423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 19:06:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

support DDP in webui

Browse Source 
Former-commit-id: 7c016b22aa
This commit is contained in:
hiyouga
2024-05-28 19:24:22 +08:00
parent 2a473f36fb
commit 3ea8f5e6b9
19 changed files with 78 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/lora_multi_gpu/ds_zero3.sh
View File

@@ -1,15 +0,0 @@
#!/bin/bash
NPROC_PER_NODE=4
NNODES=1
RANK=0
MASTER_ADDR=127.0.0.1
MASTER_PORT=29500
CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun \
--nproc_per_node $NPROC_PER_NODE \
--nnodes $NNODES \
--node_rank $RANK \
--master_addr $MASTER_ADDR \
--master_port $MASTER_PORT \
src/train.py examples/lora_multi_gpu/llama3_lora_sft_ds.yaml

6
examples/lora_multi_gpu/multi_node.sh
View File

@@ -1,6 +0,0 @@
#!/bin/bash
# also launch it on slave machine using slave_config.yaml
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
--config_file examples/accelerate/master_config.yaml \
src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml

5
examples/lora_multi_gpu/single_node.sh
View File

@@ -1,5 +0,0 @@
#!/bin/bash
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch \
--config_file examples/accelerate/single_config.yaml \
src/train.py examples/lora_multi_gpu/llama3_lora_sft.yaml