423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

support SimPO #3900

Browse Source 
Former-commit-id: cb63b32986
This commit is contained in:
hiyouga
2024-05-26 23:46:33 +08:00
parent e5d2ef4434
commit 4807c11db8
19 changed files with 145 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/webui/components/train.py
View File

@@ -186,7 +186,7 @@ def create_train_tab(engine: "Engine") -> Dict[str, "Component"]:
with gr.Row():
pref_beta = gr.Slider(minimum=0, maximum=1, value=0.1, step=0.01)
pref_ftx = gr.Slider(minimum=0, maximum=10, value=0, step=0.01)
pref_loss = gr.Dropdown(choices=["sigmoid", "hinge", "ipo", "kto_pair"], value="sigmoid")
pref_loss = gr.Dropdown(choices=["sigmoid", "hinge", "ipo", "kto_pair", "orpo", "simpo"], value="sigmoid")
reward_model = gr.Dropdown(multiselect=True, allow_custom_value=True)
with gr.Column():
ppo_score_norm = gr.Checkbox()