.bias": "model.safetensors",
898
+ "vision_model.encoder.layers.6.self_attn.v_proj.weight": "model.safetensors",
899
+ "vision_model.encoder.layers.7.layer_norm1.bias": "model.safetensors",
900
+ "vision_model.encoder.layers.7.layer_norm1.weight": "model.safetensors",
901
+ "vision_model.encoder.layers.7.layer_norm2.bias": "model.safetensors",
902
+ "vision_model.encoder.layers.7.layer_norm2.weight": "model.safetensors",
903
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model.safetensors",
904
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model.safetensors",
905
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model.safetensors",
906
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model.safetensors",
907
+ "vision_model.encoder.layers.7.self_attn.k_proj.bias": "model.safetensors",
908
+ "vision_model.encoder.layers.7.self_attn.k_proj.weight": "model.safetensors",
909
+ "vision_model.encoder.layers.7.self_attn.out_proj.bias": "model.safetensors",
910
+ "vision_model.encoder.layers.7.self_attn.out_proj.weight": "model.safetensors",
911
+ "vision_model.encoder.layers.7.self_attn.q_proj.bias": "model.safetensors",
912
+ "vision_model.encoder.layers.7.self_attn.q_proj.weight": "model.safetensors",
913
+ "vision_model.encoder.layers.7.self_attn.v_proj.bias": "model.safetensors",
914
+ "vision_model.encoder.layers.7.self_attn.v_proj.weight": "model.safetensors",
915
+ "vision_model.encoder.layers.8.layer_norm1.bias": "model.safetensors",
916
+ "vision_model.encoder.layers.8.layer_norm1.weight": "model.safetensors",
917
+ "vision_model.encoder.layers.8.layer_norm2.bias": "model.safetensors",
918
+ "vision_model.encoder.layers.8.layer_norm2.weight": "model.safetensors",
919
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model.safetensors",
920
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model.safetensors",
921
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model.safetensors",
922
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model.safetensors",
923
+ "vision_model.encoder.layers.8.self_attn.k_proj.bias": "model.safetensors",
924
+ "vision_model.encoder.layers.8.self_attn.k_proj.weight": "model.safetensors",
925
+ "vision_model.encoder.layers.8.self_attn.out_proj.bias": "model.safetensors",
926
+ "vision_model.encoder.layers.8.self_attn.out_proj.weight": "model.safetensors",
927
+ "vision_model.encoder.layers.8.self_attn.q_proj.bias": "model.safetensors",
928
+ "vision_model.encoder.layers.8.self_attn.q_proj.weight": "model.safetensors",
929
+ "vision_model.encoder.layers.8.self_attn.v_proj.bias": "model.safetensors",
930
+ "vision_model.encoder.layers.8.self_attn.v_proj.weight": "model.safetensors",
931
+ "vision_model.encoder.layers.9.layer_norm1.bias": "model.safetensors",
932
+ "vision_model.encoder.layers.9.layer_norm1.weight": "model.safetensors",
933
+ "vision_model.encoder.layers.9.layer_norm2.bias": "model.safetensors",
934
+ "vision_model.encoder.layers.9.layer_norm2.weight": "model.safetensors",
935
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model.safetensors",
936
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model.safetensors",
937
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model.safetensors",
938
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model.safetensors",
939
+ "vision_model.encoder.layers.9.self_attn.k_proj.bias": "model.safetensors",
940
+ "vision_model.encoder.layers.9.self_attn.k_proj.weight": "model.safetensors",
941
+ "vision_model.encoder.layers.9.self_attn.out_proj.bias": "model.safetensors",
942
+ "vision_model.encoder.layers.9.self_attn.out_proj.weight": "model.safetensors",
943
+ "vision_model.encoder.layers.9.self_attn.q_proj.bias": "model.safetensors",
944
+ "vision_model.encoder.layers.9.self_attn.q_proj.weight": "model.safetensors",
945
+ "vision_model.encoder.layers.9.self_attn.v_proj.bias": "model.safetensors",
946
+ "vision_model.encoder.layers.9.self_attn.v_proj.weight": "model.safetensors",
947
+ "vision_model.post_layernorm.bias": "model.safetensors",
948
+ "vision_model.post_layernorm.weight": "model.safetensors"
949
+ }
950
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": true,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "SmolVLMImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "max_image_size": {
20
+ "longest_edge": 512
21
+ },
22
+ "processor_class": "SmolVLMProcessor",
23
+ "resample": 1,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "longest_edge": 2048
27
+ },
28
+ "video_sampling": {
29
+ "fps": 1,
30
+ "max_frames": 64,
31
+ "video_size": {
32
+ "longest_edge": 512
33
+ }
34
+ }
35
+ }
processor_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_image_splitting": true,
6
+ "do_normalize": true,
7
+ "do_pad": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "SmolVLMImageProcessorFast",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "max_image_size": {
22
+ "longest_edge": 512
23
+ },
24
+ "resample": 1,
25
+ "rescale_factor": 0.00392156862745098,
26
+ "size": {
27
+ "longest_edge": 2048
28
+ },
29
+ "video_sampling": {
30
+ "fps": 1,
31
+ "max_frames": 64,
32
+ "video_size": {
33
+ "longest_edge": 512
34
+ }
35
+ }
36
+ },
37
+ "image_seq_len": 64,
38
+ "processor_class": "SmolVLMProcessor",
39
+ "video_processor": {
40
+ "data_format": "channels_first",
41
+ "default_to_square": true,
42
+ "do_convert_rgb": true,
43
+ "do_image_splitting": true,
44
+ "do_normalize": true,
45
+ "do_pad": true,
46
+ "do_rescale": true,
47
+ "do_resize": true,
48
+ "do_sample_frames": false,
49
+ "fps": 1,
50
+ "image_mean": [
51
+ 0.5,
52
+ 0.5,
53
+ 0.5
54
+ ],
55
+ "image_processor_type": "SmolVLMImageProcessor",
56
+ "image_std": [
57
+ 0.5,
58
+ 0.5,
59
+ 0.5
60
+ ],
61
+ "max_image_size": {
62
+ "longest_edge": 512
63
+ },
64
+ "num_frames": 64,
65
+ "resample": 1,
66
+ "rescale_factor": 0.00392156862745098,
67
+ "return_metadata": false,
68
+ "size": {
69
+ "longest_edge": 2048
70
+ },
71
+ "video_processor_type": "SmolVLMVideoProcessor",
72
+ "video_sampling": {
73
+ "fps": 1,
74
+ "max_frames": 64,
75
+ "video_size": {
76
+ "longest_edge": 2048
77
+ }
78
+ }
79
+ }
80
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<|im_start|>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "end_of_utterance_token": "<end_of_utterance>",
15
+ "eos_token": {
16
+ "content": "<end_of_utterance>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "fake_image_token": "<fake_token_around_image>",
23
+ "global_image_token": "<global-img>",
24
+ "image_token": "<image>",
25
+ "pad_token": {
26
+ "content": "<|im_end|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "unk_token": {
33
+ "content": "<|endoftext|>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|im_start|>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "end_of_utterance_token": "<end_of_utterance>",
7
+ "eos_token": "<end_of_utterance>",
8
+ "extra_special_tokens": [
9
+ "<fake_token_around_image>",
10
+ "<image>",
11
+ "<end_of_utterance>"
12
+ ],
13
+ "fake_image_token": "<fake_token_around_image>",
14
+ "global_image_token": "<global-img>",
15
+ "image_token": "<image>",
16
+ "is_local": true,
17
+ "legacy": false,
18
+ "model_max_length": 8192,
19
+ "model_specific_special_tokens": {
20
+ "end_of_utterance_token": "<end_of_utterance>",
21
+ "fake_image_token": "<fake_token_around_image>",
22
+ "global_image_token": "<global-img>",
23
+ "image_token": "<image>"
24
+ },
25
+ "pad_token": "<|im_end|>",
26
+ "processor_class": "SmolVLMProcessor",
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "truncation_side": "left",
29
+ "unk_token": "<|endoftext|>",
30
+ "vocab_size": 49152
31
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff