Skip to content

[Tunix] Don't skip the special token from the vllm responses in agentic training otherwise, we will need manual processing to previous token shifts. #1588

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
copybara-service wants to merge 1 commit into from
+8 −0
Closed

[Tunix] Don't skip the special token from the vllm responses in agentic training otherwise, we will need manual processing to previous token shifts. #1588

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions tunix/rl/agentic/agentic_rl_learner.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -265,6 +265,14 @@ def _validate_rollout_config(self):
configs_to_check = rollout_config

for mode, config in configs_to_check.items():
if config.rollout_vllm_sampling_kwargs is None:
config.rollout_vllm_sampling_kwargs = {}
if (
"skip_special_tokens" not in config.rollout_vllm_sampling_kwargs
or config.rollout_vllm_sampling_kwargs["skip_special_tokens"]
):
config.rollout_vllm_sampling_kwargs["skip_special_tokens"] = False

if config.max_tokens_to_generate != self.algo_config.max_response_length:
raise ValueError(
f"RolloutConfig ({mode}) max_tokens_to_generate "
Expand Down
Loading