初始化项目，由ModelHub XC社区提供模型
Model: movefast/Qwen2.5-7B-Open-R1-GRPO 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
|
||||
68
README.md
Normal file
68
README.md
Normal file
@@ -0,0 +1,68 @@
|
||||
---
|
||||
base_model: Qwen/Qwen2.5-7B-Instruct
|
||||
library_name: transformers
|
||||
model_name: Qwen2.5-7B-Open-R1-GRPO
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- grpo
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Qwen2.5-7B-Open-R1-GRPO
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="movefast/Qwen2.5-7B-Open-R1-GRPO", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/liderek269/huggingface/runs/eftsowa0)
|
||||
|
||||
|
||||
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.16.0.dev0
|
||||
- Transformers: 4.49.0
|
||||
- Pytorch: 2.5.1
|
||||
- Datasets: 3.3.2
|
||||
- Tokenizers: 0.21.1
|
||||
|
||||
## Citations
|
||||
|
||||
Cite GRPO as:
|
||||
|
||||
```bibtex
|
||||
@article{zhihong2024deepseekmath,
|
||||
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
||||
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
||||
year = 2024,
|
||||
eprint = {arXiv:2402.03300},
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
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
|
||||
}
|
||||
8
all_results.json
Normal file
8
all_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 1.0788,
|
||||
"train_samples": 5501,
|
||||
"train_samples_per_second": 25495.021,
|
||||
"train_steps_per_second": 908.385
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 131072,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.49.0",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.49.0"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a1b70ff34478e0b3a8b29f3af6e20869ff5b649fe3f9cbe05f20dec09327654b
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:514a3c7843f6fab08922cd0b08ffc266511682a0219da2a0cefea47d7bb17225
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f9559b300b6ec0a0e6bcab83ae0c44325ad9ed83395e74dc4d497a280182f0e
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e6898fbedf7fc3523718c51702560254468e9c22dd429af3ed83d3f96f36bac
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a79a7b346ba4086607f8e39c4e8843548d5a3e197b12e3d2382857cf75d34e95
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d4d011bb80ed8cb736d49db31edb7b4df453de3db335a5671a45cb1c19b09173
|
||||
size 13055349374
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:222a0df4fc91319df11e0772325c1b0ac70707f0619ecb9d3009a1cf39e834de
|
||||
size 13055349374
|
||||
3
global_step980/zero_pp_rank_0_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_0_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bf8e26243daedd44cf28db997b35ae3fd560f8f4c48d1bf53df685da6f05feb4
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_1_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_1_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edb2b33678e9aceb5af7defef79b07076984b9127e67f195782661615574c994
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_2_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_2_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9fd10d10d1056edc06b1fad221e940fc780508ce8046858f27cc12894426a806
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_3_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_3_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5b4c243217e9a0cccc241659869e5f11f6bb12f173fe942f80f5571f52037a3b
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_4_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_4_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3e31d12be348ec9d1ee7f5366acd2e1fdf5a9a768db8f74671032db12233d07
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_5_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_5_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:907c58526a0692011109e52e0fcd3ea0797816337043d83d7e0754558a0cbfc1
|
||||
size 166293
|
||||
3
global_step980/zero_pp_rank_6_mp_rank_00_model_states.pt
Normal file
3
global_step980/zero_pp_rank_6_mp_rank_00_model_states.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:38d38254e910919f8e255f18d55574cc0b93e6d5130f91beaa45cd1f1667a451
|
||||
size 166293
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00007.bin
Normal file
3
pytorch_model-00001-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb57a0fc12a9d59920fe588f0243da8eda1435ca61468a0c820a6356de9a3272
|
||||
size 4976549766
|
||||
3
pytorch_model-00002-of-00007.bin
Normal file
3
pytorch_model-00002-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46f92d6c7c358bfb1349d10c1136f10d6b461edd3d14e17fb1ba509a2beca831
|
||||
size 4778374392
|
||||
3
pytorch_model-00003-of-00007.bin
Normal file
3
pytorch_model-00003-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57637d5c676ca728c841232a988c01585790d084285ce5cc3bf374dcf35c8c12
|
||||
size 4932514090
|
||||
3
pytorch_model-00004-of-00007.bin
Normal file
3
pytorch_model-00004-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef31bb4af459e2b9622eb4605c9c82e6dbdd0601b6b1f4046425dac206f1da25
|
||||
size 4932514102
|
||||
3
pytorch_model-00005-of-00007.bin
Normal file
3
pytorch_model-00005-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c88efc81c8c3a53db78b5237724524a60b3ea9c545ef4ac9ef61ef737820136
|
||||
size 4998575416
|
||||
3
pytorch_model-00006-of-00007.bin
Normal file
3
pytorch_model-00006-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2b2529809dfb54040f1c454e74cd845a7eb5989494966ec6def9cba05dd77a0
|
||||
size 3662699518
|
||||
3
pytorch_model-00007-of-00007.bin
Normal file
3
pytorch_model-00007-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f5f39e68c99fa360bc926d822ab8e263a787cd2b222707c2b103aa9144f80c0
|
||||
size 2181355581
|
||||
346
pytorch_model.bin.index.json
Normal file
346
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 30462467392
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.24.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.24.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.24.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.25.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.25.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.26.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.26.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.27.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.27.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.bias": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.norm.weight": "pytorch_model-00006-of-00007.bin"
|
||||
}
|
||||
}
|
||||
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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
||||
size 11421896
|
||||
208
tokenizer_config.json
Normal file
208
tokenizer_config.json
Normal file
@@ -0,0 +1,208 @@
|
||||
{
|
||||
"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": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
8
train_results.json
Normal file
8
train_results.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"total_flos": 0.0,
|
||||
"train_loss": 0.0,
|
||||
"train_runtime": 1.0788,
|
||||
"train_samples": 5501,
|
||||
"train_samples_per_second": 25495.021,
|
||||
"train_steps_per_second": 908.385
|
||||
}
|
||||
12782
trainer_state.json
Normal file
12782
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
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 sha256:19c1d33a614a367424f894dff347a341f044f7ff87fc2232cb5c98d110f3dab6
|
||||
size 7992
|
||||
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