Xin Lai commited on
Commit
e007b3a
·
1 Parent(s): 43e1e6c
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -223,7 +223,7 @@ deepspeed --master_port=24999 train_ds.py \
223
  --eval_only
224
  ```
225
 
226
- Note: the v1 model is trained using both `train+val` sets, so please use the `v0` model to reproduce the validation results. (To use the v0 models, please first checkout to the legacy version repo git checkout 0e26916.)
227
 
228
 
229
  ## Inference
 
223
  --eval_only
224
  ```
225
 
226
+ Note: the `v1` model is trained using both `train+val` sets, so please use the `v0` model to reproduce the validation results. (To use the `v0` models, please first checkout to the legacy version repo with `git checkout 0e26916`.)
227
 
228
 
229
  ## Inference