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

Remove exllamav1 loaders (#5128)

Browse source
This commit is contained in:
oobabooga 2023-12-31 01:57:06 -03:00 • committed by GitHub
parent 8e397915c9
commit 0e54a09bcb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
18 changed files with 28 additions and 635 deletions
Download patch file Download diff file Expand all files Collapse all files

10
modules/models_settings.py
View file

@ -41,13 +41,11 @@ def get_model_metadata(model):
if 'loader' not in model_settings:
if hf_metadata is not None and 'quip_params' in hf_metadata:
model_settings['loader'] = 'QuIP#'
loader = 'QuIP#'
else:
loader = infer_loader(model, model_settings)
if 'wbits' in model_settings and type(model_settings['wbits']) is int and model_settings['wbits'] > 0:
loader = 'AutoGPTQ'
model_settings['loader'] = loader
model_settings['loader'] = loader
# GGUF metadata
if model_settings['loader'] in ['llama.cpp', 'llamacpp_HF', 'ctransformers']:
@ -152,7 +150,7 @@ def infer_loader(model_name, model_settings):
if not path_to_model.exists():
loader = None
elif (path_to_model / 'quantize_config.json').exists() or ('wbits' in model_settings and type(model_settings['wbits']) is int and model_settings['wbits'] > 0):
loader = 'ExLlama_HF'
loader = 'ExLlamav2_HF'
elif (path_to_model / 'quant_config.json').exists() or re.match(r'.*-awq', model_name.lower()):
loader = 'AutoAWQ'
elif len(list(path_to_model.glob('*.gguf'))) > 0:
@ -229,7 +227,7 @@ def apply_model_settings_to_state(model, state):
loader = model_settings.pop('loader')
# 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', 'ExLlamav2', 'ExLlamav2_HF']) and not (loader == 'llama.cpp' and state['loader'] in ['llamacpp_HF', 'ctransformers']):
if not (loader == 'ExLlamav2_HF' and state['loader'] in ['GPTQ-for-LLaMa', 'ExLlamav2', 'AutoGPTQ']) and not (loader == 'llama.cpp' and state['loader'] in ['llamacpp_HF', 'ctransformers']):
state['loader'] = loader
for k in model_settings: