cas / mistral-instruct-v0.2-2x7b-moe

quantization of perlthoughts/Mistral-7B-Instruct-v0.2-2x7B-MoE

13B

251 Pulls Updated 4 months ago

7 months ago

ad95f022607a · 7.3GB

model
llama
·
12.9B
·
Q4_K_M
template
[INST] {{ .System }} {{ .Prompt }} [/INST]
params
{"num_ctx":32000,"stop":["[INST]","[/INST]"]}

Readme

No readme