README.md

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
inference: true
tags:
  - pytorch
  - mistral
  - finetuned

This is an ExLlamaV2 quantized model in 4bpw of KoboldAI/Mistral-7B-Holodeck-1 using the default calibration dataset.

Original Model card:

Mistral 7B - Holodeck

Model Description

Mistral 7B-Holodeck is a finetune created using Mistral's 7B model.

Training data

The training data contains around 3000 ebooks in various genres. Most parts of the dataset have been prepended using the following text: [Genre: <genre1>, <genre2>]

### Limitations and Biases
Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).