初始化项目，由ModelHub XC社区提供模型
Model: iSEE-Laboratory/love-r1-stage3 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal 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
|
||||
20
README.md
Normal file
20
README.md
Normal file
@@ -0,0 +1,20 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-VL-7B-Instruct
|
||||
---
|
||||
|
||||
This repository contains the model of the paper [LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning](https://arxiv.org/abs/2509.24786).
|
||||
|
||||
Code: https://github.com/HumanMLLM/LOVE-R1
|
||||
|
||||
If you find our work helpful for your research, please consider citing our paper.
|
||||
|
||||
```
|
||||
@article{fu2025lover1,
|
||||
title={LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning},
|
||||
author={Fu, Shenghao and Yang, Qize and Li, Yuan-Ming and Wei, Xihan and Xie, Xiaohua and Zheng, Wei-Shi},
|
||||
journal={arXiv preprint arXiv:2509.24786},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal 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
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal 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 %}"
|
||||
}
|
||||
50
config.json
Normal file
50
config.json
Normal file
@@ -0,0 +1,50 @@
|
||||
{
|
||||
"_name_or_path": "/mnt/data1/shenghao/M-CoT_3/src/r1-v/log/Qwen2.5-VL-7B-GRPO20/checkpoint-384",
|
||||
"architectures": [
|
||||
"Qwen2_5_VLForConditionalGeneration"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"image_token_id": 151655,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 128000,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2_5_vl",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"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": false,
|
||||
"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",
|
||||
"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": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"attn_implementation": "flash_attention_2",
|
||||
"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",
|
||||
"use_cache": false
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2ecf7f81569198c3f415a941608e38ea31b71bf313adbc3e793d0b91875163c4
|
||||
size 4968243304
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:543e2058117b33849f806b24c3ecb41d6768050486d8fa8537782c0e61674511
|
||||
size 4991495816
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:32d5aae336e68135ac7d86f5f540f5d90b8f2edd76222f01acfffe82f8ff0894
|
||||
size 4932751040
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1d0f7849fb8dd5e0f6dddc4608e2b4f0f58d9b8a26ac498e2124bdb72702af5e
|
||||
size 1691924384
|
||||
736
model.safetensors.index.json
Normal file
736
model.safetensors.index.json
Normal file
@@ -0,0 +1,736 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16584333312
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
|
||||
"visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
|
||||
"visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
29
preprocessor_config.json
Normal file
29
preprocessor_config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"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
|
||||
],
|
||||
"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": 12845056,
|
||||
"shortest_edge": 3136
|
||||
},
|
||||
"temporal_patch_size": 2
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal 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
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
|
||||
size 11422063
|
||||
213
tokenizer_config.json
Normal file
213
tokenizer_config.json
Normal file
@@ -0,0 +1,213 @@
|
||||
{
|
||||
"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": {},
|
||||
"max_length": null,
|
||||
"model_max_length": 131072,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "right",
|
||||
"processor_class": "Qwen2_5_VLProcessor",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
561
trainer_state.json
Normal file
561
trainer_state.json
Normal file
@@ -0,0 +1,561 @@
|
||||
{
|
||||
"best_metric": null,
|
||||
"best_model_checkpoint": null,
|
||||
"epoch": 0.057279236276849645,
|
||||
"eval_steps": 500,
|
||||
"global_step": 48,
|
||||
"is_hyper_param_search": false,
|
||||
"is_local_process_zero": true,
|
||||
"is_world_process_zero": true,
|
||||
"log_history": [
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12863.0,
|
||||
"completions/max_terminated_length": 12863.0,
|
||||
"completions/mean_length": 10745.375,
|
||||
"completions/mean_terminated_length": 10745.375,
|
||||
"completions/min_length": 8883.0,
|
||||
"completions/min_terminated_length": 8883.0,
|
||||
"epoch": 0.0011933174224343676,
|
||||
"grad_norm": 0.6463546752929688,
|
||||
"is_mask": 0.84375,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.999964864089826e-07,
|
||||
"loss": -0.0221,
|
||||
"num_tokens": 285255.0,
|
||||
"reward": 0.75,
|
||||
"reward_std": 0.8457233309745789,
|
||||
"rewards/accuracy_reward/mean": 0.09375,
|
||||
"rewards/accuracy_reward/std": 0.2961445748806,
|
||||
"rewards/format_reward/mean": 0.5,
|
||||
"rewards/format_reward/std": 0.5080004930496216,
|
||||
"step": 1
|
||||
},
|
||||
{
|
||||
"epoch": 0.002386634844868735,
|
||||
"grad_norm": 0.8406618237495422,
|
||||
"learning_rate": 9.999859456853114e-07,
|
||||
"loss": 0.0001,
|
||||
"step": 2
|
||||
},
|
||||
{
|
||||
"epoch": 0.003579952267303103,
|
||||
"grad_norm": 0.760502815246582,
|
||||
"learning_rate": 9.9996837797713e-07,
|
||||
"loss": -0.0221,
|
||||
"step": 3
|
||||
},
|
||||
{
|
||||
"epoch": 0.00477326968973747,
|
||||
"grad_norm": 0.9957342743873596,
|
||||
"learning_rate": 9.999437835313409e-07,
|
||||
"loss": -0.0221,
|
||||
"step": 4
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12883.0,
|
||||
"completions/max_terminated_length": 12883.0,
|
||||
"completions/mean_length": 10608.40625,
|
||||
"completions/mean_terminated_length": 10608.40625,
|
||||
"completions/min_length": 8903.0,
|
||||
"completions/min_terminated_length": 8903.0,
|
||||
"epoch": 0.0059665871121718375,
|
||||
"grad_norm": 0.0,
|
||||
"is_mask": 0.875,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.999121626936037e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 571454.0,
|
||||
"reward": 0.53125,
|
||||
"reward_std": 0.5971629619598389,
|
||||
"rewards/accuracy_reward/mean": 0.0,
|
||||
"rewards/accuracy_reward/std": 0.0,
|
||||
"rewards/format_reward/mean": 0.46875,
|
||||
"rewards/format_reward/std": 0.507007360458374,
|
||||
"step": 5
|
||||
},
|
||||
{
|
||||
"epoch": 0.007159904534606206,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.998735159083292e-07,
|
||||
"loss": 0.0,
|
||||
"step": 6
|
||||
},
|
||||
{
|
||||
"epoch": 0.008353221957040573,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.998278437186732e-07,
|
||||
"loss": 0.0,
|
||||
"step": 7
|
||||
},
|
||||
{
|
||||
"epoch": 0.00954653937947494,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.997751467665294e-07,
|
||||
"loss": 0.0,
|
||||
"step": 8
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 13108.0,
|
||||
"completions/max_terminated_length": 13108.0,
|
||||
"completions/mean_length": 11084.09375,
|
||||
"completions/mean_terminated_length": 11084.09375,
|
||||
"completions/min_length": 8894.0,
|
||||
"completions/min_terminated_length": 8894.0,
|
||||
"epoch": 0.010739856801909307,
|
||||
"grad_norm": 0.934722363948822,
|
||||
"is_mask": 0.8125,
|
||||
"is_sample": 0.96875,
|
||||
"learning_rate": 9.997154257925197e-07,
|
||||
"loss": -0.0,
|
||||
"num_tokens": 858170.0,
|
||||
"reward": 1.09375,
|
||||
"reward_std": 0.6487956643104553,
|
||||
"rewards/accuracy_reward/mean": 0.09375,
|
||||
"rewards/accuracy_reward/std": 0.2961445748806,
|
||||
"rewards/format_reward/mean": 0.6875,
|
||||
"rewards/format_reward/std": 0.4709290862083435,
|
||||
"step": 9
|
||||
},
|
||||
{
|
||||
"epoch": 0.011933174224343675,
|
||||
"grad_norm": 0.9142937064170837,
|
||||
"learning_rate": 9.99648681635985e-07,
|
||||
"loss": 0.0002,
|
||||
"step": 10
|
||||
},
|
||||
{
|
||||
"epoch": 0.013126491646778043,
|
||||
"grad_norm": 0.8181187510490417,
|
||||
"learning_rate": 9.995749152349713e-07,
|
||||
"loss": 0.0001,
|
||||
"step": 11
|
||||
},
|
||||
{
|
||||
"epoch": 0.014319809069212411,
|
||||
"grad_norm": 1.1284211874008179,
|
||||
"learning_rate": 9.994941276262188e-07,
|
||||
"loss": -0.0002,
|
||||
"step": 12
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12847.0,
|
||||
"completions/max_terminated_length": 12847.0,
|
||||
"completions/mean_length": 10575.90625,
|
||||
"completions/mean_terminated_length": 10575.90625,
|
||||
"completions/min_length": 8888.0,
|
||||
"completions/min_terminated_length": 8888.0,
|
||||
"epoch": 0.015513126491646777,
|
||||
"grad_norm": 0.8638948202133179,
|
||||
"is_mask": 0.71875,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.99406319945146e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 1144312.0,
|
||||
"reward": 1.03125,
|
||||
"reward_std": 0.6127826571464539,
|
||||
"rewards/accuracy_reward/mean": 0.1875,
|
||||
"rewards/accuracy_reward/std": 0.3965577781200409,
|
||||
"rewards/format_reward/mean": 0.5625,
|
||||
"rewards/format_reward/std": 0.504016101360321,
|
||||
"step": 13
|
||||
},
|
||||
{
|
||||
"epoch": 0.016706443914081145,
|
||||
"grad_norm": 0.9017719626426697,
|
||||
"learning_rate": 9.99311493425834e-07,
|
||||
"loss": -0.0001,
|
||||
"step": 14
|
||||
},
|
||||
{
|
||||
"epoch": 0.017899761336515514,
|
||||
"grad_norm": 0.8770928978919983,
|
||||
"learning_rate": 9.99209649401009e-07,
|
||||
"loss": 0.0002,
|
||||
"step": 15
|
||||
},
|
||||
{
|
||||
"epoch": 0.01909307875894988,
|
||||
"grad_norm": 1.0520905256271362,
|
||||
"learning_rate": 9.99100789302024e-07,
|
||||
"loss": 0.0002,
|
||||
"step": 16
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12937.0,
|
||||
"completions/max_terminated_length": 12937.0,
|
||||
"completions/mean_length": 10770.40625,
|
||||
"completions/mean_terminated_length": 10770.40625,
|
||||
"completions/min_length": 8897.0,
|
||||
"completions/min_terminated_length": 8897.0,
|
||||
"epoch": 0.02028639618138425,
|
||||
"grad_norm": 0.0,
|
||||
"is_mask": 0.84375,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.98984914658839e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 1430298.0,
|
||||
"reward": 0.75,
|
||||
"reward_std": 0.7129100561141968,
|
||||
"rewards/accuracy_reward/mean": 0.09375,
|
||||
"rewards/accuracy_reward/std": 0.2961445748806,
|
||||
"rewards/format_reward/mean": 0.5625,
|
||||
"rewards/format_reward/std": 0.504016101360321,
|
||||
"step": 17
|
||||
},
|
||||
{
|
||||
"epoch": 0.021479713603818614,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.988620270999978e-07,
|
||||
"loss": 0.0,
|
||||
"step": 18
|
||||
},
|
||||
{
|
||||
"epoch": 0.022673031026252982,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.98732128352607e-07,
|
||||
"loss": 0.0,
|
||||
"step": 19
|
||||
},
|
||||
{
|
||||
"epoch": 0.02386634844868735,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.985952202423114e-07,
|
||||
"loss": 0.0,
|
||||
"step": 20
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12980.0,
|
||||
"completions/max_terminated_length": 12980.0,
|
||||
"completions/mean_length": 10494.15625,
|
||||
"completions/mean_terminated_length": 10494.15625,
|
||||
"completions/min_length": 8879.0,
|
||||
"completions/min_terminated_length": 8879.0,
|
||||
"epoch": 0.025059665871121718,
|
||||
"grad_norm": 0.7287543416023254,
|
||||
"is_mask": 0.75,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.98451304693267e-07,
|
||||
"loss": -0.0361,
|
||||
"num_tokens": 1716335.0,
|
||||
"reward": 0.84375,
|
||||
"reward_std": 0.7163528203964233,
|
||||
"rewards/accuracy_reward/mean": 0.09375,
|
||||
"rewards/accuracy_reward/std": 0.2961445748806,
|
||||
"rewards/format_reward/mean": 0.59375,
|
||||
"rewards/format_reward/std": 0.49899089336395264,
|
||||
"step": 21
|
||||
},
|
||||
{
|
||||
"epoch": 0.026252983293556086,
|
||||
"grad_norm": 1.313971996307373,
|
||||
"learning_rate": 9.983003837281153e-07,
|
||||
"loss": 0.0,
|
||||
"step": 22
|
||||
},
|
||||
{
|
||||
"epoch": 0.027446300715990454,
|
||||
"grad_norm": 0.7719064950942993,
|
||||
"learning_rate": 9.981424594679544e-07,
|
||||
"loss": -0.0364,
|
||||
"step": 23
|
||||
},
|
||||
{
|
||||
"epoch": 0.028639618138424822,
|
||||
"grad_norm": 1.057080864906311,
|
||||
"learning_rate": 9.979775341323098e-07,
|
||||
"loss": -0.0365,
|
||||
"step": 24
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12923.0,
|
||||
"completions/max_terminated_length": 12923.0,
|
||||
"completions/mean_length": 10913.5625,
|
||||
"completions/mean_terminated_length": 10913.5625,
|
||||
"completions/min_length": 8888.0,
|
||||
"completions/min_terminated_length": 8888.0,
|
||||
"epoch": 0.029832935560859187,
|
||||
"grad_norm": 0.0,
|
||||
"is_mask": 0.75,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.978056100391016e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 2003376.0,
|
||||
"reward": 0.78125,
|
||||
"reward_std": 0.5361451506614685,
|
||||
"rewards/accuracy_reward/mean": 0.0625,
|
||||
"rewards/accuracy_reward/std": 0.24593468010425568,
|
||||
"rewards/format_reward/mean": 0.71875,
|
||||
"rewards/format_reward/std": 0.45680341124534607,
|
||||
"step": 25
|
||||
},
|
||||
{
|
||||
"epoch": 0.031026252983293555,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.976266896046142e-07,
|
||||
"loss": 0.0,
|
||||
"step": 26
|
||||
},
|
||||
{
|
||||
"epoch": 0.032219570405727926,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.974407753434602e-07,
|
||||
"loss": 0.0,
|
||||
"step": 27
|
||||
},
|
||||
{
|
||||
"epoch": 0.03341288782816229,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.972478698685462e-07,
|
||||
"loss": 0.0,
|
||||
"step": 28
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12984.0,
|
||||
"completions/max_terminated_length": 12984.0,
|
||||
"completions/mean_length": 10578.90625,
|
||||
"completions/mean_terminated_length": 10578.90625,
|
||||
"completions/min_length": 8891.0,
|
||||
"completions/min_terminated_length": 8891.0,
|
||||
"epoch": 0.034606205250596656,
|
||||
"grad_norm": 0.0,
|
||||
"is_mask": 0.875,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.970479758910363e-07,
|
||||
"loss": 0.0,
|
||||
"num_tokens": 2289897.0,
|
||||
"reward": 0.6875,
|
||||
"reward_std": 0.604997992515564,
|
||||
"rewards/accuracy_reward/mean": 0.09375,
|
||||
"rewards/accuracy_reward/std": 0.2961445748806,
|
||||
"rewards/format_reward/mean": 0.59375,
|
||||
"rewards/format_reward/std": 0.49899089336395264,
|
||||
"step": 29
|
||||
},
|
||||
{
|
||||
"epoch": 0.03579952267303103,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.96841096220313e-07,
|
||||
"loss": 0.0,
|
||||
"step": 30
|
||||
},
|
||||
{
|
||||
"epoch": 0.03699284009546539,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.966272337639385e-07,
|
||||
"loss": 0.0,
|
||||
"step": 31
|
||||
},
|
||||
{
|
||||
"epoch": 0.03818615751789976,
|
||||
"grad_norm": 0.0,
|
||||
"learning_rate": 9.96406391527614e-07,
|
||||
"loss": 0.0,
|
||||
"step": 32
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.03125,
|
||||
"completions/max_length": 12975.0,
|
||||
"completions/max_terminated_length": 12975.0,
|
||||
"completions/mean_length": 10250.5,
|
||||
"completions/mean_terminated_length": 10291.2255859375,
|
||||
"completions/min_length": 8905.0,
|
||||
"completions/min_terminated_length": 8905.0,
|
||||
"epoch": 0.03937947494033413,
|
||||
"grad_norm": 0.44783833622932434,
|
||||
"is_mask": 0.8125,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.961785726151362e-07,
|
||||
"loss": -0.0361,
|
||||
"num_tokens": 2577231.0,
|
||||
"reward": 0.6145833730697632,
|
||||
"reward_std": 0.667420506477356,
|
||||
"rewards/accuracy_reward/mean": 0.0625,
|
||||
"rewards/accuracy_reward/std": 0.24593468010425568,
|
||||
"rewards/format_reward/mean": 0.40625,
|
||||
"rewards/format_reward/std": 0.49899089336395264,
|
||||
"step": 33
|
||||
},
|
||||
{
|
||||
"epoch": 0.0405727923627685,
|
||||
"grad_norm": 0.9860613942146301,
|
||||
"learning_rate": 9.95943780228355e-07,
|
||||
"loss": -0.0001,
|
||||
"step": 34
|
||||
},
|
||||
{
|
||||
"epoch": 0.041766109785202864,
|
||||
"grad_norm": 0.440227746963501,
|
||||
"learning_rate": 9.957020176671287e-07,
|
||||
"loss": -0.0361,
|
||||
"step": 35
|
||||
},
|
||||
{
|
||||
"epoch": 0.04295942720763723,
|
||||
"grad_norm": 0.5511691570281982,
|
||||
"learning_rate": 9.954532883292758e-07,
|
||||
"loss": -0.036,
|
||||
"step": 36
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12907.0,
|
||||
"completions/max_terminated_length": 12907.0,
|
||||
"completions/mean_length": 10436.34375,
|
||||
"completions/mean_terminated_length": 10436.34375,
|
||||
"completions/min_length": 8886.0,
|
||||
"completions/min_terminated_length": 8886.0,
|
||||
"epoch": 0.0441527446300716,
|
||||
"grad_norm": 1.3848559856414795,
|
||||
"is_mask": 0.6875,
|
||||
"is_sample": 0.96875,
|
||||
"learning_rate": 9.951975957105292e-07,
|
||||
"loss": -0.0221,
|
||||
"num_tokens": 2862659.0,
|
||||
"reward": 0.65625,
|
||||
"reward_std": 0.5863522887229919,
|
||||
"rewards/accuracy_reward/mean": 0.0625,
|
||||
"rewards/accuracy_reward/std": 0.24593468010425568,
|
||||
"rewards/format_reward/mean": 0.53125,
|
||||
"rewards/format_reward/std": 0.507007360458374,
|
||||
"step": 37
|
||||
},
|
||||
{
|
||||
"epoch": 0.045346062052505964,
|
||||
"grad_norm": 1.3644936084747314,
|
||||
"learning_rate": 9.94934943404486e-07,
|
||||
"loss": -0.0,
|
||||
"step": 38
|
||||
},
|
||||
{
|
||||
"epoch": 0.046539379474940336,
|
||||
"grad_norm": 1.1380318403244019,
|
||||
"learning_rate": 9.946653351025574e-07,
|
||||
"loss": -0.022,
|
||||
"step": 39
|
||||
},
|
||||
{
|
||||
"epoch": 0.0477326968973747,
|
||||
"grad_norm": 1.575966715812683,
|
||||
"learning_rate": 9.943887745939163e-07,
|
||||
"loss": -0.0223,
|
||||
"step": 40
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 12842.0,
|
||||
"completions/max_terminated_length": 12842.0,
|
||||
"completions/mean_length": 10952.875,
|
||||
"completions/mean_terminated_length": 10952.875,
|
||||
"completions/min_length": 8886.0,
|
||||
"completions/min_terminated_length": 8886.0,
|
||||
"epoch": 0.04892601431980907,
|
||||
"grad_norm": 0.5767437815666199,
|
||||
"is_mask": 0.6875,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.941052657654451e-07,
|
||||
"loss": -0.0,
|
||||
"num_tokens": 3148683.0,
|
||||
"reward": 1.0625,
|
||||
"reward_std": 0.4053322970867157,
|
||||
"rewards/accuracy_reward/mean": 0.21875,
|
||||
"rewards/accuracy_reward/std": 0.420013427734375,
|
||||
"rewards/format_reward/mean": 0.75,
|
||||
"rewards/format_reward/std": 0.4399413466453552,
|
||||
"step": 41
|
||||
},
|
||||
{
|
||||
"epoch": 0.050119331742243436,
|
||||
"grad_norm": 0.5937145352363586,
|
||||
"learning_rate": 9.938148126016804e-07,
|
||||
"loss": -0.0002,
|
||||
"step": 42
|
||||
},
|
||||
{
|
||||
"epoch": 0.0513126491646778,
|
||||
"grad_norm": 0.6468254327774048,
|
||||
"learning_rate": 9.93517419184756e-07,
|
||||
"loss": 0.0002,
|
||||
"step": 43
|
||||
},
|
||||
{
|
||||
"epoch": 0.05250596658711217,
|
||||
"grad_norm": 0.6882703304290771,
|
||||
"learning_rate": 9.932130896943477e-07,
|
||||
"loss": 0.0003,
|
||||
"step": 44
|
||||
},
|
||||
{
|
||||
"completions/clipped_ratio": 0.0,
|
||||
"completions/max_length": 13055.0,
|
||||
"completions/max_terminated_length": 13055.0,
|
||||
"completions/mean_length": 10370.34375,
|
||||
"completions/mean_terminated_length": 10370.34375,
|
||||
"completions/min_length": 8880.0,
|
||||
"completions/min_terminated_length": 8880.0,
|
||||
"epoch": 0.05369928400954654,
|
||||
"grad_norm": 0.926037073135376,
|
||||
"is_mask": 0.65625,
|
||||
"is_sample": 1.0,
|
||||
"learning_rate": 9.929018284076127e-07,
|
||||
"loss": -0.085,
|
||||
"num_tokens": 3434802.0,
|
||||
"reward": 0.8854166865348816,
|
||||
"reward_std": 0.8571243286132812,
|
||||
"rewards/accuracy_reward/mean": 0.21875,
|
||||
"rewards/accuracy_reward/std": 0.420013427734375,
|
||||
"rewards/format_reward/mean": 0.6875,
|
||||
"rewards/format_reward/std": 0.4709290862083435,
|
||||
"step": 45
|
||||
},
|
||||
{
|
||||
"epoch": 0.05489260143198091,
|
||||
"grad_norm": 1.330098271369934,
|
||||
"learning_rate": 9.925836396991307e-07,
|
||||
"loss": 0.0001,
|
||||
"step": 46
|
||||
},
|
||||
{
|
||||
"epoch": 0.05608591885441527,
|
||||
"grad_norm": 0.9060226082801819,
|
||||
"learning_rate": 9.922585280408415e-07,
|
||||
"loss": -0.0855,
|
||||
"step": 47
|
||||
},
|
||||
{
|
||||
"epoch": 0.057279236276849645,
|
||||
"grad_norm": 1.2443565130233765,
|
||||
"learning_rate": 9.919264980019829e-07,
|
||||
"loss": -0.085,
|
||||
"step": 48
|
||||
}
|
||||
],
|
||||
"logging_steps": 1.0,
|
||||
"max_steps": 838,
|
||||
"num_input_tokens_seen": 3434802,
|
||||
"num_train_epochs": 1,
|
||||
"save_steps": 48,
|
||||
"stateful_callbacks": {
|
||||
"TrainerControl": {
|
||||
"args": {
|
||||
"should_epoch_stop": false,
|
||||
"should_evaluate": false,
|
||||
"should_log": false,
|
||||
"should_save": true,
|
||||
"should_training_stop": false
|
||||
},
|
||||
"attributes": {}
|
||||
}
|
||||
},
|
||||
"total_flos": 0.0,
|
||||
"train_batch_size": 1,
|
||||
"trial_name": null,
|
||||
"trial_params": null
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f25069dc600f44d5bfd9a47ca63ad7f40a1a578f5170670bc25340b8d83260ff
|
||||
size 8824
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
674
zero_to_fp32.py
Normal file
674
zero_to_fp32.py
Normal file
@@ -0,0 +1,674 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example:
|
||||
# python zero_to_fp32.py . output_dir/
|
||||
# or
|
||||
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
import json
|
||||
from tqdm import tqdm
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in files:
|
||||
state_dict = torch.load(f, map_location=device)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
if zero_stage <= 2:
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
elif zero_stage == 3:
|
||||
# if there is more than one param group, there will be multiple flattened tensors - one
|
||||
# flattened tensor per group - for simplicity merge them into a single tensor
|
||||
#
|
||||
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
||||
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
||||
|
||||
fp32_flat_groups = [
|
||||
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
||||
]
|
||||
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# XXX: memory usage doubles here
|
||||
state_dict[name] = torch.cat(
|
||||
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
||||
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
||||
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
||||
output_dir,
|
||||
max_shard_size="5GB",
|
||||
safe_serialization=False,
|
||||
tag=None,
|
||||
exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
||||
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
||||
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
# Dependency pre-check
|
||||
if safe_serialization:
|
||||
try:
|
||||
from safetensors.torch import save_file
|
||||
except ImportError:
|
||||
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
||||
raise
|
||||
if max_shard_size is not None:
|
||||
try:
|
||||
from huggingface_hub import split_torch_state_dict_into_shards
|
||||
except ImportError:
|
||||
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
||||
raise
|
||||
|
||||
# Convert zero checkpoint to state_dict
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
||||
|
||||
# Shard the model if it is too big.
|
||||
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
||||
if max_shard_size is not None:
|
||||
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
||||
state_dict_split = split_torch_state_dict_into_shards(state_dict,
|
||||
filename_pattern=filename_pattern,
|
||||
max_shard_size=max_shard_size)
|
||||
else:
|
||||
from collections import namedtuple
|
||||
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
||||
state_dict_split = StateDictSplit(is_sharded=False,
|
||||
filename_to_tensors={weights_name: list(state_dict.keys())})
|
||||
|
||||
# Save the model
|
||||
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
||||
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
||||
shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
|
||||
output_path = os.path.join(output_dir, shard_file)
|
||||
if safe_serialization:
|
||||
save_file(shard, output_path, metadata={"format": "pt"})
|
||||
else:
|
||||
torch.save(shard, output_path)
|
||||
|
||||
# Save index if sharded
|
||||
if state_dict_split.is_sharded:
|
||||
index = {
|
||||
"metadata": state_dict_split.metadata,
|
||||
"weight_map": state_dict_split.tensor_to_filename,
|
||||
}
|
||||
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
||||
save_index_file = os.path.join(output_dir, save_index_file)
|
||||
with open(save_index_file, "w", encoding="utf-8") as f:
|
||||
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
||||
f.write(content)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument("output_dir",
|
||||
type=str,
|
||||
help="directory to the pytorch fp32 state_dict output files"
|
||||
"(e.g. path/checkpoint-12-output/)")
|
||||
parser.add_argument(
|
||||
"--max_shard_size",
|
||||
type=str,
|
||||
default="5GB",
|
||||
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
||||
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
||||
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
||||
"without CPU OOM issues.")
|
||||
parser.add_argument(
|
||||
"--safe_serialization",
|
||||
default=False,
|
||||
action='store_true',
|
||||
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_dir,
|
||||
max_shard_size=args.max_shard_size,
|
||||
safe_serialization=args.safe_serialization,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
Reference in New Issue
Block a user