423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 11:50:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

support orpo in webui

Browse Source
This commit is contained in:
hiyouga
2024-03-31 18:34:59 +08:00
parent 17bf8a2c3a
commit 5195add324
3 changed files with 22 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/webui/runner.py
View File

@@ -174,10 +174,11 @@ class Runner:
]
)
args["reward_model_type"] = "lora" if args["finetuning_type"] == "lora" else "full"
if args["stage"] == "dpo":
elif args["stage"] == "dpo":
args["dpo_beta"] = get("train.dpo_beta")
args["dpo_ftx"] = get("train.dpo_ftx")
elif args["stage"] == "orpo":
args["orpo_beta"] = get("train.orpo_beta")
if get("train.val_size") > 1e-6 and args["stage"] != "ppo":
args["val_size"] = get("train.val_size")