Jotschi/
dolphin-mistral-24b:24b-instruct-q8_0

170 10 months ago

Dolphin3.0-Mistral-24B

10 months ago

248a41e50dc1 · 25GB ·

model
llama
·
23.6B
·
Q8_0
params
{ "stop": [ "<|im_start|>", "<|im_end|>" ] }
template
{{- range .Messages }}<|im_start|>{{ .Role }} {{ .Content }}<|im_end|> {{ end }}<|im_start|>assistan

Readme

Dolphin 3.0 Mistral 24B 🐬

GGUF conversion and quantization of Dolphin3.0-Mistral-24B model.

Original model by Eric Hartford, Ben Gitter, BlouseJury and Cognitive Computations

Part of the Dolphin 3.0 Collection