DeepSeek/ESFT
1
0
Fork 0
mirror of https://github.com/deepseek-ai/ESFT synced 2025-06-26 18:15:50 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

update eval and readme

Browse Source
This commit is contained in:
ZihanWang314
2024-08-09 18:06:57 +08:00
parent 809d0e377e
commit 36c6194349
10 changed files with 333 additions and 152 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/train_ep.sh
View File

@@ -2,7 +2,7 @@
export TOKENIZERS_PARALLELISM=false
exp_name="test/eval_translation"
base_model_path="/hf3fs-jd/prod/deepseek/shared/wangzihan/models/huggingface/vanilla_model"
base_model_path="deepseek-ai/esft-vanilla-lite"
torchrun --nproc-per-node=8 train_ep.py \
--base_model_path=${base_model_path} \
--expert_config=results/expert_configs/translation.json \