mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Add no_flash_attn option

Browse source
This commit is contained in:
oobabooga 2023-11-02 08:19:42 -07:00
parent aaf726dbfb
commit 77abd9b69b
4 changed files with 4 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
modules/exllamav2_hf.py
View file

@ -152,5 +152,6 @@ class Exllamav2HF(PreTrainedModel):
config.max_seq_len = shared.args.max_seq_len
config.scale_pos_emb = shared.args.compress_pos_emb
config.scale_alpha_value = shared.args.alpha_value
config.no_flash_attn = shared.args.no_flash_attn
return Exllamav2HF(config)