You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The default model was set to TheBloke/WizardLM-7B-uncensored-GPTQ which causes issue when running on cpu.
Change the default to TheBloke/vicuna-7B-1.1-HF
When --device_type is cpu or mps, the model_basename will be set to None and will use LlamaForCausalLM. This is a temporary fix. Need a permanent fix for M1/M2.
The text was updated successfully, but these errors were encountered:
The default model was set to TheBloke/WizardLM-7B-uncensored-GPTQ which causes issue when running on cpu.
Change the default to TheBloke/vicuna-7B-1.1-HF
When --device_type is cpu or mps, the model_basename will be set to None and will use LlamaForCausalLM. This is a temporary fix. Need a permanent fix for M1/M2.
The default model was set to
TheBloke/WizardLM-7B-uncensored-GPTQ
which causes issue when running on cpu.TheBloke/vicuna-7B-1.1-HF
--device_type
iscpu
ormps
, themodel_basename
will be set toNone
and will useLlamaForCausalLM
. This is a temporary fix. Need a permanent fix for M1/M2.The text was updated successfully, but these errors were encountered: