mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-12-16 03:40:34 +08:00
refactor ray integration, support save ckpt
This commit is contained in:
@@ -95,6 +95,12 @@ FORCE_TORCHRUN=1 NNODES=2 NODE_RANK=1 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500
|
||||
FORCE_TORCHRUN=1 llamafactory-cli train examples/train_lora/llama3_lora_sft_ds3.yaml
|
||||
```
|
||||
|
||||
#### 使用 Ray 在 4 张 GPU 上微调
|
||||
|
||||
```bash
|
||||
USE_RAY=1 llamafactory-cli train examples/train_full/llama3_lora_sft_ray.yaml
|
||||
```
|
||||
|
||||
### QLoRA 微调
|
||||
|
||||
#### 基于 4/8 比特 Bitsandbytes/HQQ/EETQ 量化进行指令监督微调(推荐)
|
||||
|
||||
Reference in New Issue
Block a user