Delete qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000
Browse files- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/added_tokens.json +0 -28
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/args.json +0 -392
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/chat_template.jinja +0 -120
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/config.json +0 -70
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/generation_config.json +0 -13
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/latest +0 -1
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/merges.txt +0 -0
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model-00001-of-00002.safetensors +0 -3
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model-00002-of-00002.safetensors +0 -3
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model.safetensors.index.json +0 -722
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/preprocessor_config.json +0 -21
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/special_tokens_map.json +0 -31
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer.json +0 -3
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer_config.json +0 -240
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/trainer_state.json +0 -0
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/training_args.bin +0 -3
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/video_preprocessor_config.json +0 -41
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/vocab.json +0 -0
- qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/zero_to_fp32.py +0 -760
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/added_tokens.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/args.json
DELETED
|
@@ -1,392 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"output_dir": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453",
|
| 3 |
-
"overwrite_output_dir": false,
|
| 4 |
-
"do_train": false,
|
| 5 |
-
"do_eval": false,
|
| 6 |
-
"do_predict": false,
|
| 7 |
-
"eval_strategy": "no",
|
| 8 |
-
"prediction_loss_only": false,
|
| 9 |
-
"per_device_train_batch_size": 4,
|
| 10 |
-
"per_device_eval_batch_size": 1,
|
| 11 |
-
"per_gpu_train_batch_size": null,
|
| 12 |
-
"per_gpu_eval_batch_size": null,
|
| 13 |
-
"gradient_accumulation_steps": 1,
|
| 14 |
-
"eval_accumulation_steps": null,
|
| 15 |
-
"eval_delay": 0,
|
| 16 |
-
"torch_empty_cache_steps": null,
|
| 17 |
-
"learning_rate": 2e-05,
|
| 18 |
-
"weight_decay": 0.1,
|
| 19 |
-
"adam_beta1": 0.9,
|
| 20 |
-
"adam_beta2": 0.95,
|
| 21 |
-
"adam_epsilon": 1e-08,
|
| 22 |
-
"max_grad_norm": 1.0,
|
| 23 |
-
"num_train_epochs": 1.0,
|
| 24 |
-
"max_steps": -1,
|
| 25 |
-
"lr_scheduler_type": "cosine",
|
| 26 |
-
"lr_scheduler_kwargs": null,
|
| 27 |
-
"warmup_ratio": 0.05,
|
| 28 |
-
"warmup_steps": 0,
|
| 29 |
-
"log_level": "passive",
|
| 30 |
-
"log_level_replica": "warning",
|
| 31 |
-
"log_on_each_node": true,
|
| 32 |
-
"logging_dir": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453/runs",
|
| 33 |
-
"logging_strategy": "steps",
|
| 34 |
-
"logging_first_step": true,
|
| 35 |
-
"logging_steps": 1,
|
| 36 |
-
"logging_nan_inf_filter": true,
|
| 37 |
-
"save_strategy": "steps",
|
| 38 |
-
"save_steps": 500.0,
|
| 39 |
-
"save_total_limit": null,
|
| 40 |
-
"save_safetensors": true,
|
| 41 |
-
"save_on_each_node": false,
|
| 42 |
-
"save_only_model": false,
|
| 43 |
-
"restore_callback_states_from_checkpoint": false,
|
| 44 |
-
"no_cuda": false,
|
| 45 |
-
"use_cpu": false,
|
| 46 |
-
"use_mps_device": false,
|
| 47 |
-
"seed": 42,
|
| 48 |
-
"data_seed": 42,
|
| 49 |
-
"jit_mode_eval": false,
|
| 50 |
-
"bf16": true,
|
| 51 |
-
"fp16": false,
|
| 52 |
-
"fp16_opt_level": "O1",
|
| 53 |
-
"half_precision_backend": "auto",
|
| 54 |
-
"bf16_full_eval": false,
|
| 55 |
-
"fp16_full_eval": false,
|
| 56 |
-
"tf32": null,
|
| 57 |
-
"local_rank": 0,
|
| 58 |
-
"ddp_backend": null,
|
| 59 |
-
"tpu_num_cores": null,
|
| 60 |
-
"tpu_metrics_debug": false,
|
| 61 |
-
"debug": null,
|
| 62 |
-
"dataloader_drop_last": false,
|
| 63 |
-
"eval_steps": 10000.0,
|
| 64 |
-
"dataloader_num_workers": 8,
|
| 65 |
-
"dataloader_prefetch_factor": null,
|
| 66 |
-
"past_index": -1,
|
| 67 |
-
"run_name": "/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453",
|
| 68 |
-
"disable_tqdm": null,
|
| 69 |
-
"remove_unused_columns": true,
|
| 70 |
-
"label_names": null,
|
| 71 |
-
"load_best_model_at_end": false,
|
| 72 |
-
"metric_for_best_model": "loss",
|
| 73 |
-
"greater_is_better": false,
|
| 74 |
-
"ignore_data_skip": false,
|
| 75 |
-
"fsdp": [],
|
| 76 |
-
"fsdp_min_num_params": 0,
|
| 77 |
-
"fsdp_config": null,
|
| 78 |
-
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
-
"accelerator_config": {
|
| 80 |
-
"dispatch_batches": false
|
| 81 |
-
},
|
| 82 |
-
"parallelism_config": null,
|
| 83 |
-
"deepspeed": {
|
| 84 |
-
"fp16": {
|
| 85 |
-
"enabled": "auto",
|
| 86 |
-
"loss_scale": 0,
|
| 87 |
-
"loss_scale_window": 1000,
|
| 88 |
-
"initial_scale_power": 16,
|
| 89 |
-
"hysteresis": 2,
|
| 90 |
-
"min_loss_scale": 1
|
| 91 |
-
},
|
| 92 |
-
"bf16": {
|
| 93 |
-
"enabled": "auto"
|
| 94 |
-
},
|
| 95 |
-
"zero_optimization": {
|
| 96 |
-
"stage": 1,
|
| 97 |
-
"offload_optimizer": {
|
| 98 |
-
"device": "none",
|
| 99 |
-
"pin_memory": true
|
| 100 |
-
},
|
| 101 |
-
"allgather_partitions": true,
|
| 102 |
-
"allgather_bucket_size": 200000000.0,
|
| 103 |
-
"overlap_comm": false,
|
| 104 |
-
"reduce_scatter": true,
|
| 105 |
-
"reduce_bucket_size": 200000000.0,
|
| 106 |
-
"contiguous_gradients": true
|
| 107 |
-
},
|
| 108 |
-
"gradient_accumulation_steps": "auto",
|
| 109 |
-
"gradient_clipping": "auto",
|
| 110 |
-
"steps_per_print": 2000,
|
| 111 |
-
"train_batch_size": "auto",
|
| 112 |
-
"train_micro_batch_size_per_gpu": "auto",
|
| 113 |
-
"wall_clock_breakdown": false
|
| 114 |
-
},
|
| 115 |
-
"label_smoothing_factor": 0.0,
|
| 116 |
-
"optim": "adamw_torch_fused",
|
| 117 |
-
"optim_args": null,
|
| 118 |
-
"adafactor": false,
|
| 119 |
-
"group_by_length": false,
|
| 120 |
-
"length_column_name": "length",
|
| 121 |
-
"report_to": [
|
| 122 |
-
"wandb"
|
| 123 |
-
],
|
| 124 |
-
"project": "huggingface",
|
| 125 |
-
"trackio_space_id": "trackio",
|
| 126 |
-
"ddp_find_unused_parameters": null,
|
| 127 |
-
"ddp_bucket_cap_mb": null,
|
| 128 |
-
"ddp_broadcast_buffers": null,
|
| 129 |
-
"dataloader_pin_memory": true,
|
| 130 |
-
"dataloader_persistent_workers": false,
|
| 131 |
-
"skip_memory_metrics": true,
|
| 132 |
-
"use_legacy_prediction_loop": false,
|
| 133 |
-
"push_to_hub": false,
|
| 134 |
-
"resume_from_checkpoint": null,
|
| 135 |
-
"hub_model_id": null,
|
| 136 |
-
"hub_strategy": "every_save",
|
| 137 |
-
"hub_token": null,
|
| 138 |
-
"hub_private_repo": null,
|
| 139 |
-
"hub_always_push": false,
|
| 140 |
-
"hub_revision": null,
|
| 141 |
-
"gradient_checkpointing": true,
|
| 142 |
-
"gradient_checkpointing_kwargs": null,
|
| 143 |
-
"include_inputs_for_metrics": false,
|
| 144 |
-
"include_for_metrics": [],
|
| 145 |
-
"eval_do_concat_batches": true,
|
| 146 |
-
"fp16_backend": "auto",
|
| 147 |
-
"push_to_hub_model_id": null,
|
| 148 |
-
"push_to_hub_organization": null,
|
| 149 |
-
"push_to_hub_token": null,
|
| 150 |
-
"mp_parameters": "",
|
| 151 |
-
"auto_find_batch_size": false,
|
| 152 |
-
"full_determinism": false,
|
| 153 |
-
"torchdynamo": null,
|
| 154 |
-
"ray_scope": "last",
|
| 155 |
-
"ddp_timeout": 18000000,
|
| 156 |
-
"torch_compile": false,
|
| 157 |
-
"torch_compile_backend": null,
|
| 158 |
-
"torch_compile_mode": null,
|
| 159 |
-
"include_tokens_per_second": false,
|
| 160 |
-
"include_num_input_tokens_seen": false,
|
| 161 |
-
"neftune_noise_alpha": null,
|
| 162 |
-
"optim_target_modules": null,
|
| 163 |
-
"batch_eval_metrics": false,
|
| 164 |
-
"eval_on_start": false,
|
| 165 |
-
"use_liger_kernel": true,
|
| 166 |
-
"liger_kernel_config": null,
|
| 167 |
-
"eval_use_gather_object": false,
|
| 168 |
-
"average_tokens_across_devices": true,
|
| 169 |
-
"sortish_sampler": false,
|
| 170 |
-
"predict_with_generate": false,
|
| 171 |
-
"generation_max_length": null,
|
| 172 |
-
"generation_num_beams": null,
|
| 173 |
-
"generation_config": null,
|
| 174 |
-
"tuner_backend": "peft",
|
| 175 |
-
"vit_gradient_checkpointing": null,
|
| 176 |
-
"router_aux_loss_coef": 0.0,
|
| 177 |
-
"enable_dft_loss": false,
|
| 178 |
-
"enable_channel_loss": false,
|
| 179 |
-
"check_model": true,
|
| 180 |
-
"acc_strategy": "token",
|
| 181 |
-
"train_dataloader_shuffle": true,
|
| 182 |
-
"max_epochs": null,
|
| 183 |
-
"aligner_lr": 1e-05,
|
| 184 |
-
"vit_lr": 1e-05,
|
| 185 |
-
"use_logits_to_keep": null,
|
| 186 |
-
"ds3_gather_for_generation": true,
|
| 187 |
-
"resume_only_model": false,
|
| 188 |
-
"optimizer": null,
|
| 189 |
-
"loss_type": null,
|
| 190 |
-
"metric": null,
|
| 191 |
-
"eval_use_evalscope": false,
|
| 192 |
-
"eval_dataset": [],
|
| 193 |
-
"eval_dataset_args": null,
|
| 194 |
-
"eval_limit": null,
|
| 195 |
-
"eval_generation_config": null,
|
| 196 |
-
"extra_eval_args": null,
|
| 197 |
-
"use_flash_ckpt": false,
|
| 198 |
-
"use_ray": false,
|
| 199 |
-
"ray_exp_name": null,
|
| 200 |
-
"device_groups": null,
|
| 201 |
-
"model": "/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct",
|
| 202 |
-
"model_type": "qwen3_vl",
|
| 203 |
-
"model_revision": null,
|
| 204 |
-
"task_type": "causal_lm",
|
| 205 |
-
"torch_dtype": "bfloat16",
|
| 206 |
-
"attn_impl": "flash_attn",
|
| 207 |
-
"new_special_tokens": [],
|
| 208 |
-
"num_labels": null,
|
| 209 |
-
"problem_type": null,
|
| 210 |
-
"rope_scaling": null,
|
| 211 |
-
"device_map": null,
|
| 212 |
-
"max_memory": {},
|
| 213 |
-
"max_model_len": null,
|
| 214 |
-
"local_repo_path": null,
|
| 215 |
-
"init_strategy": null,
|
| 216 |
-
"template": "qwen3_vl",
|
| 217 |
-
"system": null,
|
| 218 |
-
"max_length": 65536,
|
| 219 |
-
"truncation_strategy": "delete",
|
| 220 |
-
"max_pixels": null,
|
| 221 |
-
"agent_template": null,
|
| 222 |
-
"norm_bbox": null,
|
| 223 |
-
"use_chat_template": true,
|
| 224 |
-
"padding_side": "right",
|
| 225 |
-
"padding_free": true,
|
| 226 |
-
"loss_scale": "default",
|
| 227 |
-
"sequence_parallel_size": 1,
|
| 228 |
-
"template_backend": "swift",
|
| 229 |
-
"response_prefix": null,
|
| 230 |
-
"enable_thinking": null,
|
| 231 |
-
"add_non_thinking_prefix": true,
|
| 232 |
-
"dataset": [
|
| 233 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l1.jsonl#163000",
|
| 234 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l1.jsonl#339000",
|
| 235 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l2.jsonl#163000",
|
| 236 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l2.jsonl#339000",
|
| 237 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_ubuntu_5k.train0107.openai_unified_converted.swift.ws4.l3.jsonl#163000",
|
| 238 |
-
"/apdcephfs_fsgm/share_304220499/data/planning/to_train/0127/AgentNet_ws4_filter_failure/agentnet_win_mac_18k.train0107.openai_unified_converted.swift.ws4.l3.jsonl#339000"
|
| 239 |
-
],
|
| 240 |
-
"val_dataset": [],
|
| 241 |
-
"cached_dataset": [],
|
| 242 |
-
"cached_val_dataset": [],
|
| 243 |
-
"split_dataset_ratio": 0.0,
|
| 244 |
-
"dataset_num_proc": 8,
|
| 245 |
-
"load_from_cache_file": false,
|
| 246 |
-
"dataset_shuffle": true,
|
| 247 |
-
"val_dataset_shuffle": false,
|
| 248 |
-
"streaming": false,
|
| 249 |
-
"interleave_prob": null,
|
| 250 |
-
"stopping_strategy": "first_exhausted",
|
| 251 |
-
"shuffle_buffer_size": 1000,
|
| 252 |
-
"download_mode": "reuse_dataset_if_exists",
|
| 253 |
-
"columns": {},
|
| 254 |
-
"strict": false,
|
| 255 |
-
"model_name": null,
|
| 256 |
-
"model_author": null,
|
| 257 |
-
"custom_dataset_info": [],
|
| 258 |
-
"quant_method": null,
|
| 259 |
-
"quant_bits": null,
|
| 260 |
-
"hqq_axis": null,
|
| 261 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 262 |
-
"bnb_4bit_quant_type": "nf4",
|
| 263 |
-
"bnb_4bit_use_double_quant": true,
|
| 264 |
-
"bnb_4bit_quant_storage": null,
|
| 265 |
-
"max_new_tokens": 64,
|
| 266 |
-
"temperature": 0.0,
|
| 267 |
-
"top_k": null,
|
| 268 |
-
"top_p": null,
|
| 269 |
-
"repetition_penalty": null,
|
| 270 |
-
"num_beams": 1,
|
| 271 |
-
"stream": false,
|
| 272 |
-
"stop_words": [],
|
| 273 |
-
"logprobs": false,
|
| 274 |
-
"top_logprobs": null,
|
| 275 |
-
"structured_outputs_regex": null,
|
| 276 |
-
"ckpt_dir": null,
|
| 277 |
-
"lora_modules": [],
|
| 278 |
-
"train_type": "full",
|
| 279 |
-
"adapters": [],
|
| 280 |
-
"external_plugins": [],
|
| 281 |
-
"model_kwargs": {},
|
| 282 |
-
"load_args": false,
|
| 283 |
-
"load_data_args": false,
|
| 284 |
-
"packing": false,
|
| 285 |
-
"packing_length": null,
|
| 286 |
-
"packing_num_proc": 1,
|
| 287 |
-
"lazy_tokenize": true,
|
| 288 |
-
"custom_register_path": [],
|
| 289 |
-
"use_hf": false,
|
| 290 |
-
"ignore_args_error": false,
|
| 291 |
-
"use_swift_lora": false,
|
| 292 |
-
"freeze_parameters": [],
|
| 293 |
-
"freeze_parameters_regex": null,
|
| 294 |
-
"freeze_parameters_ratio": 0.0,
|
| 295 |
-
"trainable_parameters": [
|
| 296 |
-
"model.visual.merger",
|
| 297 |
-
"model.visual.deepstack_merger_list"
|
| 298 |
-
],
|
| 299 |
-
"trainable_parameters_regex": null,
|
| 300 |
-
"freeze_llm": false,
|
| 301 |
-
"freeze_vit": false,
|
| 302 |
-
"freeze_aligner": false,
|
| 303 |
-
"target_modules": [
|
| 304 |
-
"all-linear"
|
| 305 |
-
],
|
| 306 |
-
"target_regex": null,
|
| 307 |
-
"target_parameters": null,
|
| 308 |
-
"modules_to_save": [],
|
| 309 |
-
"lora_rank": 8,
|
| 310 |
-
"lora_alpha": 32,
|
| 311 |
-
"lora_dropout": 0.05,
|
| 312 |
-
"lora_bias": "none",
|
| 313 |
-
"lora_dtype": null,
|
| 314 |
-
"lorap_lr_ratio": null,
|
| 315 |
-
"use_rslora": false,
|
| 316 |
-
"use_dora": false,
|
| 317 |
-
"lora_ga_batch_size": 2,
|
| 318 |
-
"lora_ga_iters": 2,
|
| 319 |
-
"lora_ga_max_length": 1024,
|
| 320 |
-
"lora_ga_direction": "ArB2r",
|
| 321 |
-
"lora_ga_scale": "stable",
|
| 322 |
-
"lora_ga_stable_gamma": 16,
|
| 323 |
-
"init_weights": true,
|
| 324 |
-
"fourier_n_frequency": 2000,
|
| 325 |
-
"fourier_scaling": 300.0,
|
| 326 |
-
"boft_block_size": 4,
|
| 327 |
-
"boft_block_num": 0,
|
| 328 |
-
"boft_n_butterfly_factor": 1,
|
| 329 |
-
"boft_dropout": 0.0,
|
| 330 |
-
"vera_rank": 256,
|
| 331 |
-
"vera_projection_prng_key": 0,
|
| 332 |
-
"vera_dropout": 0.0,
|
| 333 |
-
"vera_d_initial": 0.1,
|
| 334 |
-
"adapter_act": "gelu",
|
| 335 |
-
"adapter_length": 128,
|
| 336 |
-
"use_galore": false,
|
| 337 |
-
"galore_target_modules": null,
|
| 338 |
-
"galore_rank": 128,
|
| 339 |
-
"galore_update_proj_gap": 50,
|
| 340 |
-
"galore_scale": 1.0,
|
| 341 |
-
"galore_proj_type": "std",
|
| 342 |
-
"galore_optim_per_parameter": false,
|
| 343 |
-
"galore_with_embedding": false,
|
| 344 |
-
"galore_quantization": false,
|
| 345 |
-
"galore_proj_quant": false,
|
| 346 |
-
"galore_proj_bits": 4,
|
| 347 |
-
"galore_proj_group_size": 256,
|
| 348 |
-
"galore_cos_threshold": 0.4,
|
| 349 |
-
"galore_gamma_proj": 2,
|
| 350 |
-
"galore_queue_size": 5,
|
| 351 |
-
"adalora_target_r": 8,
|
| 352 |
-
"adalora_init_r": 12,
|
| 353 |
-
"adalora_tinit": 0,
|
| 354 |
-
"adalora_tfinal": 0,
|
| 355 |
-
"adalora_deltaT": 1,
|
| 356 |
-
"adalora_beta1": 0.85,
|
| 357 |
-
"adalora_beta2": 0.85,
|
| 358 |
-
"adalora_orth_reg_weight": 0.5,
|
| 359 |
-
"llamapro_num_new_blocks": 4,
|
| 360 |
-
"llamapro_num_groups": null,
|
| 361 |
-
"lisa_activated_layers": 0,
|
| 362 |
-
"lisa_step_interval": 20,
|
| 363 |
-
"reft_layer_key": null,
|
| 364 |
-
"reft_layers": null,
|
| 365 |
-
"reft_rank": 4,
|
| 366 |
-
"reft_intervention_type": "LoreftIntervention",
|
| 367 |
-
"reft_args": null,
|
| 368 |
-
"swanlab_token": null,
|
| 369 |
-
"swanlab_project": "ms-swift",
|
| 370 |
-
"swanlab_workspace": null,
|
| 371 |
-
"swanlab_exp_name": null,
|
| 372 |
-
"swanlab_notification_method": null,
|
| 373 |
-
"swanlab_webhook_url": null,
|
| 374 |
-
"swanlab_secret": null,
|
| 375 |
-
"swanlab_mode": "cloud",
|
| 376 |
-
"add_version": true,
|
| 377 |
-
"create_checkpoint_symlink": false,
|
| 378 |
-
"zero_hpz_partition_size": null,
|
| 379 |
-
"deepspeed_autotp_size": null,
|
| 380 |
-
"early_stop_interval": null,
|
| 381 |
-
"rank": 0,
|
| 382 |
-
"global_world_size": 96,
|
| 383 |
-
"local_world_size": 8,
|
| 384 |
-
"model_suffix": "Qwen3-VL-4B-Instruct",
|
| 385 |
-
"model_info": "ModelInfo(model_type='qwen3_vl', model_dir='/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct', 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=False, is_multimodal=True, config=None, task_type='causal_lm', num_labels=None)",
|
| 386 |
-
"model_meta": "ModelMeta(model_type='qwen3_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct', hf_model_id='Qwen/Qwen3-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking', hf_model_id='Qwen/Qwen3-VL-2B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-2B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct', hf_model_id='Qwen/Qwen3-VL-4B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking', hf_model_id='Qwen/Qwen3-VL-4B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-4B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct', hf_model_id='Qwen/Qwen3-VL-8B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking', hf_model_id='Qwen/Qwen3-VL-8B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-8B-Thinking-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct', hf_model_id='Qwen/Qwen3-VL-32B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking', hf_model_id='Qwen/Qwen3-VL-32B-Thinking', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', hf_model_id='Qwen/Qwen3-VL-32B-Instruct-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen3-VL-32B-Thinking-FP8', hf_model_id='Qwen/Qwen3-VL-32B-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_vl at 0x7f78135487c0>, 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', 'lm_head'], aligner=['model.visual.merger', 'model.visual.deepstack_merger_list'], vision_tower=['model.visual'], generator=[]), architectures=['Qwen3VLForConditionalGeneration'], additional_saved_files=[], torch_dtype=None, is_multimodal=True, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.57', 'qwen_vl_utils>=0.0.14', 'decord'], tags=['vision', 'video'])",
|
| 387 |
-
"model_dir": "/apdcephfs_fsgm/share_304220499/mclan/checkpoints/Qwen3-VL-4B-Instruct",
|
| 388 |
-
"_val_dataset_exists": [],
|
| 389 |
-
"hub": "<class 'swift.hub.hub.MSHub'>",
|
| 390 |
-
"evaluation_strategy": "steps",
|
| 391 |
-
"training_args": "Seq2SeqTrainingArguments(output_dir='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453', overwrite_output_dir=False, do_train=False, do_eval=False, do_predict=False, eval_strategy=<IntervalStrategy.NO: 'no'>, prediction_loss_only=False, per_device_train_batch_size=4, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=1, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=2e-05, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=1.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.05, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<SaveStrategy.STEPS: 'steps'>, save_steps=500, save_total_limit=None, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=10000.0, dataloader_num_workers=8, dataloader_prefetch_factor=2, past_index=-1, run_name='/apdcephfs_fsgm/share_304220499/weixian/workspace/Agent_SFT/output/Qwen3-VL-4B-Instruct/agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384/v0-20260131-020453', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), parallelism_config=None, deepspeed={'fp16': {'enabled': 'auto', 'loss_scale': 0, 'loss_scale_window': 1000, 'initial_scale_power': 16, 'hysteresis': 2, 'min_loss_scale': 1}, 'bf16': {'enabled': 'auto'}, 'zero_optimization': {'stage': 1, 'offload_optimizer': {'device': 'none', 'pin_memory': True}, 'allgather_partitions': True, 'allgather_bucket_size': 200000000.0, 'overlap_comm': False, 'reduce_scatter': True, 'reduce_bucket_size': 200000000.0, 'contiguous_gradients': True}, 'gradient_accumulation_steps': 'auto', 'gradient_clipping': 'auto', 'steps_per_print': 2000, 'train_batch_size': 'auto', 'train_micro_batch_size_per_gpu': 'auto', 'wall_clock_breakdown': False}, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH_FUSED: 'adamw_torch_fused'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['wandb'], project='huggingface', trackio_space_id='trackio', ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=None, hub_always_push=False, hub_revision=None, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=18000000, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=True, liger_kernel_config=None, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, tuner_backend='peft', vit_gradient_checkpointing=True, router_aux_loss_coef=0.0, enable_dft_loss=False, enable_channel_loss=False, check_model=True, acc_strategy='token', train_dataloader_shuffle=True, max_epochs=None, aligner_lr=1e-05, vit_lr=1e-05, use_logits_to_keep=None, ds3_gather_for_generation=True, resume_only_model=False, optimizer='multimodal', loss_type=None, metric=None, eval_use_evalscope=False, eval_dataset=[], eval_dataset_args=None, eval_limit=None, eval_generation_config=None, extra_eval_args=None, use_flash_ckpt=False, sft_alpha=0, chord_sft_dataset=[], chord_sft_per_device_train_batch_size=None, chord_enable_phi_function=False, chord_mu_warmup_steps=None, chord_mu_decay_steps=None, chord_mu_peak=None, chord_mu_valley=None, train_type='full', local_repo_path=None, galore_config=None, task_type='causal_lm', problem_type=None)"
|
| 392 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/chat_template.jinja
DELETED
|
@@ -1,120 +0,0 @@
|
|
| 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 %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/config.json
DELETED
|
@@ -1,70 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3VLForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"dtype": "bfloat16",
|
| 6 |
-
"eos_token_id": 151645,
|
| 7 |
-
"hidden_size": 2560,
|
| 8 |
-
"image_token_id": 151655,
|
| 9 |
-
"model_type": "qwen3_vl",
|
| 10 |
-
"pad_token_id": 151643,
|
| 11 |
-
"text_config": {
|
| 12 |
-
"attention_bias": false,
|
| 13 |
-
"attention_dropout": 0.0,
|
| 14 |
-
"bos_token_id": 151643,
|
| 15 |
-
"dtype": "bfloat16",
|
| 16 |
-
"eos_token_id": 151645,
|
| 17 |
-
"head_dim": 128,
|
| 18 |
-
"hidden_act": "silu",
|
| 19 |
-
"hidden_size": 2560,
|
| 20 |
-
"initializer_range": 0.02,
|
| 21 |
-
"intermediate_size": 9728,
|
| 22 |
-
"max_position_embeddings": 262144,
|
| 23 |
-
"model_type": "qwen3_vl_text",
|
| 24 |
-
"num_attention_heads": 32,
|
| 25 |
-
"num_hidden_layers": 36,
|
| 26 |
-
"num_key_value_heads": 8,
|
| 27 |
-
"pad_token_id": 151643,
|
| 28 |
-
"rms_norm_eps": 1e-06,
|
| 29 |
-
"rope_scaling": {
|
| 30 |
-
"mrope_interleaved": true,
|
| 31 |
-
"mrope_section": [
|
| 32 |
-
24,
|
| 33 |
-
20,
|
| 34 |
-
20
|
| 35 |
-
],
|
| 36 |
-
"rope_type": "default"
|
| 37 |
-
},
|
| 38 |
-
"rope_theta": 5000000,
|
| 39 |
-
"tie_word_embeddings": true,
|
| 40 |
-
"use_cache": false,
|
| 41 |
-
"vocab_size": 151936
|
| 42 |
-
},
|
| 43 |
-
"tie_word_embeddings": true,
|
| 44 |
-
"transformers_version": "4.57.1",
|
| 45 |
-
"video_token_id": 151656,
|
| 46 |
-
"vision_config": {
|
| 47 |
-
"deepstack_visual_indexes": [
|
| 48 |
-
5,
|
| 49 |
-
11,
|
| 50 |
-
17
|
| 51 |
-
],
|
| 52 |
-
"depth": 24,
|
| 53 |
-
"dtype": "bfloat16",
|
| 54 |
-
"hidden_act": "gelu_pytorch_tanh",
|
| 55 |
-
"hidden_size": 1024,
|
| 56 |
-
"in_channels": 3,
|
| 57 |
-
"initializer_range": 0.02,
|
| 58 |
-
"intermediate_size": 4096,
|
| 59 |
-
"model_type": "qwen3_vl",
|
| 60 |
-
"num_heads": 16,
|
| 61 |
-
"num_position_embeddings": 2304,
|
| 62 |
-
"out_hidden_size": 2560,
|
| 63 |
-
"pad_token_id": 151643,
|
| 64 |
-
"patch_size": 16,
|
| 65 |
-
"spatial_merge_size": 2,
|
| 66 |
-
"temporal_patch_size": 2
|
| 67 |
-
},
|
| 68 |
-
"vision_end_token_id": 151653,
|
| 69 |
-
"vision_start_token_id": 151652
|
| 70 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/latest
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
global_step1000
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:eef799a6f3a5e1372fd89d3a081bda2ed9467bc21b3927391af78eb6ccaa1cf4
|
| 3 |
-
size 4990497880
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:d7c2a2ffc84d8617236cd4d77f8ede17f106711443040a168937cd65708c61b6
|
| 3 |
-
size 4663133960
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/model.safetensors.index.json
DELETED
|
@@ -1,722 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_parameters": 4437815808,
|
| 4 |
-
"total_size": 9653543936
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
-
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
-
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
-
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
-
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
-
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
-
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
-
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
-
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
-
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
-
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
-
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
-
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
-
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
-
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
-
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
-
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
-
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
-
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
-
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
-
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
-
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
-
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
-
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
-
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
-
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
-
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
-
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
-
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
-
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
-
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
-
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
-
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
-
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
-
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
-
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
-
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
-
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
-
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
-
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
-
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
-
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
-
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
-
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
-
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
-
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
-
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
-
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
-
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
-
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
-
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
-
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
-
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
-
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
-
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
-
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
-
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
-
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
-
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
-
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
-
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
-
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
-
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
-
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
-
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
-
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
-
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
-
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
-
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
-
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
-
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
-
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
-
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
-
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
-
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
-
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
-
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
-
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
-
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
-
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
-
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
-
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
-
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
-
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
-
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
-
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
-
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
-
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
-
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
-
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 98 |
-
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 99 |
-
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
-
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 102 |
-
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
-
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
-
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
-
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
-
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
-
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 109 |
-
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
-
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
-
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
-
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
-
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
-
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
-
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
-
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
-
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
-
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
-
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
-
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
-
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
-
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
-
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
-
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
-
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
-
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
-
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
-
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
-
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
-
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 131 |
-
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
-
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
-
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
-
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
-
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
-
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
-
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
-
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
-
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
-
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
-
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
-
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
-
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
-
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
-
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
-
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
-
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
-
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
-
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
-
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
-
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
-
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
-
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
-
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
-
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
-
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
-
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
-
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
-
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
-
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
-
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
-
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
-
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
-
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
-
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
-
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
-
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
-
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
-
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
-
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
-
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
-
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
-
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
-
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
-
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
-
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
-
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
-
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
-
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
-
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
-
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
-
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
-
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
-
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
-
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
-
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
-
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
-
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
-
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
-
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
-
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
-
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
-
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
-
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
-
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
-
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
-
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
-
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
-
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
-
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
-
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
-
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
-
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
-
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
-
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
-
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
-
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 208 |
-
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
-
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
-
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
-
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
-
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
-
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
-
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
-
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
-
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
-
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
-
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
-
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
-
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
-
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
-
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
-
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
-
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
-
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
-
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
-
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
-
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
-
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
-
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
-
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
-
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
-
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
-
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
-
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
-
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
-
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
-
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
-
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
-
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
-
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
-
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
-
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
-
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
-
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
-
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
-
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
-
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
-
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
-
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
-
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
-
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
-
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
-
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
-
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
-
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
-
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
-
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
-
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
-
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
-
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
-
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
-
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
-
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
-
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
-
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
-
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
-
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
-
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
-
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
-
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
-
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
-
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
-
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
-
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
-
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
-
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
-
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
-
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
-
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
-
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
-
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
-
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
-
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
-
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
-
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
-
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
-
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
-
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
-
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
-
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
-
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
-
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
-
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
-
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
-
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
-
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
-
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
-
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
-
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
-
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
-
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
-
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
-
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
-
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
-
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
-
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
-
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
-
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
-
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
-
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
-
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
-
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
-
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
-
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
-
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
-
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 318 |
-
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
-
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
-
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
-
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
-
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
-
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
-
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
-
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
-
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
-
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
-
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 329 |
-
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
-
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
-
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
-
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
-
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
-
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
-
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
-
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
-
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
-
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
-
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
-
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
-
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
-
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
-
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
-
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
-
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
-
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
-
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
-
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
-
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
-
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
-
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
-
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
-
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
-
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
-
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
-
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
-
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
-
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
-
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
-
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
-
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
-
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
-
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
-
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
-
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
-
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
-
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
-
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
-
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
-
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
-
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
-
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
-
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
-
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
-
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
-
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
-
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
-
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
-
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
-
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
-
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
-
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
-
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
-
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
-
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
-
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
-
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
-
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
-
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
-
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
-
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
-
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
-
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
-
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
-
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
-
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
-
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
-
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
-
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
-
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
-
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
-
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
-
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 406 |
-
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 407 |
-
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
-
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 409 |
-
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 410 |
-
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
-
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
-
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
-
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
-
"model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 415 |
-
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 416 |
-
"model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 417 |
-
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 418 |
-
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
-
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
-
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 421 |
-
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 422 |
-
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
-
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
-
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
-
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
-
"model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
-
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
-
"model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
-
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
-
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
-
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
-
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 433 |
-
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 434 |
-
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 435 |
-
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 436 |
-
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 437 |
-
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 438 |
-
"model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
-
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
-
"model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
-
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
-
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 443 |
-
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 444 |
-
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 445 |
-
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 446 |
-
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 447 |
-
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 448 |
-
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 449 |
-
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 450 |
-
"model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 451 |
-
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
-
"model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 453 |
-
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 454 |
-
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 455 |
-
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 456 |
-
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 457 |
-
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 458 |
-
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
-
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
-
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
-
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
-
"model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 463 |
-
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
-
"model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 465 |
-
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 466 |
-
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
-
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
-
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 469 |
-
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 470 |
-
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
-
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
-
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
-
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
-
"model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
-
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
-
"model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
-
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
-
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
-
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
-
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 481 |
-
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 482 |
-
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 483 |
-
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 484 |
-
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 485 |
-
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 486 |
-
"model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
-
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
-
"model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
-
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
-
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 491 |
-
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 492 |
-
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 493 |
-
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 494 |
-
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 495 |
-
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 496 |
-
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 497 |
-
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 498 |
-
"model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 499 |
-
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
-
"model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 501 |
-
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 502 |
-
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 503 |
-
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
-
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 505 |
-
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 506 |
-
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
-
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
-
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
-
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
-
"model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 511 |
-
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
-
"model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 513 |
-
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 514 |
-
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
-
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
-
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 517 |
-
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 518 |
-
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
-
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
-
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
-
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
-
"model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
-
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
-
"model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
-
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
-
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
-
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
-
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 529 |
-
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 530 |
-
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 531 |
-
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 532 |
-
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 533 |
-
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 534 |
-
"model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
-
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
-
"model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
-
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
-
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 539 |
-
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
-
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 541 |
-
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 542 |
-
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 543 |
-
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 544 |
-
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 545 |
-
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 546 |
-
"model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 547 |
-
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
-
"model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 549 |
-
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 550 |
-
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 551 |
-
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
-
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 553 |
-
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 554 |
-
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
-
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
-
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
-
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
-
"model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 559 |
-
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
-
"model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 561 |
-
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 562 |
-
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
-
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
-
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 565 |
-
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 566 |
-
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
-
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
-
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
-
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
-
"model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
-
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
-
"model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
-
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
-
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
-
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
-
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 577 |
-
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 578 |
-
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 579 |
-
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 580 |
-
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 581 |
-
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 582 |
-
"model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
-
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
-
"model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
-
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
-
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 587 |
-
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 588 |
-
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 589 |
-
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 590 |
-
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 591 |
-
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 592 |
-
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 593 |
-
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 594 |
-
"model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 595 |
-
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
-
"model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 597 |
-
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 598 |
-
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 599 |
-
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
-
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 601 |
-
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 602 |
-
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
-
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
-
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
-
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
-
"model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 607 |
-
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 608 |
-
"model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 609 |
-
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 610 |
-
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
-
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
-
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 613 |
-
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 614 |
-
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
-
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
-
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
-
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
-
"model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
-
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
-
"model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
-
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
-
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
-
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
-
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 625 |
-
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 626 |
-
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 627 |
-
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 628 |
-
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 629 |
-
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 630 |
-
"model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
-
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
-
"model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
-
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
-
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 635 |
-
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
-
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 637 |
-
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 638 |
-
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 639 |
-
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 640 |
-
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 641 |
-
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 642 |
-
"model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 643 |
-
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
-
"model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 645 |
-
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 646 |
-
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 647 |
-
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 648 |
-
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 649 |
-
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 650 |
-
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
-
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
-
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
-
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
-
"model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 655 |
-
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
-
"model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 657 |
-
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 658 |
-
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
-
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
-
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 661 |
-
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 662 |
-
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
-
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
-
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
-
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
-
"model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
-
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
-
"model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
-
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
-
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
-
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
-
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 673 |
-
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 674 |
-
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 675 |
-
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 676 |
-
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 677 |
-
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 678 |
-
"model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
-
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
-
"model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
-
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
-
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 683 |
-
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
-
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 685 |
-
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 686 |
-
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 687 |
-
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 688 |
-
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 689 |
-
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 690 |
-
"model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 691 |
-
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
-
"model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 693 |
-
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 694 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
-
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
-
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
-
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 699 |
-
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 700 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 701 |
-
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 702 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 703 |
-
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
-
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 705 |
-
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 706 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 707 |
-
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 708 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 709 |
-
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 710 |
-
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 711 |
-
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 712 |
-
"model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 713 |
-
"model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 714 |
-
"model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 715 |
-
"model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
-
"model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 717 |
-
"model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 718 |
-
"model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
-
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
-
"model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
|
| 721 |
-
}
|
| 722 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/preprocessor_config.json
DELETED
|
@@ -1,21 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
-
size 11422654
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/tokenizer_config.json
DELETED
|
@@ -1,240 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/trainer_state.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/training_args.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:cb2b71716b815c69acae19745e5f5d002f10f9854295fcea3ac09170daa4d99b
|
| 3 |
-
size 9297
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/video_preprocessor_config.json
DELETED
|
@@ -1,41 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen3-vl4b-agentnet_filter_failure_ws4_lr2e-5_vit1e-5_aligner1e-5_bs384-step1000/zero_to_fp32.py
DELETED
|
@@ -1,760 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env python
|
| 2 |
-
|
| 3 |
-
# Copyright (c) Microsoft Corporation.
|
| 4 |
-
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
-
|
| 6 |
-
# DeepSpeed Team
|
| 7 |
-
|
| 8 |
-
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
-
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
-
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
-
# application.
|
| 12 |
-
#
|
| 13 |
-
# example:
|
| 14 |
-
# python zero_to_fp32.py . output_dir/
|
| 15 |
-
# or
|
| 16 |
-
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
-
|
| 18 |
-
import argparse
|
| 19 |
-
import torch
|
| 20 |
-
import glob
|
| 21 |
-
import math
|
| 22 |
-
import os
|
| 23 |
-
import re
|
| 24 |
-
import gc
|
| 25 |
-
import json
|
| 26 |
-
import numpy as np
|
| 27 |
-
from tqdm import tqdm
|
| 28 |
-
from collections import OrderedDict
|
| 29 |
-
from dataclasses import dataclass
|
| 30 |
-
|
| 31 |
-
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
-
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
-
from deepspeed.utils import logger
|
| 34 |
-
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
-
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
-
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
@dataclass
|
| 40 |
-
class zero_model_state:
|
| 41 |
-
buffers: dict()
|
| 42 |
-
param_shapes: dict()
|
| 43 |
-
shared_params: list
|
| 44 |
-
ds_version: int
|
| 45 |
-
frozen_param_shapes: dict()
|
| 46 |
-
frozen_param_fragments: dict()
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
debug = 0
|
| 50 |
-
|
| 51 |
-
# load to cpu
|
| 52 |
-
device = torch.device('cpu')
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
def atoi(text):
|
| 56 |
-
return int(text) if text.isdigit() else text
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
def natural_keys(text):
|
| 60 |
-
'''
|
| 61 |
-
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
-
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
-
(See Toothy's implementation in the comments)
|
| 64 |
-
'''
|
| 65 |
-
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
-
if not os.path.isdir(checkpoint_dir):
|
| 70 |
-
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
-
|
| 72 |
-
# there should be only one file
|
| 73 |
-
if zero_stage <= 2:
|
| 74 |
-
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
-
elif zero_stage == 3:
|
| 76 |
-
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
-
|
| 78 |
-
if not os.path.exists(file):
|
| 79 |
-
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
-
|
| 81 |
-
return file
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
-
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
-
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
-
|
| 88 |
-
if len(ckpt_files) == 0:
|
| 89 |
-
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
-
|
| 91 |
-
return ckpt_files
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
def get_optim_files(checkpoint_dir):
|
| 95 |
-
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
def get_model_state_files(checkpoint_dir):
|
| 99 |
-
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
def parse_model_states(files):
|
| 103 |
-
zero_model_states = []
|
| 104 |
-
for file in files:
|
| 105 |
-
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
-
|
| 107 |
-
if BUFFER_NAMES not in state_dict:
|
| 108 |
-
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
-
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
-
if debug:
|
| 111 |
-
print("Found buffers:", buffer_names)
|
| 112 |
-
|
| 113 |
-
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
-
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
-
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
-
|
| 117 |
-
# collect parameters that are included in param_shapes
|
| 118 |
-
param_names = []
|
| 119 |
-
for s in param_shapes:
|
| 120 |
-
for name in s.keys():
|
| 121 |
-
param_names.append(name)
|
| 122 |
-
|
| 123 |
-
# update with frozen parameters
|
| 124 |
-
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
-
if frozen_param_shapes is not None:
|
| 126 |
-
if debug:
|
| 127 |
-
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
-
param_names += list(frozen_param_shapes.keys())
|
| 129 |
-
|
| 130 |
-
# handle shared params
|
| 131 |
-
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
-
|
| 133 |
-
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
-
|
| 135 |
-
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
-
|
| 137 |
-
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
-
param_shapes=param_shapes,
|
| 139 |
-
shared_params=shared_params,
|
| 140 |
-
ds_version=ds_version,
|
| 141 |
-
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
-
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
-
zero_model_states.append(z_model_state)
|
| 144 |
-
|
| 145 |
-
return zero_model_states
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
-
total_files = len(files)
|
| 150 |
-
state_dicts = []
|
| 151 |
-
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
-
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
-
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
-
# and also handle the case where it was already removed by another helper script
|
| 155 |
-
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
-
state_dicts.append(state_dict)
|
| 157 |
-
|
| 158 |
-
if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
-
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
-
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
-
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
-
|
| 163 |
-
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
-
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
-
# use the max of the partition_count to get the dp world_size.
|
| 166 |
-
|
| 167 |
-
if type(world_size) is list:
|
| 168 |
-
world_size = max(world_size)
|
| 169 |
-
|
| 170 |
-
if world_size != total_files:
|
| 171 |
-
raise ValueError(
|
| 172 |
-
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
-
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
-
)
|
| 175 |
-
|
| 176 |
-
# the groups are named differently in each stage
|
| 177 |
-
if zero_stage <= 2:
|
| 178 |
-
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
-
elif zero_stage == 3:
|
| 180 |
-
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
-
else:
|
| 182 |
-
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
-
|
| 184 |
-
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
-
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
-
"""
|
| 190 |
-
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
-
|
| 192 |
-
Args:
|
| 193 |
-
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
-
|
| 195 |
-
"""
|
| 196 |
-
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
-
|
| 198 |
-
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
-
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
-
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
-
|
| 202 |
-
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
-
|
| 204 |
-
zero_model_states = parse_model_states(model_files)
|
| 205 |
-
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
-
|
| 207 |
-
if zero_stage <= 2:
|
| 208 |
-
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
-
exclude_frozen_parameters)
|
| 210 |
-
elif zero_stage == 3:
|
| 211 |
-
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
-
exclude_frozen_parameters)
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
-
return
|
| 218 |
-
|
| 219 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
-
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
-
|
| 222 |
-
if debug:
|
| 223 |
-
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
-
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
-
|
| 226 |
-
wanted_params = len(frozen_param_shapes)
|
| 227 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
-
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
-
|
| 232 |
-
total_params = 0
|
| 233 |
-
total_numel = 0
|
| 234 |
-
for name, shape in frozen_param_shapes.items():
|
| 235 |
-
total_params += 1
|
| 236 |
-
unpartitioned_numel = shape.numel()
|
| 237 |
-
total_numel += unpartitioned_numel
|
| 238 |
-
|
| 239 |
-
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
-
|
| 241 |
-
if debug:
|
| 242 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
-
|
| 244 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
def _has_callable(obj, fn):
|
| 248 |
-
attr = getattr(obj, fn, None)
|
| 249 |
-
return callable(attr)
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
-
|
| 255 |
-
# Reconstruction protocol:
|
| 256 |
-
#
|
| 257 |
-
# XXX: document this
|
| 258 |
-
|
| 259 |
-
if debug:
|
| 260 |
-
for i in range(world_size):
|
| 261 |
-
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
-
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
-
|
| 264 |
-
# XXX: memory usage doubles here (zero2)
|
| 265 |
-
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
-
merged_single_partition_of_fp32_groups = []
|
| 267 |
-
for i in range(num_param_groups):
|
| 268 |
-
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
-
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
-
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
-
avail_numel = sum(
|
| 272 |
-
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
-
|
| 274 |
-
if debug:
|
| 275 |
-
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
-
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
-
# not asserting if there is a mismatch due to possible padding
|
| 278 |
-
print(f"Have {avail_numel} numels to process.")
|
| 279 |
-
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
-
|
| 281 |
-
# params
|
| 282 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
-
# out-of-core computing solution
|
| 284 |
-
total_numel = 0
|
| 285 |
-
total_params = 0
|
| 286 |
-
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
-
offset = 0
|
| 288 |
-
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
-
for name, shape in shapes.items():
|
| 290 |
-
|
| 291 |
-
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
-
total_numel += unpartitioned_numel
|
| 293 |
-
total_params += 1
|
| 294 |
-
|
| 295 |
-
if debug:
|
| 296 |
-
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
-
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
-
offset += unpartitioned_numel
|
| 299 |
-
|
| 300 |
-
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
-
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
-
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
-
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
-
align_to = 2 * world_size
|
| 305 |
-
|
| 306 |
-
def zero2_align(x):
|
| 307 |
-
return align_to * math.ceil(x / align_to)
|
| 308 |
-
|
| 309 |
-
if debug:
|
| 310 |
-
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
-
|
| 312 |
-
offset = zero2_align(offset)
|
| 313 |
-
avail_numel = zero2_align(avail_numel)
|
| 314 |
-
|
| 315 |
-
if debug:
|
| 316 |
-
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
-
|
| 318 |
-
# Sanity check
|
| 319 |
-
if offset != avail_numel:
|
| 320 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
-
|
| 322 |
-
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
-
|
| 324 |
-
|
| 325 |
-
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
-
exclude_frozen_parameters):
|
| 327 |
-
state_dict = OrderedDict()
|
| 328 |
-
|
| 329 |
-
# buffers
|
| 330 |
-
buffers = zero_model_states[0].buffers
|
| 331 |
-
state_dict.update(buffers)
|
| 332 |
-
if debug:
|
| 333 |
-
print(f"added {len(buffers)} buffers")
|
| 334 |
-
|
| 335 |
-
if not exclude_frozen_parameters:
|
| 336 |
-
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
-
|
| 338 |
-
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
-
|
| 340 |
-
# recover shared parameters
|
| 341 |
-
for pair in zero_model_states[0].shared_params:
|
| 342 |
-
if pair[1] in state_dict:
|
| 343 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
-
|
| 345 |
-
return state_dict
|
| 346 |
-
|
| 347 |
-
|
| 348 |
-
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
-
remainder = unpartitioned_numel % world_size
|
| 350 |
-
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
-
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
-
return partitioned_numel, padding_numel
|
| 353 |
-
|
| 354 |
-
|
| 355 |
-
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
-
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
-
return
|
| 358 |
-
|
| 359 |
-
if debug:
|
| 360 |
-
for i in range(world_size):
|
| 361 |
-
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
-
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
-
|
| 364 |
-
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
-
wanted_params = len(frozen_param_shapes)
|
| 366 |
-
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
-
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
-
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
-
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
-
|
| 371 |
-
total_params = 0
|
| 372 |
-
total_numel = 0
|
| 373 |
-
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
-
total_params += 1
|
| 375 |
-
unpartitioned_numel = shape.numel()
|
| 376 |
-
total_numel += unpartitioned_numel
|
| 377 |
-
|
| 378 |
-
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
-
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
-
|
| 381 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
-
|
| 383 |
-
if debug:
|
| 384 |
-
print(
|
| 385 |
-
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
-
)
|
| 387 |
-
|
| 388 |
-
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
-
|
| 390 |
-
|
| 391 |
-
class GatheredTensor:
|
| 392 |
-
"""
|
| 393 |
-
A pseudo tensor that collects partitioned weights.
|
| 394 |
-
It is more memory efficient when there are multiple groups.
|
| 395 |
-
"""
|
| 396 |
-
|
| 397 |
-
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
-
self.flat_groups = flat_groups
|
| 399 |
-
self.flat_groups_offset = flat_groups_offset
|
| 400 |
-
self.offset = offset
|
| 401 |
-
self.partitioned_numel = partitioned_numel
|
| 402 |
-
self.shape = shape
|
| 403 |
-
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
-
|
| 405 |
-
def contiguous(self):
|
| 406 |
-
"""
|
| 407 |
-
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
-
"""
|
| 409 |
-
end_idx = self.offset + self.partitioned_numel
|
| 410 |
-
world_size = len(self.flat_groups)
|
| 411 |
-
pad_flat_param_chunks = []
|
| 412 |
-
|
| 413 |
-
for rank_i in range(world_size):
|
| 414 |
-
# for each rank, we need to collect weights from related group/groups
|
| 415 |
-
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
-
start_group_id = None
|
| 417 |
-
end_group_id = None
|
| 418 |
-
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
-
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
-
start_group_id = group_id
|
| 421 |
-
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
-
end_group_id = group_id
|
| 423 |
-
break
|
| 424 |
-
# collect weights from related group/groups
|
| 425 |
-
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
-
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
-
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
-
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
-
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
-
|
| 431 |
-
# collect weights from all ranks
|
| 432 |
-
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
-
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
-
return param
|
| 435 |
-
|
| 436 |
-
|
| 437 |
-
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
-
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
-
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
-
|
| 441 |
-
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
-
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
-
|
| 444 |
-
# merge list of dicts, preserving order
|
| 445 |
-
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
-
|
| 447 |
-
if debug:
|
| 448 |
-
for i in range(world_size):
|
| 449 |
-
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
-
|
| 451 |
-
wanted_params = len(param_shapes)
|
| 452 |
-
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
-
# not asserting if there is a mismatch due to possible padding
|
| 454 |
-
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
-
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
-
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
-
|
| 458 |
-
# params
|
| 459 |
-
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
-
# out-of-core computing solution
|
| 461 |
-
offset = 0
|
| 462 |
-
total_numel = 0
|
| 463 |
-
total_params = 0
|
| 464 |
-
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
-
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
-
unpartitioned_numel = shape.numel()
|
| 467 |
-
total_numel += unpartitioned_numel
|
| 468 |
-
total_params += 1
|
| 469 |
-
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
-
|
| 471 |
-
if debug:
|
| 472 |
-
print(
|
| 473 |
-
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
-
)
|
| 475 |
-
|
| 476 |
-
# memory efficient tensor
|
| 477 |
-
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
-
state_dict[name] = tensor
|
| 479 |
-
offset += partitioned_numel
|
| 480 |
-
|
| 481 |
-
offset *= world_size
|
| 482 |
-
|
| 483 |
-
# Sanity check
|
| 484 |
-
if offset != avail_numel:
|
| 485 |
-
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
-
|
| 487 |
-
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
-
|
| 489 |
-
|
| 490 |
-
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
-
exclude_frozen_parameters):
|
| 492 |
-
state_dict = OrderedDict()
|
| 493 |
-
|
| 494 |
-
# buffers
|
| 495 |
-
buffers = zero_model_states[0].buffers
|
| 496 |
-
state_dict.update(buffers)
|
| 497 |
-
if debug:
|
| 498 |
-
print(f"added {len(buffers)} buffers")
|
| 499 |
-
|
| 500 |
-
if not exclude_frozen_parameters:
|
| 501 |
-
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
-
|
| 503 |
-
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
-
|
| 505 |
-
# recover shared parameters
|
| 506 |
-
for pair in zero_model_states[0].shared_params:
|
| 507 |
-
if pair[1] in state_dict:
|
| 508 |
-
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
-
|
| 510 |
-
return state_dict
|
| 511 |
-
|
| 512 |
-
|
| 513 |
-
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
-
"""
|
| 515 |
-
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
-
"""
|
| 517 |
-
torch_state_dict = {}
|
| 518 |
-
converted_tensors = {}
|
| 519 |
-
for name, tensor in state_dict.items():
|
| 520 |
-
tensor_id = id(tensor)
|
| 521 |
-
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
-
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
-
torch_state_dict[name] = shared_tensor
|
| 524 |
-
else:
|
| 525 |
-
converted_tensors[tensor_id] = name
|
| 526 |
-
if return_empty_tensor:
|
| 527 |
-
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
-
else:
|
| 529 |
-
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
-
return torch_state_dict
|
| 531 |
-
|
| 532 |
-
|
| 533 |
-
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
-
tag=None,
|
| 535 |
-
exclude_frozen_parameters=False,
|
| 536 |
-
lazy_mode=False):
|
| 537 |
-
"""
|
| 538 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
-
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
-
via a model hub.
|
| 541 |
-
|
| 542 |
-
Args:
|
| 543 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
-
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
-
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
-
|
| 549 |
-
Returns:
|
| 550 |
-
- pytorch ``state_dict``
|
| 551 |
-
|
| 552 |
-
A typical usage might be ::
|
| 553 |
-
|
| 554 |
-
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
-
# do the training and checkpoint saving
|
| 556 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
-
model = model.cpu() # move to cpu
|
| 558 |
-
model.load_state_dict(state_dict)
|
| 559 |
-
# submit to model hub or save the model to share with others
|
| 560 |
-
|
| 561 |
-
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
-
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
-
|
| 565 |
-
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
-
|
| 567 |
-
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
-
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
-
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
-
|
| 571 |
-
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
-
for name, lazy_tensor in state_dict.item():
|
| 574 |
-
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
-
print(name, tensor)
|
| 576 |
-
# del tensor to release memory if it no longer in use
|
| 577 |
-
"""
|
| 578 |
-
if tag is None:
|
| 579 |
-
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
-
if os.path.isfile(latest_path):
|
| 581 |
-
with open(latest_path, 'r') as fd:
|
| 582 |
-
tag = fd.read().strip()
|
| 583 |
-
else:
|
| 584 |
-
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
-
|
| 586 |
-
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
-
|
| 588 |
-
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
-
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
-
|
| 591 |
-
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
-
if lazy_mode:
|
| 593 |
-
return state_dict
|
| 594 |
-
else:
|
| 595 |
-
return to_torch_tensor(state_dict)
|
| 596 |
-
|
| 597 |
-
|
| 598 |
-
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
-
output_dir,
|
| 600 |
-
max_shard_size="5GB",
|
| 601 |
-
safe_serialization=False,
|
| 602 |
-
tag=None,
|
| 603 |
-
exclude_frozen_parameters=False):
|
| 604 |
-
"""
|
| 605 |
-
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
-
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
-
|
| 608 |
-
Args:
|
| 609 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
-
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
-
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
-
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
-
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
-
"""
|
| 616 |
-
|
| 617 |
-
# Dependency pre-check
|
| 618 |
-
if safe_serialization:
|
| 619 |
-
try:
|
| 620 |
-
from safetensors.torch import save_file
|
| 621 |
-
except ImportError:
|
| 622 |
-
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
-
raise
|
| 624 |
-
if max_shard_size is not None:
|
| 625 |
-
try:
|
| 626 |
-
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
-
except ImportError:
|
| 628 |
-
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
-
raise
|
| 630 |
-
|
| 631 |
-
# Convert zero checkpoint to state_dict
|
| 632 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
-
tag,
|
| 634 |
-
exclude_frozen_parameters,
|
| 635 |
-
lazy_mode=True)
|
| 636 |
-
|
| 637 |
-
# Shard the model if it is too big.
|
| 638 |
-
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
-
if max_shard_size is not None:
|
| 640 |
-
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
-
# an memory-efficient approach for sharding
|
| 642 |
-
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
-
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
-
filename_pattern=filename_pattern,
|
| 645 |
-
max_shard_size=max_shard_size)
|
| 646 |
-
else:
|
| 647 |
-
from collections import namedtuple
|
| 648 |
-
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
-
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
-
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
-
|
| 652 |
-
# Save the model by shard
|
| 653 |
-
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
-
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
-
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
-
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
-
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
-
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
-
if safe_serialization:
|
| 660 |
-
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
-
else:
|
| 662 |
-
torch.save(shard_state_dict, output_path)
|
| 663 |
-
# release the memory of current shard
|
| 664 |
-
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
-
del state_dict[tensor_name]
|
| 666 |
-
del shard_state_dict[tensor_name]
|
| 667 |
-
del shard_state_dict
|
| 668 |
-
gc.collect()
|
| 669 |
-
|
| 670 |
-
# Save index if sharded
|
| 671 |
-
if state_dict_split.is_sharded:
|
| 672 |
-
index = {
|
| 673 |
-
"metadata": state_dict_split.metadata,
|
| 674 |
-
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
-
}
|
| 676 |
-
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
-
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
-
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
-
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
-
f.write(content)
|
| 681 |
-
|
| 682 |
-
|
| 683 |
-
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
-
"""
|
| 685 |
-
1. Put the provided model to cpu
|
| 686 |
-
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
-
3. Load it into the provided model
|
| 688 |
-
|
| 689 |
-
Args:
|
| 690 |
-
- ``model``: the model object to update
|
| 691 |
-
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
-
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
-
|
| 694 |
-
Returns:
|
| 695 |
-
- ``model`: modified model
|
| 696 |
-
|
| 697 |
-
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
-
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
-
conveniently placed for you in the checkpoint folder.
|
| 700 |
-
|
| 701 |
-
A typical usage might be ::
|
| 702 |
-
|
| 703 |
-
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
-
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
-
# submit to model hub or save the model to share with others
|
| 706 |
-
|
| 707 |
-
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
-
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
-
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
-
|
| 711 |
-
"""
|
| 712 |
-
logger.info("Extracting fp32 weights")
|
| 713 |
-
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
-
|
| 715 |
-
logger.info("Overwriting model with fp32 weights")
|
| 716 |
-
model = model.cpu()
|
| 717 |
-
model.load_state_dict(state_dict, strict=False)
|
| 718 |
-
|
| 719 |
-
return model
|
| 720 |
-
|
| 721 |
-
|
| 722 |
-
if __name__ == "__main__":
|
| 723 |
-
parser = argparse.ArgumentParser()
|
| 724 |
-
parser.add_argument("checkpoint_dir",
|
| 725 |
-
type=str,
|
| 726 |
-
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
-
parser.add_argument("output_dir",
|
| 728 |
-
type=str,
|
| 729 |
-
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
-
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
-
parser.add_argument(
|
| 732 |
-
"--max_shard_size",
|
| 733 |
-
type=str,
|
| 734 |
-
default="5GB",
|
| 735 |
-
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
-
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
-
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
-
"without CPU OOM issues.")
|
| 739 |
-
parser.add_argument(
|
| 740 |
-
"--safe_serialization",
|
| 741 |
-
default=False,
|
| 742 |
-
action='store_true',
|
| 743 |
-
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
-
parser.add_argument("-t",
|
| 745 |
-
"--tag",
|
| 746 |
-
type=str,
|
| 747 |
-
default=None,
|
| 748 |
-
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
-
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
-
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
-
args = parser.parse_args()
|
| 752 |
-
|
| 753 |
-
debug = args.debug
|
| 754 |
-
|
| 755 |
-
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
-
args.output_dir,
|
| 757 |
-
max_shard_size=args.max_shard_size,
|
| 758 |
-
safe_serialization=args.safe_serialization,
|
| 759 |
-
tag=args.tag,
|
| 760 |
-
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|