TheBloke
/

alpaca-lora-65B-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (2)

Beware! Requires new cuda.

#5 opened almost 2 years ago by

Getting size mismatch for model.layers with alpaca-lora-65B-GPTQ-4bit-1024g.safetensors

#3 opened almost 2 years ago by

Error in instructions?

#2 opened almost 2 years ago by

It also works on Windows, using last update of the CUDA GPTQ tree.

#1 opened almost 2 years ago by