ek826
/

Meta-Llama-3.1-405B-Instruct-4.25bpw-gqa-exl2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Meta-Llama-3.1-405B-Instruct-4.25bpw-gqa-exl2 / output-00010-of-00026.safetensors

Commit History

new 4.25bpw with 8 heads gqa

c673aa3
verified

ek826 commited on Aug 17