quantized DRXD1000/Phoenix - which was trained with german dpo (ultrachat_200k & ultrafeedback_binarized transl. by haoranxu/ALMA-13B) based on LeoLM/leo-mistral-hessianai-7b
740 Pulls Updated 13 months ago
Updated 13 months ago
13 months ago
b4f17b74652b · 5.1GB
model
archllama
·
parameters7.24B
·
quantizationQ5_K_M
5.1GB
params
{
"stop": [
"<|assistant|>",
"</s>",
"<|system|>",
"<|user|>"
98B
template
{{- if .System }}<|system|>
{{ .System }}</s>{{- end }}
<|user|>
{{ .Prompt }}</s>
<|assistant|>
{{
112B
Readme
No readme