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

Make universal tokenizer, xformers, sdp-attention apply to monkey patch

Browse source
This commit is contained in:
oobabooga 2023-04-25 23:18:11 -03:00
parent f39c99fa14
commit f642135517
2 changed files with 2 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

3
modules/models.py
View file

@ -149,8 +149,7 @@ def load_model(model_name):
print("Warning: applying the monkey patch for using LoRAs in 4-bit mode.\nIt may cause undefined behavior outside its intended scope.")
from modules.monkey_patch_gptq_lora import load_model_llama
model, tokenizer = load_model_llama(model_name)
return model, tokenizer
model, _ = load_model_llama(model_name)
# No monkey patch
else: