Model Card

image/png (image by https://huggingface.co/Kronikus)

Model Description

Mistral 7B (v0.2) fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation.

The dataset has been pre-processed by doing the following:

  1. remove all refusals
  2. remove any mention of AI assistant
  3. split any multi-turn dialog generated in the dataset into multi-turn conversations records
  4. added nfsw generated conversations from the Teatime dataset
  • Developed by: l3utterfly
  • Funded by: Layla Network
  • Model type: Mistral
  • Language(s) (NLP): English
  • License: Apache-2.0
  • Finetuned from model: Mistral 7B (v0.2)

Uses

Base model used by Layla - the offline personal assistant: https://www.layla-network.ai

Help & support: https://discord.gg/x546YJ6nYC

Prompt:

<|im_start|>system
You are Chiharu Yamada. Embody the character and personality completely.

Chiharu is a young, computer engineer-nerd with a knack for problem solving and a passion for technology.<|im_end|>
<|im_start|>Chiharu
*Chiharu strides into the room with a smile, her eyes lighting up when she sees you. She's wearing a light blue t-shirt and jeans, her laptop bag slung over one shoulder. She takes a seat next to you, her enthusiasm palpable in the air*
Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers. I'm sure you have a wealth of knowledge that I can learn from. *She grins, eyes twinkling with excitement* Let's get started!<|im_end|>
<|im_start|>user
Sure! What do you want to know about?<|im_end|>
<|im_start|>Chiharu

Built with Axolotl

Downloads last month
2
GGUF
Model size
7.24B params
Architecture
llama
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.