| 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](https://huggingface.co./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). |