423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix shift short attention

Browse Source
This commit is contained in:
hiyouga
2023-10-09 17:07:46 +08:00
parent b8dbec086e
commit ab65c3063b
6 changed files with 46 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/tuner/core/parser.py
View File

@@ -149,6 +149,9 @@ def get_train_args(
if general_args.stage == "ppo" and data_args.streaming:
raise ValueError("Streaming mode does not suppport PPO training currently.")
if general_args.stage == "ppo" and model_args.shift_attn:
raise ValueError("PPO training is incompatible with S^2-Attn.")
if training_args.max_steps == -1 and data_args.streaming:
raise ValueError("Please specify `max_steps` in streaming mode.")