GitLab

* qwen support

* dynamic ntk & logn attn

* fix ntk & add chat template

* fix ntk scaling & stop words

* fix lint

* add tiktoken to requirements.txt

* fix tokenizer, set model format automatically

* update model.py

* update readme

* fix lint

* check-in script for tokenizing a file

* use max_input_len

* temp

* fix lint

* csrc->src

* remove clang-format

* skip .rst

* skip doc

* clang-format

version

version

* mat_B

* add hf tokenizer

* format

* fix for comment

* don't skip speical tokens

* add ft code

* gitignore

* fix lint

* revert fmha