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

support DDP in webui

Browse Source 
Former-commit-id: d059262ff8dc857f597d2657546ec625726a664a
This commit is contained in:
hiyouga
2024-05-28 19:24:22 +08:00
parent 9912b43fcc
commit 9138a7a5ba
19 changed files with 78 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
examples/full_multi_gpu/multi_node.sh
View File

@@ -1,15 +0,0 @@
#!/bin/bash
NPROC_PER_NODE=4
NNODES=2
RANK=0
MASTER_ADDR=192.168.0.1
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/full_multi_gpu/llama3_full_sft.yaml

5
examples/full_multi_gpu/predict.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/full_multi_gpu/llama3_full_predict.yaml

15
examples/full_multi_gpu/single_node.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/full_multi_gpu/llama3_full_sft.yaml