Skip to content

Conversation

WrRan
Copy link
Contributor

@WrRan WrRan commented Mar 13, 2025

typos

@WrRan WrRan requested a review from zhaochenyang20 as a code owner March 13, 2025 14:12
* `temperature: float = 1.0` [Temperature](https://platform.openai.com/docs/api-reference/chat/create#chat-create-temperature) when sampling the next token. `temperature = 0` corresponds to greedy sampling, higher temperature leads to more diversity.
* `top_p: float = 1.0` [Top-p](https://platform.openai.com/docs/api-reference/chat/create#chat-create-top_p) selects tokens from the smallest sorted set whose cumulative probability exceeds `top_p`. When `top_p = 1`, this reduces to unrestricted sampling from all tokens.
* `top_k: int = -1` [Top-k](https://developer.nvidia.com/blog/how-to-get-better-outputs-from-your-large-language-model/#predictability_vs_creativity) randomly selects from the `k` highest-probability tokens.
* `min_p: float = 0.0` [Min-p](https://github.com/huggingface/transformers/issues/27670) samples from tokens with probability larger than `min_p * highest_token_probability`.

### Penalizers

To use penalizers you will need to `--disable-overlap`. Please note that this might degrade performance.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

penalizers are supported now in overlap mode, so we can remove this line

Copy link
Collaborator

@zhaochenyang20 zhaochenyang20 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

same as lianmin

@merrymercy merrymercy merged commit 22c96f7 into sgl-project:main Mar 15, 2025
12 checks passed
@WrRan WrRan deleted the patch-7 branch March 19, 2025 14:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants