ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor ray integration, support save ckpt

Browse Source 
Former-commit-id: 2f50b27e608b2092bfceab6c6e84e6631e973ee2
This commit is contained in:
hiyouga
2025-01-07 08:54:41 +00:00
parent 4f31ad997c
commit 944a2aec4d
18 changed files with 215 additions and 161 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/README.md
View File

@@ -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
```
#### Supervised Fine-Tuning with Ray on 4 GPUs
```bash
USE_RAY=1 llamafactory-cli train examples/train_full/llama3_lora_sft_ray.yaml
```
### QLoRA Fine-Tuning
#### Supervised Fine-Tuning with 4/8-bit Bitsandbytes/HQQ/EETQ Quantization (Recommended)