x0001's picture
Update README.md
0dac29a
|
raw
history blame
162 Bytes

Vicuna 13B v1.1 4-bit

From lmsys: https://huggingface.co/lmsys/vicuna-13b-delta-v1.1

Folders

ggml: q4_0 and q4_1

gptq: Triton and CUDA branches