latest
26GB
This model was built from the https://huggingface.co/paulkl/mixtral-8x7b-instruct-v0.1_Q4b_wa (gguf)
8x7B
10 Pulls Updated 6 months ago
Updated 6 months ago
6 months ago
7dc5a45be6b6 · 26GB
model
archllama
·
parameters46.7B
·
quantizationQ4_0
26GB
template
[INST] {{ .Prompt }} [/INST]
28B
params
{"num_ctx":32768,"num_thread":8}
33B
Readme
No readme