Add flash attention

Create handler.py

fall back to self.config for return_dict

cache alibi_mask for accelerate training

fix alibi problem and support attention_mask

Update modeling_baichuan.py

Update README.md

Delete Commercial Term of Use for Baichuan-13B Model.pdf

Delete Baichuan-13B 模型商用许可协议.pdf

Update README.md

Update README.md

Update README.md

Update README.md

Update modeling_baichuan.py

Update special_tokens_map.json

Update tokenizer_config.json

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

modify: update modeling code

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Upload 4 files

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Update generation_config.json

Create README.md

Update config.json

Upload tokenizer.model

Upload 5 files

add: add modeling code

Upload tokenizer.model

Update config.json

Upload BaichuanForCausalLM