mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-06-16 14:22:08 +00:00
When on-device sampling is enabled, we need to emulate the greedy behaviour using top-k=1, top-p=1, temperature=1. |
||
---|---|---|
.. | ||
text_generation_server | ||
.gitignore | ||
build-requirements.txt | ||
Makefile | ||
pyproject.toml |