Precompute logprobs, values
Open
- Dominant language
- Python
- Stars
- 4.8k
- Forks
- 487
- PR merge metrics
- No merged PRs in 30d
Description
https://github.com/CarperAI/trlx/blob/9fdd0d757e8f7a3d48e7edb060ddb7517da13d2d/trlx/trainer/accelerate_ppo_trainer.py#L399
I met that error when precompute logprobs, values
due to the concatenation of prompt_tensor and output .
my question is why we concat the prompt_tensor and output in the format of ids , rather than first concate into string and secondly tokenized into ids?
I think the second operation can solve my issue.
thanks
weizhen
Contributor guide
Assessment
This issue has not been assessed yet.