AutoAWQ: initial support (#3999)
This commit is contained in:
parent
3f56151f03
commit
cc632c3f33
8 changed files with 75 additions and 3 deletions
|
@ -107,10 +107,14 @@ def infer_loader(model_name, model_settings):
|
|||
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 = 'AutoGPTQ'
|
||||
elif (path_to_model / 'quant_config.json').exists():
|
||||
loader = 'AutoAWQ'
|
||||
elif len(list(path_to_model.glob('*.gguf'))) > 0:
|
||||
loader = 'llama.cpp'
|
||||
elif re.match(r'.*\.gguf', model_name.lower()):
|
||||
loader = 'llama.cpp'
|
||||
elif re.match(r'.*-awq', model_name.lower()):
|
||||
loader = 'AutoAWQ'
|
||||
elif re.match(r'.*rwkv.*\.pth', model_name.lower()):
|
||||
loader = 'RWKV'
|
||||
elif re.match(r'.*exl2', model_name.lower()):
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue