update readme

fix kwargs in generate method and update readme

refactor tokenization and update readme

update quickusage

update cpu support, readme and convert_tokens_to_string

Update Readme.md, fix typo

update fast usage

update fast usage

fix flash-attention usage

Update README.md

fix report link

fix report link

Update README.md

update demo link

update tokenization_qwen.py

upload resource files

Update README.md

initial commit