Nguyen Nhat Minh

menhguin

AI & ML interests

AI Safety and funny memes

Recent Activity

authored a paper 17 days ago

Min P Sampling: Balancing Creativity and Coherence at High Temperature

authored a paper 17 days ago

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

authored a paper 17 days ago

When Two LLMs Debate, Both Think They'll Win

View all activity

Organizations

authored 3 papers 17 days ago

Min P Sampling: Balancing Creativity and Coherence at High Temperature

Paper • 2407.01082 • Published Jul 1, 2024 • 1

RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Paper • 2504.20073 • Published Apr 24 • 11

When Two LLMs Debate, Both Think They'll Win

Paper • 2505.19184 • Published May 25

upvoted a paper 17 days ago

Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models

Paper • 2506.06751 • Published 22 days ago • 72

updated 3 Spaces 9 months ago

reacted to joaogante's post with 🤗 about 1 year ago

Post

3792

New sampling strategy dropped in 🤗 transformers -- Min P sampling 🔥

Are you tired of having top_k arbitrarily discarding high-quality continuations? Or top_p forgetting to exclude low-probability tokens, derailing your generation? Try out the new min_p flag in generate, fresh from a PR merged today! 🥬

Min P consists of a dynamic token filter -- as opposed to Top K, which keeps the K most likely tokens, and Top P, which keeps the most likely tokens up to a fixed cumulative probability, both static filters. Min P takes a base probability (defined in the min_p flag) and multiplies it by the probability of the most likely token in the distribution for the next token. All tokens less likely than the resulting value are filtered. What happens with this strategy?
👉 High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation)
👉 No high probability token present -> relaxed filter (there are many continuation possibilities that the model finds plausible)

You should set min_p to a low value, between 0.05 and 0.1. It behaves particularly well for creative text generation when paired up with temperature > 1.

Kudos to @kalomaze and @menhguin for creating this technique 🔥 Read their discussion in the original issue for benchmarks (https://github.com/huggingface/transformers/issues/27670)

Copy-pasteable version of the example in the image below here: https://pastebin.com/VqXNtuxd

Have fun experimenting! 😎