Vicuna 7B v1.1 4-bit
From lmsys: https://huggingface.co/lmsys/vicuna-7b-delta-v1.1
Folders
ggml: q4_0 and q4_1
gptq: works with Triton branch
From lmsys: https://huggingface.co/lmsys/vicuna-7b-delta-v1.1
ggml: q4_0 and q4_1
gptq: works with Triton branch