ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support SimPO #3900

Browse Source 
Former-commit-id: 6b954ce60155cf8334150b795cfc4bb63ca74c8b
This commit is contained in:
hiyouga
2024-05-26 23:46:33 +08:00
parent 26f293d587
commit b0d9966663
19 changed files with 145 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
src/llamafactory/webui/runner.py
View File

@@ -179,15 +179,10 @@ class Runner:
args["ppo_whiten_rewards"] = get("train.ppo_whiten_rewards")
args["top_k"] = 0
args["top_p"] = 0.9
elif args["stage"] == "dpo":
args["dpo_beta"] = get("train.pref_beta")
args["dpo_ftx"] = get("train.pref_ftx")
args["dpo_loss"] = get("train.pref_loss")
elif args["stage"] == "kto":
args["kto_beta"] = get("train.pref_beta")
args["kto_ftx"] = get("train.pref_ftx")
elif args["stage"] == "orpo":
args["orpo_beta"] = get("train.pref_beta")
elif args["stage"] in ["dpo", "kto"]:
args["pref_beta"] = get("train.pref_beta")
args["pref_ftx"] = get("train.pref_ftx")
args["pref_loss"] = get("train.pref_loss")
# galore config
if args["use_galore"]: