A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA. Instructed to work with Cline (prev. Claude Dev).
tools
51 Pulls Updated 3 weeks ago
Updated 3 weeks ago
3 weeks ago
0cb6523c3501 · 4.8GB
model
archllama
·
parameters12.2B
·
quantizationQ2_K
4.8GB
params
{"num_ctx":32768,"repeat_last_n":64,"repeat_penalty":1.1,"stop":["\u003c/s\u003e","[INST]","[/INST]"
144B
template
{{- /* Initial system message with core instructions */ -}}
{{- if .Messages }}
{{- if or .System .
1.7kB
license
Apache License
Version 2.0, January 2004
11kB
Readme
No readme