4bit
/

llama-13b-4bit-gr128

Text Generation

Inference Endpoints

Model card Files Files and versions Community

llama-13b-4bit-gr128 / README.md

camenduru's picture

thanks to wcde ❤

e4f1fb0 over 1 year ago

|

86 Bytes

Generated with: --wbits 4 --groupsize 128 --true-sequential --new-eval --faster-kernel