aoshen02andClaude Opus 5.5
2d8efee9a7
Signed-off-by: aoshen02 <aoshen@inferact.ai> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
5 lines
261 B
YAML
5 lines
261 B
YAML
interface:
|
|
display_name: "Train-Inference Consistency"
|
|
short_description: "Make RL training and vLLM rollout logprobs bitwise identical."
|
|
default_prompt: "Use the train-inference consistency workflow to align training with vLLM inference for this model."
|