mannix/
mixtral_7bx2_moe:q3_K_S

298 1 year ago

A high-quality Mixture of Experts (MoE) model with open weights by Mistral AI.

1 year ago

e4d505eb3a09 · 5.6GB ·

model
llama
·
12.9B
·
Q3_K_S
template
"[INST] {{ .System }} {{ .Prompt }} [/INST]"
params
{ "stop": [ "[INST]", "[/INST]" ] }

Readme

The Mixtral-7Bx2 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.

@HuggingFace https://huggingface.co/ManniX-ITA/Mixtral_7Bx2_MoE-GGUF