Use revision when downloading the quantization config file (#2697)
Co-authored-by: Pernekhan Utemuratov <pernekhan@deepinfra.com>
This commit is contained in:
co-authored by
Pernekhan Utemuratov
parent
bb8c697ee0
commit
c410f5d020
@@ -44,10 +44,7 @@ def get_model(model_config: ModelConfig,
|
||||
# Get the (maybe quantized) linear method.
|
||||
linear_method = None
|
||||
if model_config.quantization is not None:
|
||||
quant_config = get_quant_config(model_config.quantization,
|
||||
model_config.model,
|
||||
model_config.hf_config,
|
||||
model_config.download_dir)
|
||||
quant_config = get_quant_config(model_config)
|
||||
capability = torch.cuda.get_device_capability()
|
||||
capability = capability[0] * 10 + capability[1]
|
||||
if capability < quant_config.get_min_capability():
|
||||
|
||||
Reference in New Issue
Block a user