ikiru/ Dolphin-Mistral-24B-Venice-Edition:latest

8,759 6 months ago

Dolphin Mistral 24B Venice Edition is a collaborative project with Venice.ai 

ollama run ikiru/Dolphin-Mistral-24B-Venice-Edition

Details

6 months ago

d1ab0052a709 · 13GB ·

model
llama
·
23.6B
·
Q4_K_M
template
<s>{{ if .System }}[SYSTEM_PROMPT]{{ .System }}[/SYSTEM_PROMPT]{{ end }}[INST]{{ .Prompt }}[/INST]
params
{ "temperature": 0.15, "top_p": 0.95 }

Readme

What is Dolphin Mistral 24B Venice Edition?

Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini. But these models present problems for businesses seeking to include AI in their products.

  • They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
  • They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
  • They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
  • They can see all your queries and they can potentially use that data in ways you wouldn’t want. Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt. You decide the alignment. You have control of your data. Dolphin does not impose its ethics or guidelines on you. You are the one who decides the guidelines.

Reference

HuggingFace