423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-25 07:12:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: 87a7822b98ef204a7a36fa4caf4e09a092f6a2da
This commit is contained in:
hiyouga 2024-06-06 16:25:42 +08:00
parent cceff9f520
commit 8cc6bb961b
2 changed files with 18 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
README.md
View File

@ -179,8 +179,6 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [Yuan](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan | | [Yuan](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan |
> [!NOTE] > [!NOTE]
> **Default module** is used for the `lora_target` argument, you can use `lora_target: all` to specify all the available modules for better convergence.
>
> For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models. > For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models.
> >
> Remember to use the **SAME** template in training and inference. > Remember to use the **SAME** template in training and inference.
@ -291,21 +289,21 @@ huggingface-cli login
| Mandatory | Minimum | Recommend | | Mandatory | Minimum | Recommend |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| python | 3.8 | 3.10 | | python | 3.8 | 3.11 |
| torch | 1.13.1 | 2.2.0 | | torch | 1.13.1 | 2.3.0 |
| transformers | 4.37.2 | 4.41.0 | | transformers | 4.41.2 | 4.41.2 |
| datasets | 2.14.3 | 2.19.1 | | datasets | 2.16.0 | 2.19.2 |
| accelerate | 0.27.2 | 0.30.1 | | accelerate | 0.30.1 | 0.30.1 |
| peft | 0.9.0 | 0.11.1 | | peft | 0.11.1 | 0.11.1 |
| trl | 0.8.2 | 0.8.6 | | trl | 0.9.3 | 0.9.3 |
| Optional | Minimum | Recommend | | Optional | Minimum | Recommend |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| CUDA | 11.6 | 12.2 | | CUDA | 11.6 | 12.2 |
| deepspeed | 0.10.0 | 0.14.0 | | deepspeed | 0.10.0 | 0.14.0 |
| bitsandbytes | 0.39.0 | 0.43.1 | | bitsandbytes | 0.39.0 | 0.43.1 |
| vllm | 0.4.0 | 0.4.2 | | vllm | 0.4.3 | 0.4.3 |
| flash-attn | 2.3.0 | 2.5.8 | | flash-attn | 2.3.0 | 2.5.9 |
### Hardware Requirement ### Hardware Requirement

18
README_zh.md
View File

@ -289,21 +289,21 @@ huggingface-cli login
| 必需项 | 至少 | 推荐 | | 必需项 | 至少 | 推荐 |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| python | 3.8 | 3.10 | | python | 3.8 | 3.11 |
| torch | 1.13.1 | 2.2.0 | | torch | 1.13.1 | 2.3.0 |
| transformers | 4.37.2 | 4.41.0 | | transformers | 4.41.2 | 4.41.2 |
| datasets | 2.14.3 | 2.19.1 | | datasets | 2.16.0 | 2.19.2 |
| accelerate | 0.27.2 | 0.30.1 | | accelerate | 0.30.1 | 0.30.1 |
| peft | 0.9.0 | 0.11.1 | | peft | 0.11.1 | 0.11.1 |
| trl | 0.8.2 | 0.8.6 | | trl | 0.9.3 | 0.9.3 |
| 可选项 | 至少 | 推荐 | | 可选项 | 至少 | 推荐 |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| CUDA | 11.6 | 12.2 | | CUDA | 11.6 | 12.2 |
| deepspeed | 0.10.0 | 0.14.0 | | deepspeed | 0.10.0 | 0.14.0 |
| bitsandbytes | 0.39.0 | 0.43.1 | | bitsandbytes | 0.39.0 | 0.43.1 |
| vllm | 0.4.0 | 0.4.2 | | vllm | 0.4.3 | 0.4.3 |
| flash-attn | 2.3.0 | 2.5.8 | | flash-attn | 2.3.0 | 2.5.9 |
### 硬件依赖 ### 硬件依赖