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

Add LLaMA support

Browse source
This commit is contained in:
oobabooga 2023-03-03 14:39:14 -03:00
parent 2bff646130
commit ea5c5eb3da
4 changed files with 110 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/text_generation.py
View file

@ -83,7 +83,7 @@ def generate_reply(question, max_new_tokens, do_sample, temperature, top_p, typi
if not shared.args.cpu:
torch.cuda.empty_cache()
if shared.is_RWKV:
if shared.is_RWKV or shared.is_LLaMA:
if shared.args.no_stream:
reply = shared.model.generate(question, token_count=max_new_tokens, temperature=temperature, top_p=top_p)
yield formatted_outputs(reply, shared.model_name)