Hugging Face's logo

neuralmagic
/
pixtral-12b-FP8-dynamic

Text Generation
Safetensors
vllm
llava
fp8
conversational
compressed-tensors
Model card Files Community
1
mgoin commited on
Commit
2388fe8
•
1 Parent(s): 127ed48

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. chat_template.json +3 -0
  3. config.json +381 -0
  4. generation_config.json +6 -0
  5. model-00001-of-00003.safetensors +3 -0
  6. model-00002-of-00003.safetensors +3 -0
  7. model-00003-of-00003.safetensors +3 -0
  8. model.safetensors.index.json +872 -0
  9. preprocessor_config.json +27 -0
  10. processor_config.json +7 -0
  11. recipe.yaml +6 -0
  12. special_tokens_map.json +23 -0
  13. tokenizer.json +3 -0
  14. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message[\"role\"] == \"user\" %}\n {%- if loop.last and system_message is defined %}\n {{- \"[INST]\" + system_message + \"\n\n\" }}\n {%- else %}\n {{- \"[INST]\" }}\n {%- endif %}\n {%- if message[\"content\"] is not string %}\n {%- for chunk in message[\"content\"] %}\n {%- if chunk[\"type\"] == \"text\" %}\n {{- chunk[\"content\"] }}\n {%- elif chunk[\"type\"] == \"image\" %}\n {{- \"[IMG]\" }}\n {%- else %}\n {{- raise_exception(\"Unrecognized content type!\") }}\n {%- endif %}\n {%- endfor %}\n {%- else %}\n {{- message[\"content\"] }}\n {%- endif %}\n {{- \"[/INST]\" }}\n {%- elif message[\"role\"] == \"assistant\" %}\n {{- message[\"content\"] + eos_token}}\n {%- else %}\n {{- raise_exception(\"Only user and assistant roles are supported, with the exception of an initial optional system message!\") }}\n {%- endif %}\n{%- endfor %}"
3
+ }
config.json ADDED
@@ -0,0 +1,381 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/mgoin/.cache/huggingface/hub/models--mistral-community--pixtral-12b/snapshots/54521e820bfe9c740aea0c91e1ee52cf55420ba2",
3
+ "architectures": [
4
+ "LlavaForConditionalGeneration"
5
+ ],
6
+ "compression_config": {
7
+ "config_groups": {
8
+ "group_0": {
9
+ "input_activations": {
10
+ "actorder": null,
11
+ "block_structure": null,
12
+ "dynamic": true,
13
+ "group_size": null,
14
+ "num_bits": 8,
15
+ "observer": "memoryless",
16
+ "observer_kwargs": {},
17
+ "strategy": "token",
18
+ "symmetric": true,
19
+ "type": "float"
20
+ },
21
+ "output_activations": null,
22
+ "targets": [
23
+ "Linear"
24
+ ],
25
+ "weights": {
26
+ "actorder": null,
27
+ "block_structure": null,
28
+ "dynamic": false,
29
+ "group_size": null,
30
+ "num_bits": 8,
31
+ "observer": "minmax",
32
+ "observer_kwargs": {},
33
+ "strategy": "channel",
34
+ "symmetric": true,
35
+ "type": "float"
36
+ }
37
+ }
38
+ },
39
+ "format": "float-quantized",
40
+ "global_compression_ratio": 1.1688641443181655,
41
+ "ignore": [
42
+ "vision_tower.transformer.layers.0.feed_forward.gate_proj",
43
+ "vision_tower.transformer.layers.0.feed_forward.up_proj",
44
+ "vision_tower.transformer.layers.0.feed_forward.down_proj",
45
+ "vision_tower.transformer.layers.0.attention.k_proj",
46
+ "vision_tower.transformer.layers.0.attention.v_proj",
47
+ "vision_tower.transformer.layers.0.attention.q_proj",
48
+ "vision_tower.transformer.layers.0.attention.o_proj",
49
+ "vision_tower.transformer.layers.1.feed_forward.gate_proj",
50
+ "vision_tower.transformer.layers.1.feed_forward.up_proj",
51
+ "vision_tower.transformer.layers.1.feed_forward.down_proj",
52
+ "vision_tower.transformer.layers.1.attention.k_proj",
53
+ "vision_tower.transformer.layers.1.attention.v_proj",
54
+ "vision_tower.transformer.layers.1.attention.q_proj",
55
+ "vision_tower.transformer.layers.1.attention.o_proj",
56
+ "vision_tower.transformer.layers.2.feed_forward.gate_proj",
57
+ "vision_tower.transformer.layers.2.feed_forward.up_proj",
58
+ "vision_tower.transformer.layers.2.feed_forward.down_proj",
59
+ "vision_tower.transformer.layers.2.attention.k_proj",
60
+ "vision_tower.transformer.layers.2.attention.v_proj",
61
+ "vision_tower.transformer.layers.2.attention.q_proj",
62
+ "vision_tower.transformer.layers.2.attention.o_proj",
63
+ "vision_tower.transformer.layers.3.feed_forward.gate_proj",
64
+ "vision_tower.transformer.layers.3.feed_forward.up_proj",
65
+ "vision_tower.transformer.layers.3.feed_forward.down_proj",
66
+ "vision_tower.transformer.layers.3.attention.k_proj",
67
+ "vision_tower.transformer.layers.3.attention.v_proj",
68
+ "vision_tower.transformer.layers.3.attention.q_proj",
69
+ "vision_tower.transformer.layers.3.attention.o_proj",
70
+ "vision_tower.transformer.layers.4.feed_forward.gate_proj",
71
+ "vision_tower.transformer.layers.4.feed_forward.up_proj",
72
+ "vision_tower.transformer.layers.4.feed_forward.down_proj",
73
+ "vision_tower.transformer.layers.4.attention.k_proj",
74
+ "vision_tower.transformer.layers.4.attention.v_proj",
75
+ "vision_tower.transformer.layers.4.attention.q_proj",
76
+ "vision_tower.transformer.layers.4.attention.o_proj",
77
+ "vision_tower.transformer.layers.5.feed_forward.gate_proj",
78
+ "vision_tower.transformer.layers.5.feed_forward.up_proj",
79
+ "vision_tower.transformer.layers.5.feed_forward.down_proj",
80
+ "vision_tower.transformer.layers.5.attention.k_proj",
81
+ "vision_tower.transformer.layers.5.attention.v_proj",
82
+ "vision_tower.transformer.layers.5.attention.q_proj",
83
+ "vision_tower.transformer.layers.5.attention.o_proj",
84
+ "vision_tower.transformer.layers.6.feed_forward.gate_proj",
85
+ "vision_tower.transformer.layers.6.feed_forward.up_proj",
86
+ "vision_tower.transformer.layers.6.feed_forward.down_proj",
87
+ "vision_tower.transformer.layers.6.attention.k_proj",
88
+ "vision_tower.transformer.layers.6.attention.v_proj",
89
+ "vision_tower.transformer.layers.6.attention.q_proj",
90
+ "vision_tower.transformer.layers.6.attention.o_proj",
91
+ "vision_tower.transformer.layers.7.feed_forward.gate_proj",
92
+ "vision_tower.transformer.layers.7.feed_forward.up_proj",
93
+ "vision_tower.transformer.layers.7.feed_forward.down_proj",
94
+ "vision_tower.transformer.layers.7.attention.k_proj",
95
+ "vision_tower.transformer.layers.7.attention.v_proj",
96
+ "vision_tower.transformer.layers.7.attention.q_proj",
97
+ "vision_tower.transformer.layers.7.attention.o_proj",
98
+ "vision_tower.transformer.layers.8.feed_forward.gate_proj",
99
+ "vision_tower.transformer.layers.8.feed_forward.up_proj",
100
+ "vision_tower.transformer.layers.8.feed_forward.down_proj",
101
+ "vision_tower.transformer.layers.8.attention.k_proj",
102
+ "vision_tower.transformer.layers.8.attention.v_proj",
103
+ "vision_tower.transformer.layers.8.attention.q_proj",
104
+ "vision_tower.transformer.layers.8.attention.o_proj",
105
+ "vision_tower.transformer.layers.9.feed_forward.gate_proj",
106
+ "vision_tower.transformer.layers.9.feed_forward.up_proj",
107
+ "vision_tower.transformer.layers.9.feed_forward.down_proj",
108
+ "vision_tower.transformer.layers.9.attention.k_proj",
109
+ "vision_tower.transformer.layers.9.attention.v_proj",
110
+ "vision_tower.transformer.layers.9.attention.q_proj",
111
+ "vision_tower.transformer.layers.9.attention.o_proj",
112
+ "vision_tower.transformer.layers.10.feed_forward.gate_proj",
113
+ "vision_tower.transformer.layers.10.feed_forward.up_proj",
114
+ "vision_tower.transformer.layers.10.feed_forward.down_proj",
115
+ "vision_tower.transformer.layers.10.attention.k_proj",
116
+ "vision_tower.transformer.layers.10.attention.v_proj",
117
+ "vision_tower.transformer.layers.10.attention.q_proj",
118
+ "vision_tower.transformer.layers.10.attention.o_proj",
119
+ "vision_tower.transformer.layers.11.feed_forward.gate_proj",
120
+ "vision_tower.transformer.layers.11.feed_forward.up_proj",
121
+ "vision_tower.transformer.layers.11.feed_forward.down_proj",
122
+ "vision_tower.transformer.layers.11.attention.k_proj",
123
+ "vision_tower.transformer.layers.11.attention.v_proj",
124
+ "vision_tower.transformer.layers.11.attention.q_proj",
125
+ "vision_tower.transformer.layers.11.attention.o_proj",
126
+ "vision_tower.transformer.layers.12.feed_forward.gate_proj",
127
+ "vision_tower.transformer.layers.12.feed_forward.up_proj",
128
+ "vision_tower.transformer.layers.12.feed_forward.down_proj",
129
+ "vision_tower.transformer.layers.12.attention.k_proj",
130
+ "vision_tower.transformer.layers.12.attention.v_proj",
131
+ "vision_tower.transformer.layers.12.attention.q_proj",
132
+ "vision_tower.transformer.layers.12.attention.o_proj",
133
+ "vision_tower.transformer.layers.13.feed_forward.gate_proj",
134
+ "vision_tower.transformer.layers.13.feed_forward.up_proj",
135
+ "vision_tower.transformer.layers.13.feed_forward.down_proj",
136
+ "vision_tower.transformer.layers.13.attention.k_proj",
137
+ "vision_tower.transformer.layers.13.attention.v_proj",
138
+ "vision_tower.transformer.layers.13.attention.q_proj",
139
+ "vision_tower.transformer.layers.13.attention.o_proj",
140
+ "vision_tower.transformer.layers.14.feed_forward.gate_proj",
141
+ "vision_tower.transformer.layers.14.feed_forward.up_proj",
142
+ "vision_tower.transformer.layers.14.feed_forward.down_proj",
143
+ "vision_tower.transformer.layers.14.attention.k_proj",
144
+ "vision_tower.transformer.layers.14.attention.v_proj",
145
+ "vision_tower.transformer.layers.14.attention.q_proj",
146
+ "vision_tower.transformer.layers.14.attention.o_proj",
147
+ "vision_tower.transformer.layers.15.feed_forward.gate_proj",
148
+ "vision_tower.transformer.layers.15.feed_forward.up_proj",
149
+ "vision_tower.transformer.layers.15.feed_forward.down_proj",
150
+ "vision_tower.transformer.layers.15.attention.k_proj",
151
+ "vision_tower.transformer.layers.15.attention.v_proj",
152
+ "vision_tower.transformer.layers.15.attention.q_proj",
153
+ "vision_tower.transformer.layers.15.attention.o_proj",
154
+ "vision_tower.transformer.layers.16.feed_forward.gate_proj",
155
+ "vision_tower.transformer.layers.16.feed_forward.up_proj",
156
+ "vision_tower.transformer.layers.16.feed_forward.down_proj",
157
+ "vision_tower.transformer.layers.16.attention.k_proj",
158
+ "vision_tower.transformer.layers.16.attention.v_proj",
159
+ "vision_tower.transformer.layers.16.attention.q_proj",
160
+ "vision_tower.transformer.layers.16.attention.o_proj",
161
+ "vision_tower.transformer.layers.17.feed_forward.gate_proj",
162
+ "vision_tower.transformer.layers.17.feed_forward.up_proj",
163
+ "vision_tower.transformer.layers.17.feed_forward.down_proj",
164
+ "vision_tower.transformer.layers.17.attention.k_proj",
165
+ "vision_tower.transformer.layers.17.attention.v_proj",
166
+ "vision_tower.transformer.layers.17.attention.q_proj",
167
+ "vision_tower.transformer.layers.17.attention.o_proj",
168
+ "vision_tower.transformer.layers.18.feed_forward.gate_proj",
169
+ "vision_tower.transformer.layers.18.feed_forward.up_proj",
170
+ "vision_tower.transformer.layers.18.feed_forward.down_proj",
171
+ "vision_tower.transformer.layers.18.attention.k_proj",
172
+ "vision_tower.transformer.layers.18.attention.v_proj",
173
+ "vision_tower.transformer.layers.18.attention.q_proj",
174
+ "vision_tower.transformer.layers.18.attention.o_proj",
175
+ "vision_tower.transformer.layers.19.feed_forward.gate_proj",
176
+ "vision_tower.transformer.layers.19.feed_forward.up_proj",
177
+ "vision_tower.transformer.layers.19.feed_forward.down_proj",
178
+ "vision_tower.transformer.layers.19.attention.k_proj",
179
+ "vision_tower.transformer.layers.19.attention.v_proj",
180
+ "vision_tower.transformer.layers.19.attention.q_proj",
181
+ "vision_tower.transformer.layers.19.attention.o_proj",
182
+ "vision_tower.transformer.layers.20.feed_forward.gate_proj",
183
+ "vision_tower.transformer.layers.20.feed_forward.up_proj",
184
+ "vision_tower.transformer.layers.20.feed_forward.down_proj",
185
+ "vision_tower.transformer.layers.20.attention.k_proj",
186
+ "vision_tower.transformer.layers.20.attention.v_proj",
187
+ "vision_tower.transformer.layers.20.attention.q_proj",
188
+ "vision_tower.transformer.layers.20.attention.o_proj",
189
+ "vision_tower.transformer.layers.21.feed_forward.gate_proj",
190
+ "vision_tower.transformer.layers.21.feed_forward.up_proj",
191
+ "vision_tower.transformer.layers.21.feed_forward.down_proj",
192
+ "vision_tower.transformer.layers.21.attention.k_proj",
193
+ "vision_tower.transformer.layers.21.attention.v_proj",
194
+ "vision_tower.transformer.layers.21.attention.q_proj",
195
+ "vision_tower.transformer.layers.21.attention.o_proj",
196
+ "vision_tower.transformer.layers.22.feed_forward.gate_proj",
197
+ "vision_tower.transformer.layers.22.feed_forward.up_proj",
198
+ "vision_tower.transformer.layers.22.feed_forward.down_proj",
199
+ "vision_tower.transformer.layers.22.attention.k_proj",
200
+ "vision_tower.transformer.layers.22.attention.v_proj",
201
+ "vision_tower.transformer.layers.22.attention.q_proj",
202
+ "vision_tower.transformer.layers.22.attention.o_proj",
203
+ "vision_tower.transformer.layers.23.feed_forward.gate_proj",
204
+ "vision_tower.transformer.layers.23.feed_forward.up_proj",
205
+ "vision_tower.transformer.layers.23.feed_forward.down_proj",
206
+ "vision_tower.transformer.layers.23.attention.k_proj",
207
+ "vision_tower.transformer.layers.23.attention.v_proj",
208
+ "vision_tower.transformer.layers.23.attention.q_proj",
209
+ "vision_tower.transformer.layers.23.attention.o_proj",
210
+ "multi_modal_projector.linear_1",
211
+ "multi_modal_projector.linear_2",
212
+ "language_model.lm_head"
213
+ ],
214
+ "kv_cache_scheme": null,
215
+ "quant_method": "compressed-tensors",
216
+ "quantization_status": "compressed"
217
+ },
218
+ "ignore_index": -100,
219
+ "image_seq_length": 1,
220
+ "image_token_index": 10,
221
+ "model_type": "llava",
222
+ "projector_hidden_act": "gelu",
223
+ "text_config": {
224
+ "_name_or_path": "",
225
+ "add_cross_attention": false,
226
+ "architectures": null,
227
+ "attention_dropout": 0.0,
228
+ "bad_words_ids": null,
229
+ "begin_suppress_tokens": null,
230
+ "bos_token_id": 1,
231
+ "chunk_size_feed_forward": 0,
232
+ "cross_attention_hidden_size": null,
233
+ "decoder_start_token_id": null,
234
+ "diversity_penalty": 0.0,
235
+ "do_sample": false,
236
+ "early_stopping": false,
237
+ "encoder_no_repeat_ngram_size": 0,
238
+ "eos_token_id": 2,
239
+ "exponential_decay_length_penalty": null,
240
+ "finetuning_task": null,
241
+ "forced_bos_token_id": null,
242
+ "forced_eos_token_id": null,
243
+ "head_dim": 128,
244
+ "hidden_act": "silu",
245
+ "hidden_size": 5120,
246
+ "id2label": {
247
+ "0": "LABEL_0",
248
+ "1": "LABEL_1"
249
+ },
250
+ "initializer_range": 0.02,
251
+ "intermediate_size": 14336,
252
+ "is_composition": true,
253
+ "is_decoder": false,
254
+ "is_encoder_decoder": false,
255
+ "label2id": {
256
+ "LABEL_0": 0,
257
+ "LABEL_1": 1
258
+ },
259
+ "length_penalty": 1.0,
260
+ "max_length": 20,
261
+ "max_position_embeddings": 1024000,
262
+ "min_length": 0,
263
+ "model_type": "mistral",
264
+ "no_repeat_ngram_size": 0,
265
+ "num_attention_heads": 32,
266
+ "num_beam_groups": 1,
267
+ "num_beams": 1,
268
+ "num_hidden_layers": 40,
269
+ "num_key_value_heads": 8,
270
+ "num_return_sequences": 1,
271
+ "output_attentions": false,
272
+ "output_hidden_states": false,
273
+ "output_scores": false,
274
+ "pad_token_id": null,
275
+ "prefix": null,
276
+ "problem_type": null,
277
+ "pruned_heads": {},
278
+ "remove_invalid_values": false,
279
+ "repetition_penalty": 1.0,
280
+ "return_dict": true,
281
+ "return_dict_in_generate": false,
282
+ "rms_norm_eps": 1e-05,
283
+ "rope_theta": 1000000000.0,
284
+ "sep_token_id": null,
285
+ "sliding_window": null,
286
+ "suppress_tokens": null,
287
+ "task_specific_params": null,
288
+ "temperature": 1.0,
289
+ "tf_legacy_loss": false,
290
+ "tie_encoder_decoder": false,
291
+ "tie_word_embeddings": false,
292
+ "tokenizer_class": null,
293
+ "top_k": 50,
294
+ "top_p": 1.0,
295
+ "torch_dtype": null,
296
+ "torchscript": false,
297
+ "typical_p": 1.0,
298
+ "use_bfloat16": false,
299
+ "use_cache": true,
300
+ "vocab_size": 131072
301
+ },
302
+ "torch_dtype": "bfloat16",
303
+ "transformers_version": "4.45.1",
304
+ "vision_config": {
305
+ "_name_or_path": "",
306
+ "add_cross_attention": false,
307
+ "architectures": null,
308
+ "attention_dropout": 0.0,
309
+ "bad_words_ids": null,
310
+ "begin_suppress_tokens": null,
311
+ "bos_token_id": null,
312
+ "chunk_size_feed_forward": 0,
313
+ "cross_attention_hidden_size": null,
314
+ "decoder_start_token_id": null,
315
+ "diversity_penalty": 0.0,
316
+ "do_sample": false,
317
+ "early_stopping": false,
318
+ "encoder_no_repeat_ngram_size": 0,
319
+ "eos_token_id": null,
320
+ "exponential_decay_length_penalty": null,
321
+ "finetuning_task": null,
322
+ "forced_bos_token_id": null,
323
+ "forced_eos_token_id": null,
324
+ "head_dim": 64,
325
+ "hidden_act": "gelu",
326
+ "hidden_size": 1024,
327
+ "id2label": {
328
+ "0": "LABEL_0",
329
+ "1": "LABEL_1"
330
+ },
331
+ "image_size": 1024,
332
+ "intermediate_size": 4096,
333
+ "is_composition": true,
334
+ "is_decoder": false,
335
+ "is_encoder_decoder": false,
336
+ "label2id": {
337
+ "LABEL_0": 0,
338
+ "LABEL_1": 1
339
+ },
340
+ "length_penalty": 1.0,
341
+ "max_length": 20,
342
+ "min_length": 0,
343
+ "model_type": "pixtral",
344
+ "no_repeat_ngram_size": 0,
345
+ "num_attention_heads": 16,
346
+ "num_beam_groups": 1,
347
+ "num_beams": 1,
348
+ "num_channels": 3,
349
+ "num_hidden_layers": 24,
350
+ "num_return_sequences": 1,
351
+ "output_attentions": false,
352
+ "output_hidden_states": false,
353
+ "output_scores": false,
354
+ "pad_token_id": null,
355
+ "patch_size": 16,
356
+ "prefix": null,
357
+ "problem_type": null,
358
+ "pruned_heads": {},
359
+ "remove_invalid_values": false,
360
+ "repetition_penalty": 1.0,
361
+ "return_dict": true,
362
+ "return_dict_in_generate": false,
363
+ "rope_theta": 10000.0,
364
+ "sep_token_id": null,
365
+ "suppress_tokens": null,
366
+ "task_specific_params": null,
367
+ "temperature": 1.0,
368
+ "tf_legacy_loss": false,
369
+ "tie_encoder_decoder": false,
370
+ "tie_word_embeddings": false,
371
+ "tokenizer_class": null,
372
+ "top_k": 50,
373
+ "top_p": 1.0,
374
+ "torch_dtype": null,
375
+ "torchscript": false,
376
+ "typical_p": 1.0,
377
+ "use_bfloat16": false
378
+ },
379
+ "vision_feature_layer": -1,
380
+ "vision_feature_select_strategy": "full"
381
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694ff3011a5b8627ced5f199c9db28f9959260df8451373bad528b1c054fb440
3
+ size 4991999400
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e43e9bd5457a95b5a1af6bfb55e2d590fc1d003f62865899c7e02514b36ac7
3
+ size 4982793136
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6db63d7b84e4be46d19faf8c23fae527bfa9b2f762fc0e1447a57981902748
3
+ size 4489216120
model.safetensors.index.json ADDED
@@ -0,0 +1,872 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14463893504
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "language_model.model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
11
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
12
+ "language_model.model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
13
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
14
+ "language_model.model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
15
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
16
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
17
+ "language_model.model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
18
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
19
+ "language_model.model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
20
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
21
+ "language_model.model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
22
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
23
+ "language_model.model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
24
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
25
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
26
+ "language_model.model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
27
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
28
+ "language_model.model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
29
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "language_model.model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
31
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
32
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
33
+ "language_model.model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
34
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
35
+ "language_model.model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
36
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
37
+ "language_model.model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
38
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
39
+ "language_model.model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
40
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
41
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
42
+ "language_model.model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
43
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
44
+ "language_model.model.layers.10.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
45
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
46
+ "language_model.model.layers.10.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
47
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
49
+ "language_model.model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
50
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "language_model.model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
52
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
53
+ "language_model.model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
54
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
55
+ "language_model.model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
56
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
57
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
58
+ "language_model.model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
59
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
60
+ "language_model.model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
61
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
62
+ "language_model.model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
63
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
64
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
65
+ "language_model.model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
66
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
67
+ "language_model.model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
68
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
69
+ "language_model.model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
70
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "language_model.model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
72
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
73
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
74
+ "language_model.model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
75
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
76
+ "language_model.model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
77
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
78
+ "language_model.model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
79
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
80
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
81
+ "language_model.model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
82
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
83
+ "language_model.model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
84
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
85
+ "language_model.model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
86
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
87
+ "language_model.model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
88
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
89
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
90
+ "language_model.model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
91
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "language_model.model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
93
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
94
+ "language_model.model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
95
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
96
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
97
+ "language_model.model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
98
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
99
+ "language_model.model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
100
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "language_model.model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
102
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
103
+ "language_model.model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
104
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
105
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
106
+ "language_model.model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
107
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
+ "language_model.model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
109
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "language_model.model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
111
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "language_model.model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
114
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
115
+ "language_model.model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
116
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
117
+ "language_model.model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
118
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
119
+ "language_model.model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
120
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
121
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
122
+ "language_model.model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
123
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
124
+ "language_model.model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
125
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
126
+ "language_model.model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
127
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
128
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
129
+ "language_model.model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
130
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
131
+ "language_model.model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
132
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "language_model.model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
134
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
135
+ "language_model.model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
136
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
137
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
138
+ "language_model.model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
139
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
140
+ "language_model.model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
141
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
142
+ "language_model.model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
143
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
145
+ "language_model.model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
146
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
147
+ "language_model.model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
148
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
149
+ "language_model.model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
150
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
151
+ "language_model.model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
152
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "language_model.model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
155
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
156
+ "language_model.model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
157
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
158
+ "language_model.model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
159
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
160
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
161
+ "language_model.model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
162
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
163
+ "language_model.model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
164
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
165
+ "language_model.model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
166
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
167
+ "language_model.model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
168
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
169
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
170
+ "language_model.model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
171
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
172
+ "language_model.model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
173
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "language_model.model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
175
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
176
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
177
+ "language_model.model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
178
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
179
+ "language_model.model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
180
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
181
+ "language_model.model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
182
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
183
+ "language_model.model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
184
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
185
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
186
+ "language_model.model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
187
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
188
+ "language_model.model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
189
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
190
+ "language_model.model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
191
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
192
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
193
+ "language_model.model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
194
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
195
+ "language_model.model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
196
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
197
+ "language_model.model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
198
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
199
+ "language_model.model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
200
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
201
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
202
+ "language_model.model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
203
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
204
+ "language_model.model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
205
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
206
+ "language_model.model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
207
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
208
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
209
+ "language_model.model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
210
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
211
+ "language_model.model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
212
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
213
+ "language_model.model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
214
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
215
+ "language_model.model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
216
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
217
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
218
+ "language_model.model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
219
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
220
+ "language_model.model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
221
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
222
+ "language_model.model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
223
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
224
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
225
+ "language_model.model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
226
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
227
+ "language_model.model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
228
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
229
+ "language_model.model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
230
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
231
+ "language_model.model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
232
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
233
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
234
+ "language_model.model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
235
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
236
+ "language_model.model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
237
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
238
+ "language_model.model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
239
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
240
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
241
+ "language_model.model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
242
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
243
+ "language_model.model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
244
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
245
+ "language_model.model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
246
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
247
+ "language_model.model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
248
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
249
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
250
+ "language_model.model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
251
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
252
+ "language_model.model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
253
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
254
+ "language_model.model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
255
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
256
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
257
+ "language_model.model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
258
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
259
+ "language_model.model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
260
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
261
+ "language_model.model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
262
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
263
+ "language_model.model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
264
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
265
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
266
+ "language_model.model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
267
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
268
+ "language_model.model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
269
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
270
+ "language_model.model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
271
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
272
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
273
+ "language_model.model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
274
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
275
+ "language_model.model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
276
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
277
+ "language_model.model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
278
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
279
+ "language_model.model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
280
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
281
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
282
+ "language_model.model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
283
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
284
+ "language_model.model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
285
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
286
+ "language_model.model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
287
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
288
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
289
+ "language_model.model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
290
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
291
+ "language_model.model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
292
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
293
+ "language_model.model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
294
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
295
+ "language_model.model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
296
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
297
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
298
+ "language_model.model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
299
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
300
+ "language_model.model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
301
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
302
+ "language_model.model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
303
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
304
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
305
+ "language_model.model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
306
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
307
+ "language_model.model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
308
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
309
+ "language_model.model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
310
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
311
+ "language_model.model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
312
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
313
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
314
+ "language_model.model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
315
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
316
+ "language_model.model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
317
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
318
+ "language_model.model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
319
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
320
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
321
+ "language_model.model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
322
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
323
+ "language_model.model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
324
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
325
+ "language_model.model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
326
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
327
+ "language_model.model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
328
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
329
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
330
+ "language_model.model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
331
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
332
+ "language_model.model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
333
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
334
+ "language_model.model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
335
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
336
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
337
+ "language_model.model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
338
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
339
+ "language_model.model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
340
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
341
+ "language_model.model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
342
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
343
+ "language_model.model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
344
+ "language_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
345
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
346
+ "language_model.model.layers.28.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
347
+ "language_model.model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
348
+ "language_model.model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
349
+ "language_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
350
+ "language_model.model.layers.28.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
351
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
352
+ "language_model.model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
353
+ "language_model.model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
354
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
355
+ "language_model.model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
356
+ "language_model.model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
357
+ "language_model.model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
358
+ "language_model.model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
359
+ "language_model.model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
360
+ "language_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
361
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
362
+ "language_model.model.layers.29.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
363
+ "language_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
364
+ "language_model.model.layers.29.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
365
+ "language_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
366
+ "language_model.model.layers.29.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
367
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
368
+ "language_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
369
+ "language_model.model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
370
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
371
+ "language_model.model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
372
+ "language_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
373
+ "language_model.model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
374
+ "language_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
375
+ "language_model.model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
376
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
377
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
378
+ "language_model.model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
379
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
380
+ "language_model.model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
381
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
382
+ "language_model.model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
383
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
384
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
385
+ "language_model.model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
386
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
387
+ "language_model.model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
388
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
389
+ "language_model.model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
390
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
391
+ "language_model.model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
392
+ "language_model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
393
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
394
+ "language_model.model.layers.30.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
395
+ "language_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
396
+ "language_model.model.layers.30.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
397
+ "language_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
398
+ "language_model.model.layers.30.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
399
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
400
+ "language_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
401
+ "language_model.model.layers.30.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
402
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
403
+ "language_model.model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
404
+ "language_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
405
+ "language_model.model.layers.30.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
406
+ "language_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
407
+ "language_model.model.layers.30.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
408
+ "language_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
409
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
410
+ "language_model.model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
411
+ "language_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
412
+ "language_model.model.layers.31.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
413
+ "language_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
414
+ "language_model.model.layers.31.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
415
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
416
+ "language_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
417
+ "language_model.model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
418
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
419
+ "language_model.model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
420
+ "language_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
421
+ "language_model.model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
422
+ "language_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
423
+ "language_model.model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
424
+ "language_model.model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
425
+ "language_model.model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
426
+ "language_model.model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
427
+ "language_model.model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
428
+ "language_model.model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
429
+ "language_model.model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
430
+ "language_model.model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
431
+ "language_model.model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
432
+ "language_model.model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
433
+ "language_model.model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
434
+ "language_model.model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
435
+ "language_model.model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
436
+ "language_model.model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
437
+ "language_model.model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
438
+ "language_model.model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
439
+ "language_model.model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
440
+ "language_model.model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
441
+ "language_model.model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
442
+ "language_model.model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
443
+ "language_model.model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
444
+ "language_model.model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
445
+ "language_model.model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
446
+ "language_model.model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
447
+ "language_model.model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
448
+ "language_model.model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
449
+ "language_model.model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
450
+ "language_model.model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
451
+ "language_model.model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
452
+ "language_model.model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
453
+ "language_model.model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
454
+ "language_model.model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
455
+ "language_model.model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
456
+ "language_model.model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
457
+ "language_model.model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
458
+ "language_model.model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
459
+ "language_model.model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
460
+ "language_model.model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
461
+ "language_model.model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
462
+ "language_model.model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
463
+ "language_model.model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
464
+ "language_model.model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
465
+ "language_model.model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
466
+ "language_model.model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
467
+ "language_model.model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
468
+ "language_model.model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
469
+ "language_model.model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
470
+ "language_model.model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
471
+ "language_model.model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
472
+ "language_model.model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
473
+ "language_model.model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
474
+ "language_model.model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
475
+ "language_model.model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
476
+ "language_model.model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
477
+ "language_model.model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
478
+ "language_model.model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
479
+ "language_model.model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
480
+ "language_model.model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
481
+ "language_model.model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
482
+ "language_model.model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
483
+ "language_model.model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
484
+ "language_model.model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
485
+ "language_model.model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
486
+ "language_model.model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
487
+ "language_model.model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
488
+ "language_model.model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
489
+ "language_model.model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
490
+ "language_model.model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
491
+ "language_model.model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
492
+ "language_model.model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
493
+ "language_model.model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
494
+ "language_model.model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
495
+ "language_model.model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
496
+ "language_model.model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
497
+ "language_model.model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
498
+ "language_model.model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
499
+ "language_model.model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
500
+ "language_model.model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
501
+ "language_model.model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
502
+ "language_model.model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
503
+ "language_model.model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
504
+ "language_model.model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
505
+ "language_model.model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
506
+ "language_model.model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
507
+ "language_model.model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
508
+ "language_model.model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
509
+ "language_model.model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
510
+ "language_model.model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
511
+ "language_model.model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
512
+ "language_model.model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
513
+ "language_model.model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
514
+ "language_model.model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
515
+ "language_model.model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
516
+ "language_model.model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
517
+ "language_model.model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
518
+ "language_model.model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
519
+ "language_model.model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
520
+ "language_model.model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
521
+ "language_model.model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
522
+ "language_model.model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
523
+ "language_model.model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
524
+ "language_model.model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
525
+ "language_model.model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
526
+ "language_model.model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
527
+ "language_model.model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
528
+ "language_model.model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
529
+ "language_model.model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
530
+ "language_model.model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
531
+ "language_model.model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
532
+ "language_model.model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
533
+ "language_model.model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
534
+ "language_model.model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
535
+ "language_model.model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
536
+ "language_model.model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
537
+ "language_model.model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
538
+ "language_model.model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
539
+ "language_model.model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
540
+ "language_model.model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
541
+ "language_model.model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
542
+ "language_model.model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
543
+ "language_model.model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
544
+ "language_model.model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
545
+ "language_model.model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
546
+ "language_model.model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
547
+ "language_model.model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
548
+ "language_model.model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
549
+ "language_model.model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
550
+ "language_model.model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
551
+ "language_model.model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
552
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
553
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
554
+ "language_model.model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
555
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
556
+ "language_model.model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
557
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
558
+ "language_model.model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
559
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
560
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
561
+ "language_model.model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
562
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
563
+ "language_model.model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
564
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
565
+ "language_model.model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
566
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
567
+ "language_model.model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
568
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
569
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
570
+ "language_model.model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
571
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
572
+ "language_model.model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
573
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
574
+ "language_model.model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
575
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
576
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
577
+ "language_model.model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
578
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
579
+ "language_model.model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
580
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
581
+ "language_model.model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
582
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
583
+ "language_model.model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
584
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
585
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
586
+ "language_model.model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
587
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
588
+ "language_model.model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
589
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
590
+ "language_model.model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
591
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
592
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
593
+ "language_model.model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
594
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
595
+ "language_model.model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
596
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
597
+ "language_model.model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
598
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
599
+ "language_model.model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
600
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
601
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
602
+ "language_model.model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
603
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
604
+ "language_model.model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
605
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
606
+ "language_model.model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
607
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
608
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
609
+ "language_model.model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
610
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
611
+ "language_model.model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
612
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
613
+ "language_model.model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
614
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
615
+ "language_model.model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
616
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
617
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
618
+ "language_model.model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
619
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
620
+ "language_model.model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
621
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
622
+ "language_model.model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
623
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
624
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
625
+ "language_model.model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
626
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
627
+ "language_model.model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
628
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
629
+ "language_model.model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
630
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
631
+ "language_model.model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
632
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
633
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
634
+ "language_model.model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
635
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
636
+ "language_model.model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
637
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
638
+ "language_model.model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
639
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
640
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
641
+ "language_model.model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
642
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
643
+ "language_model.model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
644
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
645
+ "language_model.model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
646
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
647
+ "language_model.model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
648
+ "language_model.model.norm.weight": "model-00003-of-00003.safetensors",
649
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00003.safetensors",
650
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00003.safetensors",
651
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00003.safetensors",
652
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00003.safetensors",
653
+ "vision_tower.ln_pre.weight": "model-00001-of-00003.safetensors",
654
+ "vision_tower.patch_conv.weight": "model-00001-of-00003.safetensors",
655
+ "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00003.safetensors",
656
+ "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00003.safetensors",
657
+ "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00003.safetensors",
658
+ "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00003.safetensors",
659
+ "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00003.safetensors",
660
+ "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
661
+ "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
662
+ "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
663
+ "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00003.safetensors",
664
+ "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00003.safetensors",
665
+ "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00003.safetensors",
666
+ "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00003.safetensors",
667
+ "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00003.safetensors",
668
+ "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00003.safetensors",
669
+ "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
670
+ "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
671
+ "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
672
+ "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00003.safetensors",
673
+ "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00003.safetensors",
674
+ "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00003.safetensors",
675
+ "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00003.safetensors",
676
+ "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00003.safetensors",
677
+ "vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00003.safetensors",
678
+ "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
679
+ "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
680
+ "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
681
+ "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00003.safetensors",
682
+ "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00003.safetensors",
683
+ "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00003.safetensors",
684
+ "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00003.safetensors",
685
+ "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00003.safetensors",
686
+ "vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00003.safetensors",
687
+ "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
688
+ "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
689
+ "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
690
+ "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00003.safetensors",
691
+ "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00003.safetensors",
692
+ "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00003.safetensors",
693
+ "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00003.safetensors",
694
+ "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00003.safetensors",
695
+ "vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00003.safetensors",
696
+ "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
697
+ "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
698
+ "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
699
+ "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00003.safetensors",
700
+ "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00003.safetensors",
701
+ "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00003.safetensors",
702
+ "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00003.safetensors",
703
+ "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00003.safetensors",
704
+ "vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00003.safetensors",
705
+ "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
706
+ "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
707
+ "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
708
+ "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00003.safetensors",
709
+ "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00003.safetensors",
710
+ "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00003.safetensors",
711
+ "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00003.safetensors",
712
+ "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00003.safetensors",
713
+ "vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00003.safetensors",
714
+ "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
715
+ "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
716
+ "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
717
+ "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00003.safetensors",
718
+ "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00003.safetensors",
719
+ "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00003.safetensors",
720
+ "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00003.safetensors",
721
+ "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00003.safetensors",
722
+ "vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00003.safetensors",
723
+ "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
724
+ "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
725
+ "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
726
+ "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00003.safetensors",
727
+ "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00003.safetensors",
728
+ "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00003.safetensors",
729
+ "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00003.safetensors",
730
+ "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00003.safetensors",
731
+ "vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00003.safetensors",
732
+ "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
733
+ "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
734
+ "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
735
+ "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00003.safetensors",
736
+ "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00003.safetensors",
737
+ "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00003.safetensors",
738
+ "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00003.safetensors",
739
+ "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00003.safetensors",
740
+ "vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00003.safetensors",
741
+ "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
742
+ "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
743
+ "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
744
+ "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00003.safetensors",
745
+ "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00003.safetensors",
746
+ "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00003.safetensors",
747
+ "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00003.safetensors",
748
+ "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00003.safetensors",
749
+ "vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00003.safetensors",
750
+ "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
751
+ "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
752
+ "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
753
+ "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00003.safetensors",
754
+ "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00003.safetensors",
755
+ "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00003.safetensors",
756
+ "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00003.safetensors",
757
+ "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00003.safetensors",
758
+ "vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00003.safetensors",
759
+ "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
760
+ "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
761
+ "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
762
+ "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00003.safetensors",
763
+ "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00003.safetensors",
764
+ "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00003.safetensors",
765
+ "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00003.safetensors",
766
+ "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00003.safetensors",
767
+ "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00003.safetensors",
768
+ "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
769
+ "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
770
+ "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
771
+ "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00003.safetensors",
772
+ "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00003.safetensors",
773
+ "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00003.safetensors",
774
+ "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00003.safetensors",
775
+ "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00003.safetensors",
776
+ "vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00003.safetensors",
777
+ "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
778
+ "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
779
+ "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
780
+ "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00003.safetensors",
781
+ "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00003.safetensors",
782
+ "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00003.safetensors",
783
+ "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00003.safetensors",
784
+ "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00003.safetensors",
785
+ "vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00003.safetensors",
786
+ "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
787
+ "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
788
+ "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
789
+ "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00003.safetensors",
790
+ "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00003.safetensors",
791
+ "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00003.safetensors",
792
+ "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00003.safetensors",
793
+ "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00003.safetensors",
794
+ "vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00003.safetensors",
795
+ "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
796
+ "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
797
+ "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
798
+ "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00003.safetensors",
799
+ "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00003.safetensors",
800
+ "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00003.safetensors",
801
+ "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00003.safetensors",
802
+ "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00003.safetensors",
803
+ "vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00003.safetensors",
804
+ "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
805
+ "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
806
+ "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
807
+ "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00003.safetensors",
808
+ "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00003.safetensors",
809
+ "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00003.safetensors",
810
+ "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00003.safetensors",
811
+ "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00003.safetensors",
812
+ "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00003.safetensors",
813
+ "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
814
+ "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
815
+ "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
816
+ "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00003.safetensors",
817
+ "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00003.safetensors",
818
+ "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00003.safetensors",
819
+ "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00003.safetensors",
820
+ "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00003.safetensors",
821
+ "vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00003.safetensors",
822
+ "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
823
+ "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
824
+ "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
825
+ "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00003.safetensors",
826
+ "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00003.safetensors",
827
+ "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00003.safetensors",
828
+ "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00003.safetensors",
829
+ "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00003.safetensors",
830
+ "vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00003.safetensors",
831
+ "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
832
+ "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
833
+ "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
834
+ "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00003.safetensors",
835
+ "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00003.safetensors",
836
+ "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00003.safetensors",
837
+ "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00003.safetensors",
838
+ "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00003.safetensors",
839
+ "vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00003.safetensors",
840
+ "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
841
+ "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
842
+ "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
843
+ "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00003.safetensors",
844
+ "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00003.safetensors",
845
+ "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00003.safetensors",
846
+ "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00003.safetensors",
847
+ "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00003.safetensors",
848
+ "vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00003.safetensors",
849
+ "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
850
+ "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
851
+ "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
852
+ "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00003.safetensors",
853
+ "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00003.safetensors",
854
+ "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00003.safetensors",
855
+ "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00003.safetensors",
856
+ "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00003.safetensors",
857
+ "vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00003.safetensors",
858
+ "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
859
+ "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
860
+ "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
861
+ "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00003.safetensors",
862
+ "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00003.safetensors",
863
+ "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00003.safetensors",
864
+ "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00003.safetensors",
865
+ "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00003.safetensors",
866
+ "vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00003.safetensors",
867
+ "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00003.safetensors",
868
+ "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00003.safetensors",
869
+ "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00003.safetensors",
870
+ "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00003.safetensors"
871
+ }
872
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "PixtralImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "patch_size": {
18
+ "height": 16,
19
+ "width": 16
20
+ },
21
+ "processor_class": "PixtralProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1024
26
+ }
27
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_break_token": "[IMG_BREAK]",
3
+ "image_end_token": "[IMG_END]",
4
+ "image_token": "[IMG]",
5
+ "patch_size": 16,
6
+ "processor_class": "PixtralProcessor"
7
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ DEFAULT_stage:
2
+ DEFAULT_modifiers:
3
+ QuantizationModifier:
4
+ ignore: ['re:.*lm_head', 're:multi_modal_projector.*', 're:vision_tower.*']
5
+ targets: Linear
6
+ scheme: FP8_DYNAMIC
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcdf3e6b96371b9a5c8673bdf2f1bc838b994b73a6fa995dca62196346aaddb5
3
+ size 17077311
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff