Text Generation
Transformers
Safetensors
English
llama
causal-lm
text-generation-inference
4-bit precision
gptq

Rename stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors to model.safetensors

#26
by dclab - opened
No description provided.

If I was going to rename it I would use the AutoGPTQ format gptq_model-4bit-128g so it can autodetect the filename. But I think it's fine having custom names, as they can be specified with model_basename

TheBloke changed pull request status to closed

Sign up or log in to comment