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

fix #4005 #4013

Browse Source 
Former-commit-id: 8608fa268cde5cddf8d0c6c2eb2cb5fa246c1831
This commit is contained in:
hiyouga
2024-06-03 19:12:29 +08:00
parent 1a3764ab8f
commit 82d744716a
24 changed files with 52 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/README.md
View File

@@ -107,13 +107,13 @@ CUDA_VISIBLE_DEVICES=0 llamafactory-cli train examples/qlora_single_gpu/llama3_l
### LoRA Fine-Tuning on Multiple GPUs
#### Supervised Fine-Tuning with Accelerate on Single Node
#### Supervised Fine-Tuning on Single Node
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
```
#### Supervised Fine-Tuning with Accelerate on Multiple Nodes
#### Supervised Fine-Tuning on Multiple Nodes
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/lora_multi_gpu/llama3_lora_sft.yaml
@@ -136,13 +136,13 @@ ASCEND_RT_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/lora_multi_npu
### Full-Parameter Fine-Tuning on Multiple GPUs
#### Supervised Fine-Tuning with Accelerate on Single Node
#### Supervised Fine-Tuning on Single Node
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml
```
#### Supervised Fine-Tuning with Accelerate on Multiple Nodes
#### Supervised Fine-Tuning on Multiple Nodes
```bash
CUDA_VISIBLE_DEVICES=0,1,2,3 NNODES=2 RANK=0 MASTER_ADDR=192.168.0.1 MASTER_PORT=29500 llamafactory-cli train examples/full_multi_gpu/llama3_full_sft.yaml