Text Generation
Transformers
llama
Inference Endpoints
Guanaco-65B-GPTQ / README.md
raffr's picture
guanaco-65b-gptq
ae47724
|
raw
history blame
170 Bytes

Guanaco 65B GPTQ

From timdettmers: https://huggingface.co/timdettmers/guanaco-65b

Folders

ggml: q4_0 and q4_1

gptq: works with Triton and CUDA branches