internlm2-chat-20b / modeling_internlm2.py

Commit History

fix flash attention import
2d0920c

x54-729 commited on

small update
2750ce8

x54-729 commited on

update for new version
04830fb

x54-729 commited on

small
3f710f7

x54-729 commited on

remove unnecessary attention_drop
180a5b8

x54-729 commited on

Update special tokens (#3)
50ffaf2
verified

RangiLyu commited on

fix import error
8c8a68a

x54-729 commited on

support flash attn 2
4e70767

x54-729 commited on

fix: add eoa into eos_token_id in chat to accelerate chat interface
b149c04

ZwwWayne commited on

use bin instead of safetensors with max shard of 2GB
e2955f1

ZwwWayne commited on

fix(modeling): fix inference code
a726bdd

ZwwWayne commited on

initial commit internlm2-chat-20b model
4d06ea7

ZwwWayne commited on