Hu Zang

zanghu

AI & ML interests

None yet

Recent Activity

reacted to joaogante's post with šŸ¤— 2 days ago
New sampling strategy dropped in šŸ¤— transformers -- Min P sampling šŸ”„ 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! šŸ„¬ 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? šŸ‘‰ High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation) šŸ‘‰ 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 šŸ”„ 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! šŸ˜Ž
reacted to joaogante's post with šŸ‘ 2 days ago
New sampling strategy dropped in šŸ¤— transformers -- Min P sampling šŸ”„ 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! šŸ„¬ 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? šŸ‘‰ High probability token present -> aggressive filter (we don't want to miss on that high-probability case and risk derailing generation) šŸ‘‰ 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 šŸ”„ 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! šŸ˜Ž
liked a Space 16 days ago
bigcode/bigcode-models-leaderboard
View all activity

Organizations

None yet

models

None public yet

datasets

None public yet