internlm2-chat-7b / modeling_internlm2.py

Commit History

fast tokenizer and stream_chat fix
2335a07
verified

x54-729 commited on

remove unnecessary attention_drop
008c536

x54-729 commited on

Update special tokens (#3)
30482dd
verified

RangiLyu commited on

fix import error
0143463

x54-729 commited on

support flash attn 2
d762e4c

x54-729 commited on

fix: add eoa into eos_token_id in chat to accelerate chat interface
0e5f375

ZwwWayne commited on

use bin instead of safetensors with max shard of 2GB
03da3f2

ZwwWayne commited on

fix(modeling): fix inference code
405ebfe

ZwwWayne commited on

initial commit internlm2-chat-7b model
d64cff5

ZwwWayne commited on