423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2026-07-07 09:35:27 +08:00
Code Issues Packages Projects Releases Wiki Activity

[v1] support reward training stage (#10431)

Browse Source 
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
浮梦
2026-05-20 20:46:52 +08:00
committed by GitHub
parent 40e786d016
commit 8b5ea65770
9 changed files with 217 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/llamafactory/v1/launcher.py
View File

@@ -148,7 +148,9 @@ def launch():
elif command == "dpo":
raise NotImplementedError("DPO trainer is not implemented yet.")
elif command == "rm":
raise NotImplementedError("RM trainer is not implemented yet.")
from llamafactory.v1.trainers.rm_trainer import run_rm
run_rm()
else:
print(f"Unknown command: {command}.\n{USAGE}")
@@ -175,9 +177,9 @@ def main():
# run_dpo()
raise NotImplementedError("DPO trainer is not implemented yet.")
elif command == "rm":
# from llamafactory.v1.trainers.rm_trainer import run_rm
# run_rm()
raise NotImplementedError("RM trainer is not implemented yet.")
from llamafactory.v1.trainers.rm_trainer import run_rm
run_rm()
if __name__ == "__main__":