sl-alex
/

flash_llama

Model card Files Files and versions Community

flash_llama / README.md

sl-alex's picture

Update README.md

95ee7e4 over 1 year ago

|

407 Bytes

metadata

license: apache-2.0

This repository houses a fork of togethercomputer/LLaMA-2-7B-32K's modeling_flash_llama.py, with a fix for padding of attention weights merged into it.