commit 8e119f3436c959e35e3b29b9e229689ad8670bc3 Author: ModelHub XC Date: Sat May 23 00:18:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DaDing777/qwen2.5-VL-3B-atm-finetune-rain-ana-finetune-full Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2506665 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text + + +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +training_args.bin filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..6a8251e --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +library_name: transformers +license: other +base_model: /home/xuke/dch/checkpoint_models/qwen2.5-VL-3B-atm-finetune +tags: +- llama-factory +- full +- generated_from_trainer +model-index: +- name: qwen2.5-VL-3B-atm-finetune-rain-ana-finetune-full + results: [] +--- + + + +# qwen2.5-VL-3B-atm-finetune-rain-ana-finetune-full + +This model is a fine-tuned version of [/home/xuke/dch/checkpoint_models/qwen2.5-VL-3B-atm-finetune](https://huggingface.co//home/xuke/dch/checkpoint_models/qwen2.5-VL-3B-atm-finetune) on the atm_rain_ana dataset. + +## Model description + +More information needed + +## Intended uses & limitations + +More information needed + +## Training and evaluation data + +More information needed + +## Training procedure + +### Training hyperparameters + +The following hyperparameters were used during training: +- learning_rate: 1e-05 +- train_batch_size: 1 +- eval_batch_size: 8 +- seed: 42 +- distributed_type: multi-GPU +- num_devices: 4 +- gradient_accumulation_steps: 4 +- total_train_batch_size: 16 +- total_eval_batch_size: 32 +- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments +- lr_scheduler_type: cosine +- lr_scheduler_warmup_ratio: 0.1 +- num_epochs: 1.0 + +### Training results + + + +### Framework versions + +- Transformers 4.52.4 +- Pytorch 2.5.1+cu121 +- Datasets 3.6.0 +- Tokenizers 0.21.1 diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/all_results.json b/all_results.json new file mode 100644 index 0000000..15afc67 --- /dev/null +++ b/all_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 9533860949786624.0, + "train_loss": 1.0508991407185067, + "train_runtime": 222.7751, + "train_samples_per_second": 2.891, + "train_steps_per_second": 0.184 +} \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..6c22663 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system +You are a helpful assistant.<|im_end|> +{% endif %}<|im_start|>{{ message['role'] }} +{% if message['content'] is string %}{{ message['content'] }}<|im_end|> +{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|> +{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant +{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..d68b631 --- /dev/null +++ b/config.json @@ -0,0 +1,105 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 128000, + "max_window_layers": 70, + "model_type": "qwen2_5_vl", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "text_config": { + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 2048, + "image_token_id": null, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 128000, + "max_window_layers": 70, + "model_type": "qwen2_5_vl_text", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": null, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.52.4", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "fullatt_block_indexes": [ + 7, + 15, + 23, + 31 + ], + "hidden_act": "silu", + "hidden_size": 1280, + "in_channels": 3, + "in_chans": 3, + "initializer_range": 0.02, + "intermediate_size": 3420, + "model_type": "qwen2_5_vl", + "num_heads": 16, + "out_hidden_size": 2048, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2, + "tokens_per_second": 2, + "torch_dtype": "bfloat16", + "window_size": 112 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..3a6d425 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"image-text-to-text"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..c110271 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 1e-06, + "transformers_version": "4.52.4" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..9ca5e97 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5423e5f181b5f8458048b8344aa6f65998e2eed511db41450650cf4564e8ef4 +size 4997750760 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..298e897 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599bf9d270b4f16d6f2a85a3492aa022088ec2e5a17bfc0397aba674453a7329 +size 3133917248 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4997778 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,832 @@ +{ + "metadata": { + "total_size": 8131575808 + }, + "weight_map": { + "lm_head.weight": "model-00002-of-00002.safetensors", + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors", + "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors", + "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors", + "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors", + "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors", + "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..1c234b7 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,36 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "input_data_format": null, + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 +} diff --git a/runs/Nov30_15-59-30_A800Server/events.out.tfevents.1764518400.A800Server.158282.0 b/runs/Nov30_15-59-30_A800Server/events.out.tfevents.1764518400.A800Server.158282.0 new file mode 100644 index 0000000..3143158 --- /dev/null +++ b/runs/Nov30_15-59-30_A800Server/events.out.tfevents.1764518400.A800Server.158282.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d85363d72825b6fb135e3792478aa2c1d8a6da47a3203b10fc4afb37e3ef4c +size 9472 diff --git a/runs/Nov30_16-01-10_A800Server/events.out.tfevents.1764518497.A800Server.167303.0 b/runs/Nov30_16-01-10_A800Server/events.out.tfevents.1764518497.A800Server.167303.0 new file mode 100644 index 0000000..5702f7f --- /dev/null +++ b/runs/Nov30_16-01-10_A800Server/events.out.tfevents.1764518497.A800Server.167303.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc5ddc8e7664525e136e6d0bf201be9d6ae11259f079e6cf2c3998df494bb61 +size 16237 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..230f071 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,209 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "processor_class": "Qwen2_5_VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/train_results.json b/train_results.json new file mode 100644 index 0000000..15afc67 --- /dev/null +++ b/train_results.json @@ -0,0 +1,8 @@ +{ + "epoch": 1.0, + "total_flos": 9533860949786624.0, + "train_loss": 1.0508991407185067, + "train_runtime": 222.7751, + "train_samples_per_second": 2.891, + "train_steps_per_second": 0.184 +} \ No newline at end of file diff --git a/trainer_log.jsonl b/trainer_log.jsonl new file mode 100644 index 0000000..2dec557 --- /dev/null +++ b/trainer_log.jsonl @@ -0,0 +1,42 @@ +{"current_steps": 1, "total_steps": 41, "loss": 2.5711, "lr": 0.0, "epoch": 0.024844720496894408, "percentage": 2.44, "elapsed_time": "0:00:06", "remaining_time": "0:04:39"} +{"current_steps": 2, "total_steps": 41, "loss": 2.6176, "lr": 2.0000000000000003e-06, "epoch": 0.049689440993788817, "percentage": 4.88, "elapsed_time": "0:00:11", "remaining_time": "0:03:42"} +{"current_steps": 3, "total_steps": 41, "loss": 2.5861, "lr": 4.000000000000001e-06, "epoch": 0.07453416149068323, "percentage": 7.32, "elapsed_time": "0:00:17", "remaining_time": "0:03:40"} +{"current_steps": 4, "total_steps": 41, "loss": 2.449, "lr": 6e-06, "epoch": 0.09937888198757763, "percentage": 9.76, "elapsed_time": "0:00:21", "remaining_time": "0:03:20"} +{"current_steps": 5, "total_steps": 41, "loss": 2.1501, "lr": 8.000000000000001e-06, "epoch": 0.12422360248447205, "percentage": 12.2, "elapsed_time": "0:00:25", "remaining_time": "0:03:06"} +{"current_steps": 6, "total_steps": 41, "loss": 1.6997, "lr": 1e-05, "epoch": 0.14906832298136646, "percentage": 14.63, "elapsed_time": "0:00:30", "remaining_time": "0:02:55"} +{"current_steps": 7, "total_steps": 41, "loss": 1.6168, "lr": 9.980973490458728e-06, "epoch": 0.17391304347826086, "percentage": 17.07, "elapsed_time": "0:00:34", "remaining_time": "0:02:48"} +{"current_steps": 8, "total_steps": 41, "loss": 1.4418, "lr": 9.924038765061042e-06, "epoch": 0.19875776397515527, "percentage": 19.51, "elapsed_time": "0:00:38", "remaining_time": "0:02:40"} +{"current_steps": 9, "total_steps": 41, "loss": 1.3728, "lr": 9.829629131445342e-06, "epoch": 0.2236024844720497, "percentage": 21.95, "elapsed_time": "0:00:43", "remaining_time": "0:02:33"} +{"current_steps": 10, "total_steps": 41, "loss": 1.1993, "lr": 9.698463103929542e-06, "epoch": 0.2484472049689441, "percentage": 24.39, "elapsed_time": "0:00:47", "remaining_time": "0:02:27"} +{"current_steps": 11, "total_steps": 41, "loss": 1.1649, "lr": 9.531538935183252e-06, "epoch": 0.2732919254658385, "percentage": 26.83, "elapsed_time": "0:00:52", "remaining_time": "0:02:24"} +{"current_steps": 12, "total_steps": 41, "loss": 0.9107, "lr": 9.330127018922195e-06, "epoch": 0.2981366459627329, "percentage": 29.27, "elapsed_time": "0:00:57", "remaining_time": "0:02:18"} +{"current_steps": 13, "total_steps": 41, "loss": 1.1491, "lr": 9.09576022144496e-06, "epoch": 0.32298136645962733, "percentage": 31.71, "elapsed_time": "0:01:01", "remaining_time": "0:02:13"} +{"current_steps": 14, "total_steps": 41, "loss": 1.1275, "lr": 8.83022221559489e-06, "epoch": 0.34782608695652173, "percentage": 34.15, "elapsed_time": "0:01:07", "remaining_time": "0:02:10"} +{"current_steps": 15, "total_steps": 41, "loss": 0.9593, "lr": 8.535533905932739e-06, "epoch": 0.37267080745341613, "percentage": 36.59, "elapsed_time": "0:01:12", "remaining_time": "0:02:05"} +{"current_steps": 16, "total_steps": 41, "loss": 0.8073, "lr": 8.213938048432697e-06, "epoch": 0.39751552795031053, "percentage": 39.02, "elapsed_time": "0:01:16", "remaining_time": "0:02:00"} +{"current_steps": 17, "total_steps": 41, "loss": 0.9254, "lr": 7.86788218175523e-06, "epoch": 0.422360248447205, "percentage": 41.46, "elapsed_time": "0:01:21", "remaining_time": "0:01:55"} +{"current_steps": 18, "total_steps": 41, "loss": 0.7109, "lr": 7.500000000000001e-06, "epoch": 0.4472049689440994, "percentage": 43.9, "elapsed_time": "0:01:26", "remaining_time": "0:01:49"} +{"current_steps": 19, "total_steps": 41, "loss": 0.8236, "lr": 7.113091308703498e-06, "epoch": 0.4720496894409938, "percentage": 46.34, "elapsed_time": "0:01:32", "remaining_time": "0:01:46"} +{"current_steps": 20, "total_steps": 41, "loss": 0.7223, "lr": 6.710100716628345e-06, "epoch": 0.4968944099378882, "percentage": 48.78, "elapsed_time": "0:01:37", "remaining_time": "0:01:41"} +{"current_steps": 21, "total_steps": 41, "loss": 0.6406, "lr": 6.294095225512604e-06, "epoch": 0.5217391304347826, "percentage": 51.22, "elapsed_time": "0:01:42", "remaining_time": "0:01:37"} +{"current_steps": 22, "total_steps": 41, "loss": 0.7979, "lr": 5.8682408883346535e-06, "epoch": 0.546583850931677, "percentage": 53.66, "elapsed_time": "0:01:46", "remaining_time": "0:01:32"} +{"current_steps": 23, "total_steps": 41, "loss": 0.6265, "lr": 5.435778713738292e-06, "epoch": 0.5714285714285714, "percentage": 56.1, "elapsed_time": "0:01:51", "remaining_time": "0:01:26"} +{"current_steps": 24, "total_steps": 41, "loss": 0.6584, "lr": 5e-06, "epoch": 0.5962732919254659, "percentage": 58.54, "elapsed_time": "0:01:55", "remaining_time": "0:01:21"} +{"current_steps": 25, "total_steps": 41, "loss": 0.7447, "lr": 4.564221286261709e-06, "epoch": 0.6211180124223602, "percentage": 60.98, "elapsed_time": "0:02:00", "remaining_time": "0:01:16"} +{"current_steps": 26, "total_steps": 41, "loss": 0.7641, "lr": 4.131759111665349e-06, "epoch": 0.6459627329192547, "percentage": 63.41, "elapsed_time": "0:02:04", "remaining_time": "0:01:11"} +{"current_steps": 27, "total_steps": 41, "loss": 0.6721, "lr": 3.705904774487396e-06, "epoch": 0.6708074534161491, "percentage": 65.85, "elapsed_time": "0:02:09", "remaining_time": "0:01:06"} +{"current_steps": 28, "total_steps": 41, "loss": 0.7569, "lr": 3.289899283371657e-06, "epoch": 0.6956521739130435, "percentage": 68.29, "elapsed_time": "0:02:13", "remaining_time": "0:01:01"} +{"current_steps": 29, "total_steps": 41, "loss": 0.7, "lr": 2.886908691296504e-06, "epoch": 0.7204968944099379, "percentage": 70.73, "elapsed_time": "0:02:17", "remaining_time": "0:00:57"} +{"current_steps": 30, "total_steps": 41, "loss": 0.6907, "lr": 2.5000000000000015e-06, "epoch": 0.7453416149068323, "percentage": 73.17, "elapsed_time": "0:02:21", "remaining_time": "0:00:51"} +{"current_steps": 31, "total_steps": 41, "loss": 0.5626, "lr": 2.132117818244771e-06, "epoch": 0.7701863354037267, "percentage": 75.61, "elapsed_time": "0:02:25", "remaining_time": "0:00:46"} +{"current_steps": 32, "total_steps": 41, "loss": 0.7463, "lr": 1.7860619515673034e-06, "epoch": 0.7950310559006211, "percentage": 78.05, "elapsed_time": "0:02:28", "remaining_time": "0:00:41"} +{"current_steps": 33, "total_steps": 41, "loss": 0.6265, "lr": 1.4644660940672628e-06, "epoch": 0.8198757763975155, "percentage": 80.49, "elapsed_time": "0:02:32", "remaining_time": "0:00:36"} +{"current_steps": 34, "total_steps": 41, "loss": 0.7379, "lr": 1.1697777844051105e-06, "epoch": 0.84472049689441, "percentage": 82.93, "elapsed_time": "0:02:36", "remaining_time": "0:00:32"} +{"current_steps": 35, "total_steps": 41, "loss": 0.5555, "lr": 9.042397785550405e-07, "epoch": 0.8695652173913043, "percentage": 85.37, "elapsed_time": "0:02:40", "remaining_time": "0:00:27"} +{"current_steps": 36, "total_steps": 41, "loss": 0.7681, "lr": 6.698729810778065e-07, "epoch": 0.8944099378881988, "percentage": 87.8, "elapsed_time": "0:02:43", "remaining_time": "0:00:22"} +{"current_steps": 37, "total_steps": 41, "loss": 0.7249, "lr": 4.6846106481675035e-07, "epoch": 0.9192546583850931, "percentage": 90.24, "elapsed_time": "0:02:47", "remaining_time": "0:00:18"} +{"current_steps": 38, "total_steps": 41, "loss": 0.5846, "lr": 3.015368960704584e-07, "epoch": 0.9440993788819876, "percentage": 92.68, "elapsed_time": "0:02:50", "remaining_time": "0:00:13"} +{"current_steps": 39, "total_steps": 41, "loss": 0.7607, "lr": 1.7037086855465902e-07, "epoch": 0.968944099378882, "percentage": 95.12, "elapsed_time": "0:02:54", "remaining_time": "0:00:08"} +{"current_steps": 40, "total_steps": 41, "loss": 0.7828, "lr": 7.59612349389599e-08, "epoch": 0.9937888198757764, "percentage": 97.56, "elapsed_time": "0:02:58", "remaining_time": "0:00:04"} +{"current_steps": 41, "total_steps": 41, "loss": 0.1798, "lr": 1.9026509541272276e-08, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:02:59", "remaining_time": "0:00:00"} +{"current_steps": 41, "total_steps": 41, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:42", "remaining_time": "0:00:00"} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..d9e2146 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,330 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 41, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.024844720496894408, + "grad_norm": 25.944225311279297, + "learning_rate": 0.0, + "loss": 2.5711, + "step": 1 + }, + { + "epoch": 0.049689440993788817, + "grad_norm": 25.800203323364258, + "learning_rate": 2.0000000000000003e-06, + "loss": 2.6176, + "step": 2 + }, + { + "epoch": 0.07453416149068323, + "grad_norm": 26.629310607910156, + "learning_rate": 4.000000000000001e-06, + "loss": 2.5861, + "step": 3 + }, + { + "epoch": 0.09937888198757763, + "grad_norm": 23.926393508911133, + "learning_rate": 6e-06, + "loss": 2.449, + "step": 4 + }, + { + "epoch": 0.12422360248447205, + "grad_norm": 25.569169998168945, + "learning_rate": 8.000000000000001e-06, + "loss": 2.1501, + "step": 5 + }, + { + "epoch": 0.14906832298136646, + "grad_norm": 12.590336799621582, + "learning_rate": 1e-05, + "loss": 1.6997, + "step": 6 + }, + { + "epoch": 0.17391304347826086, + "grad_norm": 13.70421314239502, + "learning_rate": 9.980973490458728e-06, + "loss": 1.6168, + "step": 7 + }, + { + "epoch": 0.19875776397515527, + "grad_norm": 19.300262451171875, + "learning_rate": 9.924038765061042e-06, + "loss": 1.4418, + "step": 8 + }, + { + "epoch": 0.2236024844720497, + "grad_norm": 9.026307106018066, + "learning_rate": 9.829629131445342e-06, + "loss": 1.3728, + "step": 9 + }, + { + "epoch": 0.2484472049689441, + "grad_norm": 10.970627784729004, + "learning_rate": 9.698463103929542e-06, + "loss": 1.1993, + "step": 10 + }, + { + "epoch": 0.2732919254658385, + "grad_norm": 24.517372131347656, + "learning_rate": 9.531538935183252e-06, + "loss": 1.1649, + "step": 11 + }, + { + "epoch": 0.2981366459627329, + "grad_norm": 8.326200485229492, + "learning_rate": 9.330127018922195e-06, + "loss": 0.9107, + "step": 12 + }, + { + "epoch": 0.32298136645962733, + "grad_norm": 7.975063800811768, + "learning_rate": 9.09576022144496e-06, + "loss": 1.1491, + "step": 13 + }, + { + "epoch": 0.34782608695652173, + "grad_norm": 8.031881332397461, + "learning_rate": 8.83022221559489e-06, + "loss": 1.1275, + "step": 14 + }, + { + "epoch": 0.37267080745341613, + "grad_norm": 7.613478660583496, + "learning_rate": 8.535533905932739e-06, + "loss": 0.9593, + "step": 15 + }, + { + "epoch": 0.39751552795031053, + "grad_norm": 6.6011786460876465, + "learning_rate": 8.213938048432697e-06, + "loss": 0.8073, + "step": 16 + }, + { + "epoch": 0.422360248447205, + "grad_norm": 7.115065574645996, + "learning_rate": 7.86788218175523e-06, + "loss": 0.9254, + "step": 17 + }, + { + "epoch": 0.4472049689440994, + "grad_norm": 7.958808422088623, + "learning_rate": 7.500000000000001e-06, + "loss": 0.7109, + "step": 18 + }, + { + "epoch": 0.4720496894409938, + "grad_norm": 6.170507431030273, + "learning_rate": 7.113091308703498e-06, + "loss": 0.8236, + "step": 19 + }, + { + "epoch": 0.4968944099378882, + "grad_norm": 24.92851448059082, + "learning_rate": 6.710100716628345e-06, + "loss": 0.7223, + "step": 20 + }, + { + "epoch": 0.5217391304347826, + "grad_norm": 9.233124732971191, + "learning_rate": 6.294095225512604e-06, + "loss": 0.6406, + "step": 21 + }, + { + "epoch": 0.546583850931677, + "grad_norm": 10.176820755004883, + "learning_rate": 5.8682408883346535e-06, + "loss": 0.7979, + "step": 22 + }, + { + "epoch": 0.5714285714285714, + "grad_norm": 5.572312831878662, + "learning_rate": 5.435778713738292e-06, + "loss": 0.6265, + "step": 23 + }, + { + "epoch": 0.5962732919254659, + "grad_norm": 6.122556686401367, + "learning_rate": 5e-06, + "loss": 0.6584, + "step": 24 + }, + { + "epoch": 0.6211180124223602, + "grad_norm": 9.502265930175781, + "learning_rate": 4.564221286261709e-06, + "loss": 0.7447, + "step": 25 + }, + { + "epoch": 0.6459627329192547, + "grad_norm": 6.603946685791016, + "learning_rate": 4.131759111665349e-06, + "loss": 0.7641, + "step": 26 + }, + { + "epoch": 0.6708074534161491, + "grad_norm": 5.79754114151001, + "learning_rate": 3.705904774487396e-06, + "loss": 0.6721, + "step": 27 + }, + { + "epoch": 0.6956521739130435, + "grad_norm": 6.924298286437988, + "learning_rate": 3.289899283371657e-06, + "loss": 0.7569, + "step": 28 + }, + { + "epoch": 0.7204968944099379, + "grad_norm": 5.339048385620117, + "learning_rate": 2.886908691296504e-06, + "loss": 0.7, + "step": 29 + }, + { + "epoch": 0.7453416149068323, + "grad_norm": 10.632051467895508, + "learning_rate": 2.5000000000000015e-06, + "loss": 0.6907, + "step": 30 + }, + { + "epoch": 0.7701863354037267, + "grad_norm": 12.731398582458496, + "learning_rate": 2.132117818244771e-06, + "loss": 0.5626, + "step": 31 + }, + { + "epoch": 0.7950310559006211, + "grad_norm": 19.54654312133789, + "learning_rate": 1.7860619515673034e-06, + "loss": 0.7463, + "step": 32 + }, + { + "epoch": 0.8198757763975155, + "grad_norm": 4.928001403808594, + "learning_rate": 1.4644660940672628e-06, + "loss": 0.6265, + "step": 33 + }, + { + "epoch": 0.84472049689441, + "grad_norm": 6.796016693115234, + "learning_rate": 1.1697777844051105e-06, + "loss": 0.7379, + "step": 34 + }, + { + "epoch": 0.8695652173913043, + "grad_norm": 5.8230204582214355, + "learning_rate": 9.042397785550405e-07, + "loss": 0.5555, + "step": 35 + }, + { + "epoch": 0.8944099378881988, + "grad_norm": 8.123178482055664, + "learning_rate": 6.698729810778065e-07, + "loss": 0.7681, + "step": 36 + }, + { + "epoch": 0.9192546583850931, + "grad_norm": 7.072976112365723, + "learning_rate": 4.6846106481675035e-07, + "loss": 0.7249, + "step": 37 + }, + { + "epoch": 0.9440993788819876, + "grad_norm": 5.121836185455322, + "learning_rate": 3.015368960704584e-07, + "loss": 0.5846, + "step": 38 + }, + { + "epoch": 0.968944099378882, + "grad_norm": 7.06396484375, + "learning_rate": 1.7037086855465902e-07, + "loss": 0.7607, + "step": 39 + }, + { + "epoch": 0.9937888198757764, + "grad_norm": 7.021341323852539, + "learning_rate": 7.59612349389599e-08, + "loss": 0.7828, + "step": 40 + }, + { + "epoch": 1.0, + "grad_norm": 7.021341323852539, + "learning_rate": 1.9026509541272276e-08, + "loss": 0.1798, + "step": 41 + }, + { + "epoch": 1.0, + "step": 41, + "total_flos": 9533860949786624.0, + "train_loss": 1.0508991407185067, + "train_runtime": 222.7751, + "train_samples_per_second": 2.891, + "train_steps_per_second": 0.184 + } + ], + "logging_steps": 1, + "max_steps": 41, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 100, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 9533860949786624.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..1ebf505 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee534e93e024c641525e340f202f4633b09e4f14854b672b576a12ffa8c1e8f +size 7480 diff --git a/training_loss.png b/training_loss.png new file mode 100644 index 0000000..53b671f Binary files /dev/null and b/training_loss.png differ diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000..b64d80b --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,86 @@ +{ + "_valid_kwargs_names": [ + "do_convert_rgb", + "do_resize", + "size", + "size_divisor", + "default_to_square", + "resample", + "do_rescale", + "rescale_factor", + "do_normalize", + "image_mean", + "image_std", + "do_pad", + "do_center_crop", + "crop_size", + "data_format", + "input_data_format", + "device", + "min_pixels", + "max_pixels", + "patch_size", + "temporal_patch_size", + "merge_size" + ], + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "input_data_format": null, + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "model_valid_processing_keys": [ + "do_convert_rgb", + "do_resize", + "size", + "size_divisor", + "default_to_square", + "resample", + "do_rescale", + "rescale_factor", + "do_normalize", + "image_mean", + "image_std", + "do_pad", + "do_center_crop", + "crop_size", + "data_format", + "input_data_format", + "device", + "min_pixels", + "max_pixels", + "patch_size", + "temporal_patch_size", + "merge_size" + ], + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "size_divisor": null, + "temporal_patch_size": 2, + "video_processor_type": "Qwen2VLVideoProcessor" +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833