v000000's picture
Update README.md
0b1acc1 verified
|
raw
history blame
1.04 kB
metadata
tags:
  - mistral
  - merge

image/png

DupletBoreas-7B-t0.001

A merge of the following models using a custom NearSwap algorithm:

With fearlessdots/WizardLM-2-7B-abliterated as the base model.

WizardLM-2 adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, 
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......

Add Genre's in a list like this.

[Genre: <genre1>, <genre2>]