huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 04:14:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix:error use loadin8bit model.cuda

Browse Source
This commit is contained in:
mmnga 2023-10-16 11:03:32 +09:00
parent 3af1a11401
commit ac531c8d0a
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/text_generation_server/models/causal_lm.py
View File

@ -511,7 +511,7 @@ class CausalLM(Model):
load_in_8bit=quantize == "bitsandbytes", load_in_8bit=quantize == "bitsandbytes",
trust_remote_code=trust_remote_code, trust_remote_code=trust_remote_code,
) )
if torch.cuda.is_available() and torch.cuda.device_count() == 1: if torch.cuda.is_available() and torch.cuda.device_count() == 1 and quantize != "bitsandbytes":
model = model.cuda() model = model.cuda()
if tokenizer.pad_token_id is None: if tokenizer.pad_token_id is None: