Hugging Face's logo

GregTarr
/
Qwen3-VL-30B-A3B-Instruct-002-v3-20251028-060225

Safetensors
qwen3_vl_moe
Model card Files
xet
Community
GregTarr commited on
Commit
3e4f1d3
·
verified ·
1 Parent(s): 2ff703c

Add files using upload-large-folder tool

Browse files
Files changed (27) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +28 -0
  3. args.json +476 -0
  4. chat_template.jinja +120 -0
  5. config.json +75 -0
  6. generation_config.json +13 -0
  7. merges.txt +0 -0
  8. model-00001-of-00013.safetensors +3 -0
  9. model-00002-of-00013.safetensors +3 -0
  10. model-00003-of-00013.safetensors +3 -0
  11. model-00004-of-00013.safetensors +3 -0
  12. model-00005-of-00013.safetensors +3 -0
  13. model-00006-of-00013.safetensors +3 -0
  14. model-00007-of-00013.safetensors +3 -0
  15. model-00008-of-00013.safetensors +3 -0
  16. model-00009-of-00013.safetensors +3 -0
  17. model-00010-of-00013.safetensors +3 -0
  18. model-00011-of-00013.safetensors +3 -0
  19. model-00012-of-00013.safetensors +3 -0
  20. model-00013-of-00013.safetensors +3 -0
  21. model.safetensors.index.json +890 -0
  22. preprocessor_config.json +21 -0
  23. special_tokens_map.json +31 -0
  24. tokenizer.json +3 -0
  25. tokenizer_config.json +240 -0
  26. video_preprocessor_config.json +41 -0
  27. vocab.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
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
args.json ADDED
@@ -0,0 +1,476 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "Qwen/Qwen3-VL-30B-A3B-Instruct",
3
+ "model_type": "qwen3_moe_vl",
4
+ "model_revision": null,
5
+ "task_type": "causal_lm",
6
+ "torch_dtype": "bfloat16",
7
+ "attn_impl": null,
8
+ "new_special_tokens": [],
9
+ "num_labels": null,
10
+ "problem_type": null,
11
+ "rope_scaling": {
12
+ "mrope_interleaved": true,
13
+ "mrope_section": [
14
+ 24,
15
+ 20,
16
+ 20
17
+ ],
18
+ "rope_type": "default"
19
+ },
20
+ "device_map": null,
21
+ "max_memory": {},
22
+ "max_model_len": null,
23
+ "local_repo_path": null,
24
+ "init_strategy": null,
25
+ "template": "qwen3_vl",
26
+ "system": null,
27
+ "max_length": 8192,
28
+ "truncation_strategy": "delete",
29
+ "max_pixels": null,
30
+ "agent_template": null,
31
+ "norm_bbox": null,
32
+ "use_chat_template": true,
33
+ "padding_free": true,
34
+ "padding_side": "right",
35
+ "loss_scale": "default",
36
+ "sequence_parallel_size": 1,
37
+ "response_prefix": null,
38
+ "template_backend": "swift",
39
+ "dataset": [
40
+ "datasets/combined.jsonl"
41
+ ],
42
+ "val_dataset": [],
43
+ "split_dataset_ratio": 0.0,
44
+ "data_seed": 42,
45
+ "dataset_num_proc": 64,
46
+ "load_from_cache_file": true,
47
+ "dataset_shuffle": true,
48
+ "val_dataset_shuffle": false,
49
+ "streaming": false,
50
+ "interleave_prob": null,
51
+ "stopping_strategy": "first_exhausted",
52
+ "shuffle_buffer_size": 1000,
53
+ "download_mode": "reuse_dataset_if_exists",
54
+ "columns": {},
55
+ "strict": false,
56
+ "remove_unused_columns": true,
57
+ "model_name": null,
58
+ "model_author": null,
59
+ "custom_dataset_info": [],
60
+ "quant_method": null,
61
+ "quant_bits": null,
62
+ "hqq_axis": null,
63
+ "bnb_4bit_compute_dtype": "bfloat16",
64
+ "bnb_4bit_quant_type": "nf4",
65
+ "bnb_4bit_use_double_quant": true,
66
+ "bnb_4bit_quant_storage": null,
67
+ "max_new_tokens": null,
68
+ "temperature": null,
69
+ "top_k": null,
70
+ "top_p": null,
71
+ "repetition_penalty": null,
72
+ "num_beams": 1,
73
+ "stream": false,
74
+ "stop_words": [],
75
+ "logprobs": false,
76
+ "top_logprobs": null,
77
+ "ckpt_dir": "/root/ms-swift/Qwen3-VL-30B-A3B-Instruct-mcore",
78
+ "lora_modules": [],
79
+ "tuner_backend": "peft",
80
+ "train_type": "full",
81
+ "adapters": [],
82
+ "external_plugins": [],
83
+ "seed": 42,
84
+ "model_kwargs": {},
85
+ "load_args": false,
86
+ "load_data_args": false,
87
+ "packing": true,
88
+ "packing_length": 8192,
89
+ "lazy_tokenize": false,
90
+ "cached_dataset": [],
91
+ "custom_register_path": [],
92
+ "use_hf": true,
93
+ "hub_token": null,
94
+ "ddp_timeout": 18000000,
95
+ "ddp_backend": null,
96
+ "ignore_args_error": false,
97
+ "use_swift_lora": false,
98
+ "freeze_llm": false,
99
+ "freeze_vit": true,
100
+ "freeze_aligner": true,
101
+ "freeze_parameters": [],
102
+ "freeze_parameters_regex": null,
103
+ "freeze_parameters_ratio": 0.0,
104
+ "trainable_parameters": [],
105
+ "trainable_parameters_regex": null,
106
+ "adapter_load": null,
107
+ "target_modules": [
108
+ "all-linear"
109
+ ],
110
+ "target_regex": null,
111
+ "modules_to_save": [],
112
+ "lora_rank": 8,
113
+ "lora_alpha": 32,
114
+ "lora_dropout": 0.05,
115
+ "lora_bias": "none",
116
+ "lora_dtype": null,
117
+ "use_rslora": false,
118
+ "rlhf_type": null,
119
+ "ref_load": null,
120
+ "ref_adapter_load": null,
121
+ "beta": 0.1,
122
+ "rpo_alpha": null,
123
+ "reference_free": false,
124
+ "label_smoothing": 0.0,
125
+ "f_divergence_type": "reverse_kl",
126
+ "loss_type": null,
127
+ "desirable_weight": 1.0,
128
+ "undesirable_weight": 1.0,
129
+ "calculate_KL": null,
130
+ "center_rewards_coefficient": null,
131
+ "padded_vocab_size": 151936,
132
+ "initialize_embedding": false,
133
+ "mlp_padding_free": false,
134
+ "dataloader_persistent_workers": true,
135
+ "dataloader_prefetch_factor": 10,
136
+ "architectures": "Qwen3VLMoeForConditionalGeneration",
137
+ "llm_architectures": null,
138
+ "max_epochs": 1,
139
+ "enable_dft_loss": false,
140
+ "enable_channel_loss": false,
141
+ "original_max_position_embeddings": null,
142
+ "partial_rotary_factor": null,
143
+ "use_shared_expert_gate": false,
144
+ "vit_gradient_checkpointing": true,
145
+ "gradient_checkpointing_kwargs": null,
146
+ "linear_num_value_heads": null,
147
+ "linear_num_key_heads": null,
148
+ "linear_key_head_dim": null,
149
+ "linear_value_head_dim": null,
150
+ "linear_conv_kernel_dim": null,
151
+ "layer_types": null,
152
+ "mrope_interleaved": true,
153
+ "micro_batch_size": 1,
154
+ "global_batch_size": 16,
155
+ "recompute_granularity": "full",
156
+ "recompute_method": "uniform",
157
+ "recompute_num_layers": 1,
158
+ "recompute_modules": [
159
+ "core_attn"
160
+ ],
161
+ "use_cpu_initialization": false,
162
+ "deterministic_mode": false,
163
+ "train_iters": null,
164
+ "log_interval": 1,
165
+ "tensorboard_dir": "/root/ms-swift/megatron_output/Qwen3-VL-30B-A3B-Instruct-002/v3-20251028-060225/runs",
166
+ "no_masked_softmax_fusion": false,
167
+ "no_bias_dropout_fusion": false,
168
+ "no_bias_swiglu_fusion": false,
169
+ "no_rope_fusion": false,
170
+ "no_gradient_accumulation_fusion": false,
171
+ "cross_entropy_loss_fusion": true,
172
+ "cross_entropy_fusion_impl": "native",
173
+ "calculate_per_token_loss": true,
174
+ "use_flash_attn": false,
175
+ "attention_backend": "flash",
176
+ "optimizer": "adam",
177
+ "optimizer_cpu_offload": false,
178
+ "optimizer_offload_fraction": 1.0,
179
+ "use_precision_aware_optimizer": true,
180
+ "main_grads_dtype": "fp32",
181
+ "main_params_dtype": "fp32",
182
+ "exp_avg_dtype": "fp32",
183
+ "exp_avg_sq_dtype": "fp32",
184
+ "dataloader_type": "cyclic",
185
+ "manual_gc": false,
186
+ "manual_gc_interval": 0,
187
+ "lr": 1e-05,
188
+ "lr_decay_style": "cosine",
189
+ "lr_decay_iters": null,
190
+ "lr_warmup_iters": 0,
191
+ "lr_warmup_fraction": 0.05,
192
+ "min_lr": 1e-06,
193
+ "weight_decay": 0.1,
194
+ "clip_grad": 1.0,
195
+ "adam_beta1": 0.9,
196
+ "adam_beta2": 0.95,
197
+ "adam_eps": 1e-08,
198
+ "sgd_momentum": 0.9,
199
+ "save": "/root/ms-swift/megatron_output/Qwen3-VL-30B-A3B-Instruct-002/v3-20251028-060225",
200
+ "save_interval": 1000,
201
+ "no_save_optim": true,
202
+ "no_save_rng": true,
203
+ "load": "/root/ms-swift/Qwen3-VL-30B-A3B-Instruct-mcore",
204
+ "no_load_optim": false,
205
+ "no_load_rng": false,
206
+ "finetune": true,
207
+ "ckpt_format": "torch_dist",
208
+ "no_initialization": true,
209
+ "auto_detect_ckpt_format": true,
210
+ "exit_on_missing_checkpoint": true,
211
+ "distributed_backend": "nccl",
212
+ "local_rank": 0,
213
+ "use_distributed_optimizer": true,
214
+ "tensor_model_parallel_size": 1,
215
+ "pipeline_model_parallel_size": 1,
216
+ "decoder_first_pipeline_num_layers": null,
217
+ "decoder_last_pipeline_num_layers": null,
218
+ "sequence_parallel": true,
219
+ "context_parallel_size": 1,
220
+ "tp_comm_overlap": false,
221
+ "overlap_grad_reduce": true,
222
+ "overlap_param_gather": true,
223
+ "distributed_timeout_minutes": 300000,
224
+ "num_layers_per_virtual_pipeline_stage": null,
225
+ "num_virtual_stages_per_pipeline_rank": null,
226
+ "microbatch_group_size_per_virtual_pipeline_stage": null,
227
+ "pipeline_model_parallel_layout": null,
228
+ "num_layers": 48,
229
+ "hidden_size": 2048,
230
+ "ffn_hidden_size": null,
231
+ "num_attention_heads": 32,
232
+ "group_query_attention": true,
233
+ "num_query_groups": 4,
234
+ "max_position_embeddings": 262144,
235
+ "position_embedding_type": "mrope",
236
+ "mrope_section": [
237
+ 24,
238
+ 20,
239
+ 20
240
+ ],
241
+ "rotary_base": 5000000,
242
+ "rotary_percent": 1.0,
243
+ "rotary_interleaved": false,
244
+ "normalization": "RMSNorm",
245
+ "norm_epsilon": 1e-06,
246
+ "swiglu": true,
247
+ "untie_embeddings_and_output_weights": true,
248
+ "disable_bias_linear": true,
249
+ "add_qkv_bias": false,
250
+ "attention_dropout": 0.0,
251
+ "hidden_dropout": 0.0,
252
+ "kv_channels": 128,
253
+ "qk_layernorm": true,
254
+ "transformer_impl": "transformer_engine",
255
+ "num_experts": 128,
256
+ "moe_layer_freq": "1",
257
+ "moe_ffn_hidden_size": 768,
258
+ "moe_shared_expert_intermediate_size": null,
259
+ "moe_router_topk": 8,
260
+ "moe_router_pre_softmax": false,
261
+ "moe_router_dtype": "fp32",
262
+ "moe_router_score_function": "softmax",
263
+ "moe_router_bias_update_rate": 0.001,
264
+ "moe_router_enable_expert_bias": false,
265
+ "moe_router_topk_scaling_factor": null,
266
+ "moe_router_load_balancing_type": "aux_loss",
267
+ "expert_model_parallel_size": 8,
268
+ "expert_tensor_parallel_size": 1,
269
+ "moe_token_dispatcher_type": null,
270
+ "moe_enable_deepep": false,
271
+ "moe_grouped_gemm": true,
272
+ "moe_permute_fusion": true,
273
+ "moe_aux_loss_coeff": 0.0,
274
+ "moe_z_loss_coeff": null,
275
+ "moe_shared_expert_overlap": true,
276
+ "moe_layer_recompute": false,
277
+ "moe_expert_capacity_factor": null,
278
+ "moe_pad_expert_input_to_capacity": false,
279
+ "moe_token_drop_policy": null,
280
+ "multi_latent_attention": false,
281
+ "q_lora_rank": null,
282
+ "kv_lora_rank": 32,
283
+ "qk_head_dim": 128,
284
+ "qk_pos_emb_head_dim": 64,
285
+ "fp8_format": null,
286
+ "fp8_recipe": "delayed",
287
+ "fp8_amax_history_len": 1024,
288
+ "fp8_amax_compute_algo": "max",
289
+ "fp8_param_gather": false,
290
+ "fp16": false,
291
+ "bf16": true,
292
+ "apply_query_key_layer_scaling": false,
293
+ "attention_softmax_in_fp32": true,
294
+ "log_params_norm": false,
295
+ "log_throughput": true,
296
+ "tensorboard_log_interval": 1,
297
+ "tensorboard_queue_size": 50,
298
+ "log_timers_to_tensorboard": true,
299
+ "no_log_learning_rate_to_tensorboard": false,
300
+ "log_validation_ppl_to_tensorboard": true,
301
+ "log_memory_to_tensorboard": true,
302
+ "logging_level": null,
303
+ "wandb_project": null,
304
+ "wandb_exp_name": null,
305
+ "wandb_save_dir": null,
306
+ "eval_iters": -1,
307
+ "eval_interval": 1000,
308
+ "seq_length": 8192,
309
+ "num_workers": 16,
310
+ "extra_megatron_kwargs": {},
311
+ "add_version": true,
312
+ "rank": 0,
313
+ "global_world_size": 8,
314
+ "local_world_size": 8,
315
+ "model_suffix": "Qwen3-VL-30B-A3B-Instruct",
316
+ "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-VL-30B-A3B-Instruct/snapshots/4b184fbdab8886057d8d80c09f35bcfc65fe640e', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
317
+ "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_moe_vl at 0x72079394e020>, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
318
+ "model_dir": "/root/.cache/huggingface/hub/models--Qwen--Qwen3-VL-30B-A3B-Instruct/snapshots/4b184fbdab8886057d8d80c09f35bcfc65fe640e",
319
+ "hub": "<class 'swift.hub.hub.HFHub'>",
320
+ "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], convert_mcore2hf=<function convert_mcore2hf_qwen3_vl at 0x7206cb39cd60>, convert_hf2mcore=<function convert_hf2mcore_qwen3_vl at 0x7206cb39c5e0>, model_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VLGPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x7206cb53ccc0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7206cb523880>, visual_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VL_Vit'>, extra_args_provider=None)",
321
+ "extra_args": {
322
+ "model": "Qwen/Qwen3-VL-30B-A3B-Instruct",
323
+ "model_type": "qwen3_moe_vl",
324
+ "model_revision": null,
325
+ "task_type": "causal_lm",
326
+ "torch_dtype": "bfloat16",
327
+ "attn_impl": null,
328
+ "new_special_tokens": [],
329
+ "num_labels": null,
330
+ "problem_type": null,
331
+ "rope_scaling": {
332
+ "mrope_interleaved": true,
333
+ "mrope_section": [
334
+ 24,
335
+ 20,
336
+ 20
337
+ ],
338
+ "rope_type": "default"
339
+ },
340
+ "device_map": null,
341
+ "max_memory": {},
342
+ "max_model_len": null,
343
+ "local_repo_path": null,
344
+ "init_strategy": null,
345
+ "template": "qwen3_vl",
346
+ "system": null,
347
+ "max_length": 8192,
348
+ "truncation_strategy": "delete",
349
+ "max_pixels": null,
350
+ "agent_template": null,
351
+ "norm_bbox": null,
352
+ "use_chat_template": true,
353
+ "padding_free": true,
354
+ "padding_side": "right",
355
+ "sequence_parallel_size": 1,
356
+ "response_prefix": null,
357
+ "template_backend": "swift",
358
+ "dataset": [
359
+ "datasets/combined.jsonl"
360
+ ],
361
+ "val_dataset": [],
362
+ "split_dataset_ratio": 0.0,
363
+ "data_seed": 42,
364
+ "dataset_num_proc": 64,
365
+ "load_from_cache_file": true,
366
+ "dataset_shuffle": true,
367
+ "val_dataset_shuffle": false,
368
+ "streaming": false,
369
+ "interleave_prob": null,
370
+ "stopping_strategy": "first_exhausted",
371
+ "shuffle_buffer_size": 1000,
372
+ "download_mode": "reuse_dataset_if_exists",
373
+ "columns": {},
374
+ "strict": false,
375
+ "remove_unused_columns": true,
376
+ "model_name": null,
377
+ "model_author": null,
378
+ "custom_dataset_info": [],
379
+ "quant_method": null,
380
+ "quant_bits": null,
381
+ "hqq_axis": null,
382
+ "bnb_4bit_compute_dtype": "bfloat16",
383
+ "bnb_4bit_quant_type": "nf4",
384
+ "bnb_4bit_use_double_quant": true,
385
+ "bnb_4bit_quant_storage": null,
386
+ "max_new_tokens": null,
387
+ "temperature": null,
388
+ "top_k": null,
389
+ "top_p": null,
390
+ "repetition_penalty": null,
391
+ "num_beams": 1,
392
+ "stream": false,
393
+ "stop_words": [],
394
+ "logprobs": false,
395
+ "top_logprobs": null,
396
+ "ckpt_dir": "/root/ms-swift/Qwen3-VL-30B-A3B-Instruct-mcore",
397
+ "lora_modules": [],
398
+ "tuner_backend": "peft",
399
+ "train_type": "full",
400
+ "adapters": [],
401
+ "external_plugins": [],
402
+ "model_kwargs": {},
403
+ "load_args": false,
404
+ "load_data_args": false,
405
+ "packing": true,
406
+ "packing_length": 8192,
407
+ "lazy_tokenize": false,
408
+ "cached_dataset": [],
409
+ "custom_register_path": [],
410
+ "use_hf": true,
411
+ "hub_token": null,
412
+ "ddp_timeout": 18000000,
413
+ "ddp_backend": null,
414
+ "ignore_args_error": false,
415
+ "use_swift_lora": false,
416
+ "freeze_llm": false,
417
+ "freeze_vit": true,
418
+ "freeze_aligner": true,
419
+ "freeze_parameters": [],
420
+ "freeze_parameters_regex": null,
421
+ "freeze_parameters_ratio": 0.0,
422
+ "trainable_parameters": [],
423
+ "trainable_parameters_regex": null,
424
+ "adapter_load": null,
425
+ "target_modules": [
426
+ "all-linear"
427
+ ],
428
+ "target_regex": null,
429
+ "modules_to_save": [],
430
+ "lora_rank": 8,
431
+ "lora_alpha": 32,
432
+ "lora_dropout": 0.05,
433
+ "lora_bias": "none",
434
+ "lora_dtype": null,
435
+ "use_rslora": false,
436
+ "rlhf_type": null,
437
+ "ref_load": null,
438
+ "ref_adapter_load": null,
439
+ "beta": 0.1,
440
+ "rpo_alpha": null,
441
+ "reference_free": false,
442
+ "label_smoothing": 0.0,
443
+ "f_divergence_type": "reverse_kl",
444
+ "loss_type": null,
445
+ "desirable_weight": 1.0,
446
+ "undesirable_weight": 1.0,
447
+ "calculate_KL": null,
448
+ "center_rewards_coefficient": null,
449
+ "padded_vocab_size": 151936,
450
+ "initialize_embedding": false,
451
+ "mlp_padding_free": false,
452
+ "dataloader_persistent_workers": true,
453
+ "dataloader_prefetch_factor": 10,
454
+ "architectures": "Qwen3VLMoeForConditionalGeneration",
455
+ "llm_architectures": null,
456
+ "max_epochs": 1,
457
+ "enable_dft_loss": false,
458
+ "enable_channel_loss": false,
459
+ "original_max_position_embeddings": null,
460
+ "partial_rotary_factor": null,
461
+ "use_shared_expert_gate": false,
462
+ "vit_gradient_checkpointing": true,
463
+ "gradient_checkpointing_kwargs": null,
464
+ "linear_num_value_heads": null,
465
+ "linear_num_key_heads": null,
466
+ "linear_key_head_dim": null,
467
+ "linear_value_head_dim": null,
468
+ "linear_conv_kernel_dim": null,
469
+ "layer_types": null,
470
+ "mrope_interleaved": true,
471
+ "add_version": true,
472
+ "model_info": "ModelInfo(model_type='qwen3_moe_vl', model_dir='/root/.cache/huggingface/hub/models--Qwen--Qwen3-VL-30B-A3B-Instruct/snapshots/4b184fbdab8886057d8d80c09f35bcfc65fe640e', torch_dtype=torch.bfloat16, max_model_len=262144, quant_method=None, quant_bits=None, rope_scaling={'mrope_interleaved': True, 'mrope_section': [24, 20, 20], 'rope_type': 'default'}, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)",
473
+ "model_meta": "ModelMeta(model_type='qwen3_moe_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-30B-A3B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-235B-A22B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='qwen3_vl', get_function=<function get_model_tokenizer_qwen3_moe_vl at 0x72079394e020>, model_arch=MultiModelKeys(arch_name='qwen3_vl', embedding=None, module_list=None, lm_head=None, q_proj=None, k_proj=None, v_proj=None, o_proj=None, attention=None, mlp=None, down_proj=None, qkv_proj=None, qk_proj=None, qa_proj=None, qb_proj=None, kv_proj=None, kva_proj=None, kvb_proj=None, language_model=['model.language_model'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLMoeForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
474
+ "megatron_model_meta": "MMGPTMegatronModelMeta(megatron_model_type='qwen3_vl', model_types=['qwen3_vl', 'qwen3_moe_vl'], convert_mcore2hf=<function convert_mcore2hf_qwen3_vl at 0x7206cb39cd60>, convert_hf2mcore=<function convert_hf2mcore_qwen3_vl at 0x7206cb39c5e0>, model_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VLGPTModel'>, convert_hf_config=<function convert_gpt_hf_config at 0x7206cb53ccc0>, get_transformer_layer_spec=None, model_provider=<function model_provider at 0x7206cb523880>, visual_cls=<class 'swift.megatron.model.mm_gpt.qwen3_vl.Qwen3VL_Vit'>, extra_args_provider=None)"
475
+ }
476
+ }
chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if 'text' in content %}
9
+ {{- content.text }}
10
+ {%- endif %}
11
+ {%- endfor %}
12
+ {%- endif %}
13
+ {{- '\n\n' }}
14
+ {%- endif %}
15
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
16
+ {%- for tool in tools %}
17
+ {{- "\n" }}
18
+ {{- tool | tojson }}
19
+ {%- endfor %}
20
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
21
+ {%- else %}
22
+ {%- if messages[0].role == 'system' %}
23
+ {{- '<|im_start|>system\n' }}
24
+ {%- if messages[0].content is string %}
25
+ {{- messages[0].content }}
26
+ {%- else %}
27
+ {%- for content in messages[0].content %}
28
+ {%- if 'text' in content %}
29
+ {{- content.text }}
30
+ {%- endif %}
31
+ {%- endfor %}
32
+ {%- endif %}
33
+ {{- '<|im_end|>\n' }}
34
+ {%- endif %}
35
+ {%- endif %}
36
+ {%- set image_count = namespace(value=0) %}
37
+ {%- set video_count = namespace(value=0) %}
38
+ {%- for message in messages %}
39
+ {%- if message.role == "user" %}
40
+ {{- '<|im_start|>' + message.role + '\n' }}
41
+ {%- if message.content is string %}
42
+ {{- message.content }}
43
+ {%- else %}
44
+ {%- for content in message.content %}
45
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
46
+ {%- set image_count.value = image_count.value + 1 %}
47
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
48
+ <|vision_start|><|image_pad|><|vision_end|>
49
+ {%- elif content.type == 'video' or 'video' in content %}
50
+ {%- set video_count.value = video_count.value + 1 %}
51
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
52
+ <|vision_start|><|video_pad|><|vision_end|>
53
+ {%- elif 'text' in content %}
54
+ {{- content.text }}
55
+ {%- endif %}
56
+ {%- endfor %}
57
+ {%- endif %}
58
+ {{- '<|im_end|>\n' }}
59
+ {%- elif message.role == "assistant" %}
60
+ {{- '<|im_start|>' + message.role + '\n' }}
61
+ {%- if message.content is string %}
62
+ {{- message.content }}
63
+ {%- else %}
64
+ {%- for content_item in message.content %}
65
+ {%- if 'text' in content_item %}
66
+ {{- content_item.text }}
67
+ {%- endif %}
68
+ {%- endfor %}
69
+ {%- endif %}
70
+ {%- if message.tool_calls %}
71
+ {%- for tool_call in message.tool_calls %}
72
+ {%- if (loop.first and message.content) or (not loop.first) %}
73
+ {{- '\n' }}
74
+ {%- endif %}
75
+ {%- if tool_call.function %}
76
+ {%- set tool_call = tool_call.function %}
77
+ {%- endif %}
78
+ {{- '<tool_call>\n{"name": "' }}
79
+ {{- tool_call.name }}
80
+ {{- '", "arguments": ' }}
81
+ {%- if tool_call.arguments is string %}
82
+ {{- tool_call.arguments }}
83
+ {%- else %}
84
+ {{- tool_call.arguments | tojson }}
85
+ {%- endif %}
86
+ {{- '}\n</tool_call>' }}
87
+ {%- endfor %}
88
+ {%- endif %}
89
+ {{- '<|im_end|>\n' }}
90
+ {%- elif message.role == "tool" %}
91
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
92
+ {{- '<|im_start|>user' }}
93
+ {%- endif %}
94
+ {{- '\n<tool_response>\n' }}
95
+ {%- if message.content is string %}
96
+ {{- message.content }}
97
+ {%- else %}
98
+ {%- for content in message.content %}
99
+ {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
100
+ {%- set image_count.value = image_count.value + 1 %}
101
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
102
+ <|vision_start|><|image_pad|><|vision_end|>
103
+ {%- elif content.type == 'video' or 'video' in content %}
104
+ {%- set video_count.value = video_count.value + 1 %}
105
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
106
+ <|vision_start|><|video_pad|><|vision_end|>
107
+ {%- elif 'text' in content %}
108
+ {{- content.text }}
109
+ {%- endif %}
110
+ {%- endfor %}
111
+ {%- endif %}
112
+ {{- '\n</tool_response>' }}
113
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
114
+ {{- '<|im_end|>\n' }}
115
+ {%- endif %}
116
+ {%- endif %}
117
+ {%- endfor %}
118
+ {%- if add_generation_prompt %}
119
+ {{- '<|im_start|>assistant\n' }}
120
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLMoeForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "hidden_size": 2048,
7
+ "image_token_id": 151655,
8
+ "model_type": "qwen3_vl_moe",
9
+ "pad_token_id": 151643,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 151643,
14
+ "decoder_sparse_step": 1,
15
+ "dtype": "bfloat16",
16
+ "eos_token_id": 151645,
17
+ "head_dim": 128,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 6144,
22
+ "max_position_embeddings": 262144,
23
+ "mlp_only_layers": [],
24
+ "model_type": "qwen3_vl_moe_text",
25
+ "moe_intermediate_size": 768,
26
+ "norm_topk_prob": true,
27
+ "num_attention_heads": 32,
28
+ "num_experts": 128,
29
+ "num_experts_per_tok": 8,
30
+ "num_hidden_layers": 48,
31
+ "num_key_value_heads": 4,
32
+ "pad_token_id": 151643,
33
+ "rms_norm_eps": 1e-06,
34
+ "rope_scaling": {
35
+ "mrope_interleaved": true,
36
+ "mrope_section": [
37
+ 24,
38
+ 20,
39
+ 20
40
+ ],
41
+ "rope_type": "default"
42
+ },
43
+ "rope_theta": 5000000,
44
+ "router_aux_loss_coef": 0.001,
45
+ "use_cache": true,
46
+ "vocab_size": 151936
47
+ },
48
+ "tie_word_embeddings": false,
49
+ "transformers_version": "4.57.1",
50
+ "video_token_id": 151656,
51
+ "vision_config": {
52
+ "deepstack_visual_indexes": [
53
+ 8,
54
+ 16,
55
+ 24
56
+ ],
57
+ "depth": 27,
58
+ "dtype": "bfloat16",
59
+ "hidden_act": "gelu_pytorch_tanh",
60
+ "hidden_size": 1152,
61
+ "in_channels": 3,
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 4304,
64
+ "model_type": "qwen3_vl_moe",
65
+ "num_heads": 16,
66
+ "num_position_embeddings": 2304,
67
+ "out_hidden_size": 2048,
68
+ "pad_token_id": 151643,
69
+ "patch_size": 16,
70
+ "spatial_merge_size": 2,
71
+ "temporal_patch_size": 2
72
+ },
73
+ "vision_end_token_id": 151653,
74
+ "vision_start_token_id": 151652
75
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.7,
10
+ "top_k": 20,
11
+ "top_p": 0.8,
12
+ "transformers_version": "4.57.1"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f8c6cec5805fd2637ffd6cf0b91d46319ebfd7bd67700e9022d59525b9fa74
3
+ size 4230392720
model-00002-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85779f72563cb3e329d2ec2fadcc476735c7284413de39d3b71d3c616e41cdc9
3
+ size 4984970872
model-00003-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03ee6c2f7138eacb3f6649f677bc72ef6089a1948d1b4924ffa10bc792026669
3
+ size 4984970848
model-00004-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:947a1db5a53a0f84ff4ee363364df0b054ccb70dfa90ef2649ba5776c615690d
3
+ size 4984970912
model-00005-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b6d8c89a819992e9dc9f0682f279866b8c887620603d0ab04f9749b6a8c6eb
3
+ size 4984970912
model-00006-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c97cbce3b33fd5133e8fcd453a8097370960fe1ed0f71b2c51c2df8f29333d
3
+ size 4984970912
model-00007-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269998c00723c6ac7ce831cef800fac5426a82182b742229e8b7b26ca7998b51
3
+ size 4984970912
model-00008-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c259eb0554163421355a9afdd3cea233f29f9fdc3973a4904866d58217a2d14
3
+ size 4984970912
model-00009-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f056f8b1b3348383d4e328f75e17e12392376658f6c43dc6f67a93a2e9a2aef5
3
+ size 4984970912
model-00010-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27a818b7a6cd3a9fd633da49e628b9a3cc378a63d8585a7503a8df72a6e7868
3
+ size 4984970912
model-00011-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2865654fd9ebc0c074a1d693d00b7254ac93dcc348e8c446309472b97ce5fe08
3
+ size 4984970912
model-00012-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6323c8e2faf2fb868f70ed987cc86236a234e7663088e443dbecb39d3fb889
3
+ size 4984970912
model-00013-of-00013.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74253a5496433344da7c4918f77b91402623235d3941f7060d076cdff964e3ac
3
+ size 3076545184
model.safetensors.index.json ADDED
@@ -0,0 +1,890 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 31070754032,
4
+ "total_size": 62141508064
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00013-of-00013.safetensors",
8
+ "model.language_model.embed_tokens.weight": "model-00001-of-00013.safetensors",
9
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
10
+ "model.language_model.layers.0.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
11
+ "model.language_model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
12
+ "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00013.safetensors",
13
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
15
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
16
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
18
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
19
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
20
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
21
+ "model.language_model.layers.1.mlp.experts.down_proj": "model-00001-of-00013.safetensors",
22
+ "model.language_model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00013.safetensors",
23
+ "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00013.safetensors",
24
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
26
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
27
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
29
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
30
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
31
+ "model.language_model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
32
+ "model.language_model.layers.10.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
33
+ "model.language_model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
34
+ "model.language_model.layers.10.mlp.gate.weight": "model-00003-of-00013.safetensors",
35
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
37
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
38
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
40
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
41
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
42
+ "model.language_model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
43
+ "model.language_model.layers.11.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
44
+ "model.language_model.layers.11.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
45
+ "model.language_model.layers.11.mlp.gate.weight": "model-00004-of-00013.safetensors",
46
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
48
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
49
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
51
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
52
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
53
+ "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00013.safetensors",
54
+ "model.language_model.layers.12.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
55
+ "model.language_model.layers.12.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
56
+ "model.language_model.layers.12.mlp.gate.weight": "model-00004-of-00013.safetensors",
57
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
59
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
60
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
62
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
63
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
64
+ "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors",
65
+ "model.language_model.layers.13.mlp.experts.down_proj": "model-00004-of-00013.safetensors",
66
+ "model.language_model.layers.13.mlp.experts.gate_up_proj": "model-00004-of-00013.safetensors",
67
+ "model.language_model.layers.13.mlp.gate.weight": "model-00004-of-00013.safetensors",
68
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
70
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
71
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
73
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
74
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
75
+ "model.language_model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
76
+ "model.language_model.layers.14.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
77
+ "model.language_model.layers.14.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
78
+ "model.language_model.layers.14.mlp.gate.weight": "model-00004-of-00013.safetensors",
79
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
81
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
82
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
84
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
85
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
86
+ "model.language_model.layers.15.input_layernorm.weight": "model-00005-of-00013.safetensors",
87
+ "model.language_model.layers.15.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
88
+ "model.language_model.layers.15.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
89
+ "model.language_model.layers.15.mlp.gate.weight": "model-00005-of-00013.safetensors",
90
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
92
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
93
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
95
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
96
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
97
+ "model.language_model.layers.16.input_layernorm.weight": "model-00005-of-00013.safetensors",
98
+ "model.language_model.layers.16.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
99
+ "model.language_model.layers.16.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
100
+ "model.language_model.layers.16.mlp.gate.weight": "model-00005-of-00013.safetensors",
101
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
103
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
104
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
106
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
107
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
108
+ "model.language_model.layers.17.input_layernorm.weight": "model-00005-of-00013.safetensors",
109
+ "model.language_model.layers.17.mlp.experts.down_proj": "model-00005-of-00013.safetensors",
110
+ "model.language_model.layers.17.mlp.experts.gate_up_proj": "model-00005-of-00013.safetensors",
111
+ "model.language_model.layers.17.mlp.gate.weight": "model-00005-of-00013.safetensors",
112
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
114
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
115
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
117
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
118
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
119
+ "model.language_model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
120
+ "model.language_model.layers.18.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
121
+ "model.language_model.layers.18.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
122
+ "model.language_model.layers.18.mlp.gate.weight": "model-00005-of-00013.safetensors",
123
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
125
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
126
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
128
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
129
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
130
+ "model.language_model.layers.19.input_layernorm.weight": "model-00006-of-00013.safetensors",
131
+ "model.language_model.layers.19.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
132
+ "model.language_model.layers.19.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
133
+ "model.language_model.layers.19.mlp.gate.weight": "model-00006-of-00013.safetensors",
134
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
136
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
137
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
139
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
140
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
141
+ "model.language_model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
142
+ "model.language_model.layers.2.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
143
+ "model.language_model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
144
+ "model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00013.safetensors",
145
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
147
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
148
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
150
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
151
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
152
+ "model.language_model.layers.20.input_layernorm.weight": "model-00006-of-00013.safetensors",
153
+ "model.language_model.layers.20.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
154
+ "model.language_model.layers.20.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
155
+ "model.language_model.layers.20.mlp.gate.weight": "model-00006-of-00013.safetensors",
156
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
158
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
159
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
161
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
162
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
163
+ "model.language_model.layers.21.input_layernorm.weight": "model-00006-of-00013.safetensors",
164
+ "model.language_model.layers.21.mlp.experts.down_proj": "model-00006-of-00013.safetensors",
165
+ "model.language_model.layers.21.mlp.experts.gate_up_proj": "model-00006-of-00013.safetensors",
166
+ "model.language_model.layers.21.mlp.gate.weight": "model-00006-of-00013.safetensors",
167
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
169
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
170
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
172
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
173
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
174
+ "model.language_model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
175
+ "model.language_model.layers.22.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
176
+ "model.language_model.layers.22.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
177
+ "model.language_model.layers.22.mlp.gate.weight": "model-00006-of-00013.safetensors",
178
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
180
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
181
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
183
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
184
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
185
+ "model.language_model.layers.23.input_layernorm.weight": "model-00007-of-00013.safetensors",
186
+ "model.language_model.layers.23.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
187
+ "model.language_model.layers.23.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
188
+ "model.language_model.layers.23.mlp.gate.weight": "model-00007-of-00013.safetensors",
189
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
191
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
192
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
194
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
195
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
196
+ "model.language_model.layers.24.input_layernorm.weight": "model-00007-of-00013.safetensors",
197
+ "model.language_model.layers.24.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
198
+ "model.language_model.layers.24.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
199
+ "model.language_model.layers.24.mlp.gate.weight": "model-00007-of-00013.safetensors",
200
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
202
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
203
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
205
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
206
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
207
+ "model.language_model.layers.25.input_layernorm.weight": "model-00007-of-00013.safetensors",
208
+ "model.language_model.layers.25.mlp.experts.down_proj": "model-00007-of-00013.safetensors",
209
+ "model.language_model.layers.25.mlp.experts.gate_up_proj": "model-00007-of-00013.safetensors",
210
+ "model.language_model.layers.25.mlp.gate.weight": "model-00007-of-00013.safetensors",
211
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
213
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
214
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
216
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
217
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
218
+ "model.language_model.layers.26.input_layernorm.weight": "model-00008-of-00013.safetensors",
219
+ "model.language_model.layers.26.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
220
+ "model.language_model.layers.26.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
221
+ "model.language_model.layers.26.mlp.gate.weight": "model-00007-of-00013.safetensors",
222
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
224
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
225
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
227
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
228
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
229
+ "model.language_model.layers.27.input_layernorm.weight": "model-00008-of-00013.safetensors",
230
+ "model.language_model.layers.27.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
231
+ "model.language_model.layers.27.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
232
+ "model.language_model.layers.27.mlp.gate.weight": "model-00008-of-00013.safetensors",
233
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
235
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
236
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
238
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
239
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
240
+ "model.language_model.layers.28.input_layernorm.weight": "model-00008-of-00013.safetensors",
241
+ "model.language_model.layers.28.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
242
+ "model.language_model.layers.28.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
243
+ "model.language_model.layers.28.mlp.gate.weight": "model-00008-of-00013.safetensors",
244
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
246
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
247
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
249
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
250
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
251
+ "model.language_model.layers.29.input_layernorm.weight": "model-00008-of-00013.safetensors",
252
+ "model.language_model.layers.29.mlp.experts.down_proj": "model-00008-of-00013.safetensors",
253
+ "model.language_model.layers.29.mlp.experts.gate_up_proj": "model-00008-of-00013.safetensors",
254
+ "model.language_model.layers.29.mlp.gate.weight": "model-00008-of-00013.safetensors",
255
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
257
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
258
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
260
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
261
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
262
+ "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
263
+ "model.language_model.layers.3.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
264
+ "model.language_model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
265
+ "model.language_model.layers.3.mlp.gate.weight": "model-00002-of-00013.safetensors",
266
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
268
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
269
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
271
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
272
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
273
+ "model.language_model.layers.30.input_layernorm.weight": "model-00009-of-00013.safetensors",
274
+ "model.language_model.layers.30.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
275
+ "model.language_model.layers.30.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
276
+ "model.language_model.layers.30.mlp.gate.weight": "model-00008-of-00013.safetensors",
277
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
279
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
280
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
282
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
283
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
284
+ "model.language_model.layers.31.input_layernorm.weight": "model-00009-of-00013.safetensors",
285
+ "model.language_model.layers.31.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
286
+ "model.language_model.layers.31.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
287
+ "model.language_model.layers.31.mlp.gate.weight": "model-00009-of-00013.safetensors",
288
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
290
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
291
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
293
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
294
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
295
+ "model.language_model.layers.32.input_layernorm.weight": "model-00009-of-00013.safetensors",
296
+ "model.language_model.layers.32.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
297
+ "model.language_model.layers.32.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
298
+ "model.language_model.layers.32.mlp.gate.weight": "model-00009-of-00013.safetensors",
299
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
301
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
302
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
304
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
305
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
306
+ "model.language_model.layers.33.input_layernorm.weight": "model-00009-of-00013.safetensors",
307
+ "model.language_model.layers.33.mlp.experts.down_proj": "model-00009-of-00013.safetensors",
308
+ "model.language_model.layers.33.mlp.experts.gate_up_proj": "model-00009-of-00013.safetensors",
309
+ "model.language_model.layers.33.mlp.gate.weight": "model-00009-of-00013.safetensors",
310
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
312
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
313
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
315
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
316
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
317
+ "model.language_model.layers.34.input_layernorm.weight": "model-00010-of-00013.safetensors",
318
+ "model.language_model.layers.34.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
319
+ "model.language_model.layers.34.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
320
+ "model.language_model.layers.34.mlp.gate.weight": "model-00009-of-00013.safetensors",
321
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
323
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
324
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
326
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
327
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
328
+ "model.language_model.layers.35.input_layernorm.weight": "model-00010-of-00013.safetensors",
329
+ "model.language_model.layers.35.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
330
+ "model.language_model.layers.35.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
331
+ "model.language_model.layers.35.mlp.gate.weight": "model-00010-of-00013.safetensors",
332
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
334
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
335
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
337
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
338
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
339
+ "model.language_model.layers.36.input_layernorm.weight": "model-00010-of-00013.safetensors",
340
+ "model.language_model.layers.36.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
341
+ "model.language_model.layers.36.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
342
+ "model.language_model.layers.36.mlp.gate.weight": "model-00010-of-00013.safetensors",
343
+ "model.language_model.layers.36.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
344
+ "model.language_model.layers.36.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
345
+ "model.language_model.layers.36.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
346
+ "model.language_model.layers.36.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
347
+ "model.language_model.layers.36.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
348
+ "model.language_model.layers.36.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
349
+ "model.language_model.layers.36.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
350
+ "model.language_model.layers.37.input_layernorm.weight": "model-00010-of-00013.safetensors",
351
+ "model.language_model.layers.37.mlp.experts.down_proj": "model-00010-of-00013.safetensors",
352
+ "model.language_model.layers.37.mlp.experts.gate_up_proj": "model-00010-of-00013.safetensors",
353
+ "model.language_model.layers.37.mlp.gate.weight": "model-00010-of-00013.safetensors",
354
+ "model.language_model.layers.37.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
355
+ "model.language_model.layers.37.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
356
+ "model.language_model.layers.37.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
357
+ "model.language_model.layers.37.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
358
+ "model.language_model.layers.37.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
359
+ "model.language_model.layers.37.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
360
+ "model.language_model.layers.37.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
361
+ "model.language_model.layers.38.input_layernorm.weight": "model-00011-of-00013.safetensors",
362
+ "model.language_model.layers.38.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
363
+ "model.language_model.layers.38.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
364
+ "model.language_model.layers.38.mlp.gate.weight": "model-00010-of-00013.safetensors",
365
+ "model.language_model.layers.38.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
366
+ "model.language_model.layers.38.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
367
+ "model.language_model.layers.38.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
368
+ "model.language_model.layers.38.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
369
+ "model.language_model.layers.38.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
370
+ "model.language_model.layers.38.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
371
+ "model.language_model.layers.38.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
372
+ "model.language_model.layers.39.input_layernorm.weight": "model-00011-of-00013.safetensors",
373
+ "model.language_model.layers.39.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
374
+ "model.language_model.layers.39.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
375
+ "model.language_model.layers.39.mlp.gate.weight": "model-00011-of-00013.safetensors",
376
+ "model.language_model.layers.39.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
377
+ "model.language_model.layers.39.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
378
+ "model.language_model.layers.39.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
379
+ "model.language_model.layers.39.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
380
+ "model.language_model.layers.39.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
381
+ "model.language_model.layers.39.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
382
+ "model.language_model.layers.39.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
383
+ "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
384
+ "model.language_model.layers.4.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
385
+ "model.language_model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
386
+ "model.language_model.layers.4.mlp.gate.weight": "model-00002-of-00013.safetensors",
387
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
388
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
389
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
390
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
391
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
392
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
393
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
394
+ "model.language_model.layers.40.input_layernorm.weight": "model-00011-of-00013.safetensors",
395
+ "model.language_model.layers.40.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
396
+ "model.language_model.layers.40.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
397
+ "model.language_model.layers.40.mlp.gate.weight": "model-00011-of-00013.safetensors",
398
+ "model.language_model.layers.40.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
399
+ "model.language_model.layers.40.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
400
+ "model.language_model.layers.40.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
401
+ "model.language_model.layers.40.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
402
+ "model.language_model.layers.40.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
403
+ "model.language_model.layers.40.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
404
+ "model.language_model.layers.40.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
405
+ "model.language_model.layers.41.input_layernorm.weight": "model-00011-of-00013.safetensors",
406
+ "model.language_model.layers.41.mlp.experts.down_proj": "model-00011-of-00013.safetensors",
407
+ "model.language_model.layers.41.mlp.experts.gate_up_proj": "model-00011-of-00013.safetensors",
408
+ "model.language_model.layers.41.mlp.gate.weight": "model-00011-of-00013.safetensors",
409
+ "model.language_model.layers.41.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
410
+ "model.language_model.layers.41.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
411
+ "model.language_model.layers.41.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
412
+ "model.language_model.layers.41.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
413
+ "model.language_model.layers.41.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
414
+ "model.language_model.layers.41.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
415
+ "model.language_model.layers.41.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
416
+ "model.language_model.layers.42.input_layernorm.weight": "model-00012-of-00013.safetensors",
417
+ "model.language_model.layers.42.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
418
+ "model.language_model.layers.42.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
419
+ "model.language_model.layers.42.mlp.gate.weight": "model-00011-of-00013.safetensors",
420
+ "model.language_model.layers.42.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
421
+ "model.language_model.layers.42.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
422
+ "model.language_model.layers.42.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
423
+ "model.language_model.layers.42.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
424
+ "model.language_model.layers.42.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
425
+ "model.language_model.layers.42.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
426
+ "model.language_model.layers.42.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
427
+ "model.language_model.layers.43.input_layernorm.weight": "model-00012-of-00013.safetensors",
428
+ "model.language_model.layers.43.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
429
+ "model.language_model.layers.43.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
430
+ "model.language_model.layers.43.mlp.gate.weight": "model-00012-of-00013.safetensors",
431
+ "model.language_model.layers.43.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
432
+ "model.language_model.layers.43.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
433
+ "model.language_model.layers.43.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
434
+ "model.language_model.layers.43.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
435
+ "model.language_model.layers.43.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
436
+ "model.language_model.layers.43.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
437
+ "model.language_model.layers.43.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
438
+ "model.language_model.layers.44.input_layernorm.weight": "model-00012-of-00013.safetensors",
439
+ "model.language_model.layers.44.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
440
+ "model.language_model.layers.44.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
441
+ "model.language_model.layers.44.mlp.gate.weight": "model-00012-of-00013.safetensors",
442
+ "model.language_model.layers.44.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
443
+ "model.language_model.layers.44.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
444
+ "model.language_model.layers.44.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
445
+ "model.language_model.layers.44.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
446
+ "model.language_model.layers.44.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
447
+ "model.language_model.layers.44.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
448
+ "model.language_model.layers.44.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
449
+ "model.language_model.layers.45.input_layernorm.weight": "model-00012-of-00013.safetensors",
450
+ "model.language_model.layers.45.mlp.experts.down_proj": "model-00012-of-00013.safetensors",
451
+ "model.language_model.layers.45.mlp.experts.gate_up_proj": "model-00012-of-00013.safetensors",
452
+ "model.language_model.layers.45.mlp.gate.weight": "model-00012-of-00013.safetensors",
453
+ "model.language_model.layers.45.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
454
+ "model.language_model.layers.45.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
455
+ "model.language_model.layers.45.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
456
+ "model.language_model.layers.45.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
457
+ "model.language_model.layers.45.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
458
+ "model.language_model.layers.45.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
459
+ "model.language_model.layers.45.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
460
+ "model.language_model.layers.46.input_layernorm.weight": "model-00013-of-00013.safetensors",
461
+ "model.language_model.layers.46.mlp.experts.down_proj": "model-00013-of-00013.safetensors",
462
+ "model.language_model.layers.46.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors",
463
+ "model.language_model.layers.46.mlp.gate.weight": "model-00012-of-00013.safetensors",
464
+ "model.language_model.layers.46.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
465
+ "model.language_model.layers.46.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
466
+ "model.language_model.layers.46.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
467
+ "model.language_model.layers.46.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
468
+ "model.language_model.layers.46.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
469
+ "model.language_model.layers.46.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
470
+ "model.language_model.layers.46.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
471
+ "model.language_model.layers.47.input_layernorm.weight": "model-00013-of-00013.safetensors",
472
+ "model.language_model.layers.47.mlp.experts.down_proj": "model-00013-of-00013.safetensors",
473
+ "model.language_model.layers.47.mlp.experts.gate_up_proj": "model-00013-of-00013.safetensors",
474
+ "model.language_model.layers.47.mlp.gate.weight": "model-00013-of-00013.safetensors",
475
+ "model.language_model.layers.47.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
476
+ "model.language_model.layers.47.self_attn.k_norm.weight": "model-00013-of-00013.safetensors",
477
+ "model.language_model.layers.47.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
478
+ "model.language_model.layers.47.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
479
+ "model.language_model.layers.47.self_attn.q_norm.weight": "model-00013-of-00013.safetensors",
480
+ "model.language_model.layers.47.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
481
+ "model.language_model.layers.47.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
482
+ "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
483
+ "model.language_model.layers.5.mlp.experts.down_proj": "model-00002-of-00013.safetensors",
484
+ "model.language_model.layers.5.mlp.experts.gate_up_proj": "model-00002-of-00013.safetensors",
485
+ "model.language_model.layers.5.mlp.gate.weight": "model-00002-of-00013.safetensors",
486
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
487
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
488
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
489
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
490
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
491
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
492
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
493
+ "model.language_model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
494
+ "model.language_model.layers.6.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
495
+ "model.language_model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
496
+ "model.language_model.layers.6.mlp.gate.weight": "model-00002-of-00013.safetensors",
497
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
498
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
499
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
500
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
501
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
502
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
503
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
504
+ "model.language_model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
505
+ "model.language_model.layers.7.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
506
+ "model.language_model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
507
+ "model.language_model.layers.7.mlp.gate.weight": "model-00003-of-00013.safetensors",
508
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
509
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
510
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
511
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
512
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
513
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
514
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
515
+ "model.language_model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
516
+ "model.language_model.layers.8.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
517
+ "model.language_model.layers.8.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
518
+ "model.language_model.layers.8.mlp.gate.weight": "model-00003-of-00013.safetensors",
519
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
520
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
521
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
522
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
523
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
524
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
525
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
526
+ "model.language_model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
527
+ "model.language_model.layers.9.mlp.experts.down_proj": "model-00003-of-00013.safetensors",
528
+ "model.language_model.layers.9.mlp.experts.gate_up_proj": "model-00003-of-00013.safetensors",
529
+ "model.language_model.layers.9.mlp.gate.weight": "model-00003-of-00013.safetensors",
530
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
531
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
532
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
533
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
534
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
535
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
536
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
537
+ "model.language_model.norm.weight": "model-00013-of-00013.safetensors",
538
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00013.safetensors",
539
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00013.safetensors",
540
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00013.safetensors",
541
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00013.safetensors",
542
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
543
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
544
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
545
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
546
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00013.safetensors",
547
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00013.safetensors",
548
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00013.safetensors",
549
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00013.safetensors",
550
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00013.safetensors",
551
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00013.safetensors",
552
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00013.safetensors",
553
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00013.safetensors",
554
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
555
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
556
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
557
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
558
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00013.safetensors",
559
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00013.safetensors",
560
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00013.safetensors",
561
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00013.safetensors",
562
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00013.safetensors",
563
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00013.safetensors",
564
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00013.safetensors",
565
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00013.safetensors",
566
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
567
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
568
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
569
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
570
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00013.safetensors",
571
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00013.safetensors",
572
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00013.safetensors",
573
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00013.safetensors",
574
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00013.safetensors",
575
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00013.safetensors",
576
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00013.safetensors",
577
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00013.safetensors",
578
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
579
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
580
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
581
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
582
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00013.safetensors",
583
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00013.safetensors",
584
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00013.safetensors",
585
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00013.safetensors",
586
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00013.safetensors",
587
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00013.safetensors",
588
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00013.safetensors",
589
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00013.safetensors",
590
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
591
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
592
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
593
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
594
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00013.safetensors",
595
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00013.safetensors",
596
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00013.safetensors",
597
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00013.safetensors",
598
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00013.safetensors",
599
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00013.safetensors",
600
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00013.safetensors",
601
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00013.safetensors",
602
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
603
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
604
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
605
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
606
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00013.safetensors",
607
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00013.safetensors",
608
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00013.safetensors",
609
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00013.safetensors",
610
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00013.safetensors",
611
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00013.safetensors",
612
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00013.safetensors",
613
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00013.safetensors",
614
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
615
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
616
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
617
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
618
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00013.safetensors",
619
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00013.safetensors",
620
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00013.safetensors",
621
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00013.safetensors",
622
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00013.safetensors",
623
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00013.safetensors",
624
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00013.safetensors",
625
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00013.safetensors",
626
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
627
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
628
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
629
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
630
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00013.safetensors",
631
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00013.safetensors",
632
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00013.safetensors",
633
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00013.safetensors",
634
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00013.safetensors",
635
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00013.safetensors",
636
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00013.safetensors",
637
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00013.safetensors",
638
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
639
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
640
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
641
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
642
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00013.safetensors",
643
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00013.safetensors",
644
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00013.safetensors",
645
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00013.safetensors",
646
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00013.safetensors",
647
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00013.safetensors",
648
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00013.safetensors",
649
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00013.safetensors",
650
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
651
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
652
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
653
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
654
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00013.safetensors",
655
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00013.safetensors",
656
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00013.safetensors",
657
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00013.safetensors",
658
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00013.safetensors",
659
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00013.safetensors",
660
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00013.safetensors",
661
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00013.safetensors",
662
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
663
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
664
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
665
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
666
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00013.safetensors",
667
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00013.safetensors",
668
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00013.safetensors",
669
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00013.safetensors",
670
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00013.safetensors",
671
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00013.safetensors",
672
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00013.safetensors",
673
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00013.safetensors",
674
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
675
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
676
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
677
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
678
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00013.safetensors",
679
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00013.safetensors",
680
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00013.safetensors",
681
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00013.safetensors",
682
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00013.safetensors",
683
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00013.safetensors",
684
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00013.safetensors",
685
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00013.safetensors",
686
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
687
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
688
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
689
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
690
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00013.safetensors",
691
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00013.safetensors",
692
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00013.safetensors",
693
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00013.safetensors",
694
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00013.safetensors",
695
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00013.safetensors",
696
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00013.safetensors",
697
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00013.safetensors",
698
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
699
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
700
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
701
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
702
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00013.safetensors",
703
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00013.safetensors",
704
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00013.safetensors",
705
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00013.safetensors",
706
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00013.safetensors",
707
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00013.safetensors",
708
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00013.safetensors",
709
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00013.safetensors",
710
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
711
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
712
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
713
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
714
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00013.safetensors",
715
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00013.safetensors",
716
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00013.safetensors",
717
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00013.safetensors",
718
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00013.safetensors",
719
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00013.safetensors",
720
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00013.safetensors",
721
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00013.safetensors",
722
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
723
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
724
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
725
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
726
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00013.safetensors",
727
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00013.safetensors",
728
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00013.safetensors",
729
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00013.safetensors",
730
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00013.safetensors",
731
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00013.safetensors",
732
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00013.safetensors",
733
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00013.safetensors",
734
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
735
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
736
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
737
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
738
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00013.safetensors",
739
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00013.safetensors",
740
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00013.safetensors",
741
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00013.safetensors",
742
+ "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00013.safetensors",
743
+ "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00013.safetensors",
744
+ "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00013.safetensors",
745
+ "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00013.safetensors",
746
+ "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
747
+ "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
748
+ "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
749
+ "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
750
+ "model.visual.blocks.24.norm1.bias": "model-00001-of-00013.safetensors",
751
+ "model.visual.blocks.24.norm1.weight": "model-00001-of-00013.safetensors",
752
+ "model.visual.blocks.24.norm2.bias": "model-00001-of-00013.safetensors",
753
+ "model.visual.blocks.24.norm2.weight": "model-00001-of-00013.safetensors",
754
+ "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00013.safetensors",
755
+ "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00013.safetensors",
756
+ "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00013.safetensors",
757
+ "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00013.safetensors",
758
+ "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
759
+ "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
760
+ "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
761
+ "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
762
+ "model.visual.blocks.25.norm1.bias": "model-00001-of-00013.safetensors",
763
+ "model.visual.blocks.25.norm1.weight": "model-00001-of-00013.safetensors",
764
+ "model.visual.blocks.25.norm2.bias": "model-00001-of-00013.safetensors",
765
+ "model.visual.blocks.25.norm2.weight": "model-00001-of-00013.safetensors",
766
+ "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00013.safetensors",
767
+ "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00013.safetensors",
768
+ "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00013.safetensors",
769
+ "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00013.safetensors",
770
+ "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
771
+ "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
772
+ "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
773
+ "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
774
+ "model.visual.blocks.26.norm1.bias": "model-00001-of-00013.safetensors",
775
+ "model.visual.blocks.26.norm1.weight": "model-00001-of-00013.safetensors",
776
+ "model.visual.blocks.26.norm2.bias": "model-00001-of-00013.safetensors",
777
+ "model.visual.blocks.26.norm2.weight": "model-00001-of-00013.safetensors",
778
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00013.safetensors",
779
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00013.safetensors",
780
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00013.safetensors",
781
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00013.safetensors",
782
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
783
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
784
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
785
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
786
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00013.safetensors",
787
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00013.safetensors",
788
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00013.safetensors",
789
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00013.safetensors",
790
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00013.safetensors",
791
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00013.safetensors",
792
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00013.safetensors",
793
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00013.safetensors",
794
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
795
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
796
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
797
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
798
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00013.safetensors",
799
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00013.safetensors",
800
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00013.safetensors",
801
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00013.safetensors",
802
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00013.safetensors",
803
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00013.safetensors",
804
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00013.safetensors",
805
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00013.safetensors",
806
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
807
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
808
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
809
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
810
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00013.safetensors",
811
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00013.safetensors",
812
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00013.safetensors",
813
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00013.safetensors",
814
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00013.safetensors",
815
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00013.safetensors",
816
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00013.safetensors",
817
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00013.safetensors",
818
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
819
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
820
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
821
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
822
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00013.safetensors",
823
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00013.safetensors",
824
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00013.safetensors",
825
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00013.safetensors",
826
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00013.safetensors",
827
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00013.safetensors",
828
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00013.safetensors",
829
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00013.safetensors",
830
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
831
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
832
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
833
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
834
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00013.safetensors",
835
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00013.safetensors",
836
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00013.safetensors",
837
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00013.safetensors",
838
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00013.safetensors",
839
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00013.safetensors",
840
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00013.safetensors",
841
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00013.safetensors",
842
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
843
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
844
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
845
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
846
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00013.safetensors",
847
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00013.safetensors",
848
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00013.safetensors",
849
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00013.safetensors",
850
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00013.safetensors",
851
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00013.safetensors",
852
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00013.safetensors",
853
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00013.safetensors",
854
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00013.safetensors",
855
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00013.safetensors",
856
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00013.safetensors",
857
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00013.safetensors",
858
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00013.safetensors",
859
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00013.safetensors",
860
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00013.safetensors",
861
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00013.safetensors",
862
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00013.safetensors",
863
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00013.safetensors",
864
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00013.safetensors",
865
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00013.safetensors",
866
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00013.safetensors",
867
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00013.safetensors",
868
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00013.safetensors",
869
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00013.safetensors",
870
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00013.safetensors",
871
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00013.safetensors",
872
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00013.safetensors",
873
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00013.safetensors",
874
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00013.safetensors",
875
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00013.safetensors",
876
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00013.safetensors",
877
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00013.safetensors",
878
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00013.safetensors",
879
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00013.safetensors",
880
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00013.safetensors",
881
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00013.safetensors",
882
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00013.safetensors",
883
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00013.safetensors",
884
+ "model.visual.merger.norm.bias": "model-00001-of-00013.safetensors",
885
+ "model.visual.merger.norm.weight": "model-00001-of-00013.safetensors",
886
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00013.safetensors",
887
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00013.safetensors",
888
+ "model.visual.pos_embed.weight": "model-00001-of-00013.safetensors"
889
+ }
890
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 262144,
235
+ "pad_token": "<|endoftext|>",
236
+ "processor_class": "Qwen3VLProcessor",
237
+ "split_special_tokens": false,
238
+ "tokenizer_class": "Qwen2Tokenizer",
239
+ "unk_token": null
240
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": true,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff