Skip to content

Expose enable_thinking in RLCluster.generate. #1087

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

Open
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −1
Open

Expose enable_thinking in RLCluster.generate. #1087

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
4 changes: 3 additions & 1 deletion tunix/rl/rl_cluster.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -794,6 +794,7 @@ def generate(
apply_chat_template: bool = False,
mode: Mode = Mode.TRAIN,
micro_batch_size: int | None = None,
enable_thinking: bool = False
) -> base_rollout.RolloutOutput:
"""Generates text from the given prompts.

Expand All @@ -806,6 +807,7 @@ def generate(
mode: The mode of rollout, either TRAIN or EVAL.
micro_batch_size: The micro-batch size for generation. If None, no
micro-batching is performed.
enable_thinking: Whether to enable reasoning for supported models.

Returns:
A `RolloutOutput` object containing the generated text and other info.
Expand All @@ -818,7 +820,7 @@ def generate(
prompt, # pytype: disable=wrong-arg-types
add_generation_prompt=True,
tokenize=False,
enable_thinking=False,
enable_thinking=enable_thinking
)
for prompt in prompts
]
Expand Down