internlm2-chat-7b-sft / modeling_internlm2.py

Commit History

fast tokenizer and stream_chat fix
0447da5
verified

x54-729 commited on

remove unnecessary attention_drop
6e85777

x54-729 commited on

Update special tokens (#1)
0ce7fbf
verified

RangiLyu commited on

fix import error
25f6a3e

x54-729 commited on

support flash attn 2
5651285

x54-729 commited on

fix: add eoa into eos_token_id in chat to accelerate chat interface
792f68a

ZwwWayne commited on

initial commit internlm2-chat-7b-sft model
ca4e235

ZwwWayne commited on