github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-08-11 12:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

add boxed reward

Browse Source
This commit is contained in:
YeAnbang 2025-04-28 18:15:43 +08:00
parent 14c01aec00
commit 064be50946
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
applications/ColossalChat/rl_example.py
View File

@ -144,8 +144,8 @@ if __name__ == "__main__":
max_length=args.max_new_tokens + args.max_prompt_tokens, max_length=args.max_new_tokens + args.max_prompt_tokens,
do_sample=True, do_sample=True,
max_new_tokens=None, max_new_tokens=None,
early_stopping=False, early_stopping=False if args.reward_type == "think_answer_tags" else True,
stop_strings=["</answer>"], stop_strings=["</answer>"] if args.reward_type == "think_answer_tags" else None,
) )
) )
elif args.backend == "vllm": elif args.backend == "vllm":
@ -161,9 +161,9 @@ if __name__ == "__main__":
generate_config.update( generate_config.update(
dict( dict(
max_tokens=args.max_new_tokens, # max new tokens max_tokens=args.max_new_tokens, # max new tokens
ignore_eos=True, ignore_eos=True if args.reward_type == "think_answer_tags" else False,
include_stop_str_in_output=True, include_stop_str_in_output=True,
stop=["</answer>"], stop=["</answer>"] if args.reward_type == "think_answer_tags" else None,
) )
) )
else: else: