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

Implement CFG for ExLlama_HF (#3666)

Browse source
This commit is contained in:
oobabooga 2023-08-24 16:27:36 -03:00 • committed by GitHub
parent 2b675533f7
commit d6934bc7bc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 122 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

4
modules/models_settings.py
View file

@ -91,8 +91,8 @@ def apply_model_settings_to_state(model, state):
if 'wbits' in model_settings and type(model_settings['wbits']) is int and model_settings['wbits'] > 0:
loader = 'AutoGPTQ'
# If the user is using an alternative GPTQ loader, let them keep using it
if not (loader == 'AutoGPTQ' and state['loader'] in ['GPTQ-for-LLaMa', 'ExLlama', 'ExLlama_HF']):
# If the user is using an alternative loader for the same model type, let them keep using it
if not (loader == 'AutoGPTQ' and state['loader'] in ['GPTQ-for-LLaMa', 'ExLlama', 'ExLlama_HF']) and not (loader == 'llama.cpp' and state['loader'] in ['llamacpp_HF', 'ctransformers']):
state['loader'] = loader
for k in model_settings: