423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 19:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

release v0.2.2, fix #1478 #1466

Browse Source
This commit is contained in:
hiyouga
2023-11-13 23:09:05 +08:00
parent 87390ae3b7
commit 35cc1e28f6
3 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/webui/runner.py
View File

@@ -136,7 +136,7 @@ class Runner:
args["upcast_layernorm"] = True
if args["stage"] == "ppo":
args["reward_model"] = get("train.reward_model")
args["reward_model"] = get_save_dir(get("top.model_name"), get("top.finetuning_type"), get("train.reward_model"))
if args["stage"] == "dpo":
args["dpo_beta"] = get("train.dpo_beta")