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

Fix bug in multigpu setups

Browse source
This commit is contained in:
oobabooga 2023-03-06 14:58:30 -03:00
parent 5bed607b77
commit d88b7836c6
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/text_generation.py
View file

@ -194,7 +194,7 @@ def generate_reply(question, max_new_tokens, do_sample, temperature, top_p, typi
yield formatted_outputs(reply, shared.model_name)
if not shared.args.flexgen:
if output[-1] == n:
if int(output[-1]) == int(n):
break
input_ids = torch.reshape(output, (1, output.shape[0]))
else: