LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: LMMs-Lab-Turtle/Qwen-2.5VL-3B-Cold-Start
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-19 19:26:54 +08:00
commit 3c48792196
21 changed files with 152887 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt 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
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz 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
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl 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
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* 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
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-VL-3B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: Qwen2.5-VL-3B-Instruct
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# Qwen2.5-VL-3B-Instruct
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) on the mllm_data1_cotOnly and the mllm_data1_description_val_text_only datasets.
## 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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.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: 3.0
### Training results
### Framework versions
- Transformers 4.49.0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1

24
added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 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
}

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.957983193277311,
"total_flos": 92447203917824.0,
"train_loss": 0.6085002004763501,
"train_runtime": 1135.371,
"train_samples_per_second": 20.124,
"train_steps_per_second": 0.156
}

3
chat_template.json Normal file
View File

@@ -0,0 +1,3 @@
{
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
}

51
config.json Normal file
View File

@@ -0,0 +1,51 @@
{
"_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
"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,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.49.0",
"use_cache": false,
"use_sliding_window": false,
"video_token_id": 151656,
"vision_config": {
"hidden_size": 1280,
"in_chans": 3,
"model_type": "qwen2_5_vl",
"out_hidden_size": 2048,
"spatial_patch_size": 14,
"tokens_per_second": 2,
"torch_dtype": "float32"
},
"vision_end_token_id": 151653,
"vision_start_token_id": 151652,
"vision_token_id": 151654,
"vocab_size": 151936
}

12
generation_config.json Normal file
View File

@@ -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": "4.49.0"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3ba88e4a85ec40aa5a4f494cb032cbf89d2e6508b289803d9de772e30958291
size 4997750760

3
model-00002-of-00002.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aded00e3fb717ce9941efedaa16e8bbfeb5a2785c3e0a27272d419a8e5576534
size 2511587184

831
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,831 @@
{
"metadata": {
"total_size": 7509245952
},
"weight_map": {
"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"
}
}

32
preprocessor_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"crop_size": null,
"default_to_square": true,
"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
],
"max_pixels": 12845056,
"merge_size": 2,
"min_pixels": 3136,
"patch_size": 14,
"processor_class": "Qwen2_5_VLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"size": {
"longest_edge": 1003520,
"shortest_edge": 3136
},
"temporal_patch_size": 2
}

31
special_tokens_map.json Normal file
View File

@@ -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
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896

210
tokenizer_config.json Normal file
View File

@@ -0,0 +1,210 @@
{
"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": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"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,
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"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
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.957983193277311,
"total_flos": 92447203917824.0,
"train_loss": 0.6085002004763501,
"train_runtime": 1135.371,
"train_samples_per_second": 20.124,
"train_steps_per_second": 0.156
}

18
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,18 @@
{"current_steps": 10, "total_steps": 177, "loss": 0.8834, "lr": 5.555555555555557e-06, "epoch": 0.16806722689075632, "percentage": 5.65, "elapsed_time": "0:01:07", "remaining_time": "0:18:45"}
{"current_steps": 20, "total_steps": 177, "loss": 0.832, "lr": 9.99609654676786e-06, "epoch": 0.33613445378151263, "percentage": 11.3, "elapsed_time": "0:02:15", "remaining_time": "0:17:41"}
{"current_steps": 30, "total_steps": 177, "loss": 0.7929, "lr": 9.860114570402055e-06, "epoch": 0.5042016806722689, "percentage": 16.95, "elapsed_time": "0:03:19", "remaining_time": "0:16:19"}
{"current_steps": 40, "total_steps": 177, "loss": 0.7613, "lr": 9.535012074008688e-06, "epoch": 0.6722689075630253, "percentage": 22.6, "elapsed_time": "0:04:18", "remaining_time": "0:14:46"}
{"current_steps": 50, "total_steps": 177, "loss": 0.7369, "lr": 9.033439696227966e-06, "epoch": 0.8403361344537815, "percentage": 28.25, "elapsed_time": "0:05:20", "remaining_time": "0:13:33"}
{"current_steps": 60, "total_steps": 177, "loss": 0.6853, "lr": 8.374915007591053e-06, "epoch": 1.0, "percentage": 33.9, "elapsed_time": "0:06:18", "remaining_time": "0:12:17"}
{"current_steps": 70, "total_steps": 177, "loss": 0.6288, "lr": 7.58506302778873e-06, "epoch": 1.1680672268907564, "percentage": 39.55, "elapsed_time": "0:07:23", "remaining_time": "0:11:17"}
{"current_steps": 80, "total_steps": 177, "loss": 0.5971, "lr": 6.694619085176159e-06, "epoch": 1.3361344537815127, "percentage": 45.2, "elapsed_time": "0:08:21", "remaining_time": "0:10:07"}
{"current_steps": 90, "total_steps": 177, "loss": 0.5633, "lr": 5.738232820012407e-06, "epoch": 1.504201680672269, "percentage": 50.85, "elapsed_time": "0:09:27", "remaining_time": "0:09:08"}
{"current_steps": 100, "total_steps": 177, "loss": 0.5586, "lr": 4.753119870981486e-06, "epoch": 1.6722689075630253, "percentage": 56.5, "elapsed_time": "0:10:28", "remaining_time": "0:08:04"}
{"current_steps": 110, "total_steps": 177, "loss": 0.5633, "lr": 3.777613711607087e-06, "epoch": 1.8403361344537816, "percentage": 62.15, "elapsed_time": "0:11:30", "remaining_time": "0:07:00"}
{"current_steps": 120, "total_steps": 177, "loss": 0.5249, "lr": 2.8496739886173994e-06, "epoch": 2.0, "percentage": 67.8, "elapsed_time": "0:12:30", "remaining_time": "0:05:56"}
{"current_steps": 130, "total_steps": 177, "loss": 0.4774, "lr": 2.005409406946e-06, "epoch": 2.168067226890756, "percentage": 73.45, "elapsed_time": "0:13:35", "remaining_time": "0:04:54"}
{"current_steps": 140, "total_steps": 177, "loss": 0.4569, "lr": 1.277672640004936e-06, "epoch": 2.3361344537815127, "percentage": 79.1, "elapsed_time": "0:14:38", "remaining_time": "0:03:52"}
{"current_steps": 150, "total_steps": 177, "loss": 0.4598, "lr": 6.947819411632223e-07, "epoch": 2.504201680672269, "percentage": 84.75, "elapsed_time": "0:15:41", "remaining_time": "0:02:49"}
{"current_steps": 160, "total_steps": 177, "loss": 0.4533, "lr": 2.7941920206915443e-07, "epoch": 2.6722689075630255, "percentage": 90.4, "elapsed_time": "0:16:44", "remaining_time": "0:01:46"}
{"current_steps": 170, "total_steps": 177, "loss": 0.4608, "lr": 4.774733741942206e-08, "epoch": 2.8403361344537816, "percentage": 96.05, "elapsed_time": "0:17:48", "remaining_time": "0:00:43"}
{"current_steps": 177, "total_steps": 177, "epoch": 2.957983193277311, "percentage": 100.0, "elapsed_time": "0:18:55", "remaining_time": "0:00:00"}

161
trainer_state.json Normal file
View File

@@ -0,0 +1,161 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.957983193277311,
"eval_steps": 500,
"global_step": 177,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.16806722689075632,
"grad_norm": 1.64210754465846,
"learning_rate": 5.555555555555557e-06,
"loss": 0.8834,
"step": 10
},
{
"epoch": 0.33613445378151263,
"grad_norm": 1.6216633128454179,
"learning_rate": 9.99609654676786e-06,
"loss": 0.832,
"step": 20
},
{
"epoch": 0.5042016806722689,
"grad_norm": 1.0890026008565015,
"learning_rate": 9.860114570402055e-06,
"loss": 0.7929,
"step": 30
},
{
"epoch": 0.6722689075630253,
"grad_norm": 0.9852931548778409,
"learning_rate": 9.535012074008688e-06,
"loss": 0.7613,
"step": 40
},
{
"epoch": 0.8403361344537815,
"grad_norm": 1.0010829198190254,
"learning_rate": 9.033439696227966e-06,
"loss": 0.7369,
"step": 50
},
{
"epoch": 1.0,
"grad_norm": 0.9912119135873784,
"learning_rate": 8.374915007591053e-06,
"loss": 0.6853,
"step": 60
},
{
"epoch": 1.1680672268907564,
"grad_norm": 0.9598316653212201,
"learning_rate": 7.58506302778873e-06,
"loss": 0.6288,
"step": 70
},
{
"epoch": 1.3361344537815127,
"grad_norm": 0.9969526888332303,
"learning_rate": 6.694619085176159e-06,
"loss": 0.5971,
"step": 80
},
{
"epoch": 1.504201680672269,
"grad_norm": 5.712426354685314,
"learning_rate": 5.738232820012407e-06,
"loss": 0.5633,
"step": 90
},
{
"epoch": 1.6722689075630253,
"grad_norm": 0.8053877541293872,
"learning_rate": 4.753119870981486e-06,
"loss": 0.5586,
"step": 100
},
{
"epoch": 1.8403361344537816,
"grad_norm": 0.9085557253419428,
"learning_rate": 3.777613711607087e-06,
"loss": 0.5633,
"step": 110
},
{
"epoch": 2.0,
"grad_norm": 0.9125623622985397,
"learning_rate": 2.8496739886173994e-06,
"loss": 0.5249,
"step": 120
},
{
"epoch": 2.168067226890756,
"grad_norm": 0.9796403145730364,
"learning_rate": 2.005409406946e-06,
"loss": 0.4774,
"step": 130
},
{
"epoch": 2.3361344537815127,
"grad_norm": 0.8379009664030831,
"learning_rate": 1.277672640004936e-06,
"loss": 0.4569,
"step": 140
},
{
"epoch": 2.504201680672269,
"grad_norm": 0.912579146579012,
"learning_rate": 6.947819411632223e-07,
"loss": 0.4598,
"step": 150
},
{
"epoch": 2.6722689075630255,
"grad_norm": 0.8570497984949336,
"learning_rate": 2.7941920206915443e-07,
"loss": 0.4533,
"step": 160
},
{
"epoch": 2.8403361344537816,
"grad_norm": 0.913025927962694,
"learning_rate": 4.774733741942206e-08,
"loss": 0.4608,
"step": 170
},
{
"epoch": 2.957983193277311,
"step": 177,
"total_flos": 92447203917824.0,
"train_loss": 0.6085002004763501,
"train_runtime": 1135.371,
"train_samples_per_second": 20.124,
"train_steps_per_second": 0.156
}
],
"logging_steps": 10,
"max_steps": 177,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 92447203917824.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:68bed477eab3e27b189bc05a6761a0a4012e9297a2ff7b153f90f873dca3ed4b
size 8081

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 38 KiB

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long