423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-17 04:10:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[parser] support omegaconf (#7793)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-04-21 23:30:30 +08:00
committed by GitHub
parent bd7bc31c79
commit 416853dd25
25 changed files with 62 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
examples/README.md
View File

@@ -15,6 +15,18 @@ Use `CUDA_VISIBLE_DEVICES` (GPU) or `ASCEND_RT_VISIBLE_DEVICES` (NPU) to choose
By default, LLaMA-Factory uses all visible computing devices.
Basic usage:
```bash
llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
```
Advanced usage:
```bash
CUDA_VISIBLE_DEVICES=0,1 llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml learning_rate=1e-5 logging_steps=1
```
## Examples
### LoRA Fine-Tuning
@@ -34,7 +46,6 @@ llamafactory-cli train examples/train_lora/llama3_lora_sft.yaml
#### Multimodal Supervised Fine-Tuning
```bash
llamafactory-cli train examples/train_lora/llava1_5_lora_sft.yaml
llamafactory-cli train examples/train_lora/qwen2vl_lora_sft.yaml
```