rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-02-01 10:06:44 +01:00
Code Issues Projects Releases Wiki Activity

Potential fix for tokenizer using a fallback

Browse Source
This commit is contained in:
ebolam 2022-06-09 09:01:40 -04:00
parent db9a94ca2a
commit 606c276f9d
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
aiserver.py
View File

@ -1410,6 +1410,7 @@ def load_model(use_gpu=True, gpu_layers=None, initial_load=False, online_model="
global torch
global model_config
global GPT2TokenizerFast
global tokenizer
print("Loading vars.model: {} vars.custmodpth: {}".format(vars.model, vars.custmodpth))
vars.noai = False
if not initial_load: