Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Holodeck-1 - GGUF

• Model creator: https://huggingface.co/KoboldAI/
• Original model: https://huggingface.co/KoboldAI/Mistral-7B-Holodeck-1/

Name	Quant method	Size
Mistral-7B-Holodeck-1.Q2_K.gguf	Q2_K	2.53GB
Mistral-7B-Holodeck-1.IQ3_XS.gguf	IQ3_XS	2.81GB
Mistral-7B-Holodeck-1.IQ3_S.gguf	IQ3_S	2.96GB
Mistral-7B-Holodeck-1.Q3_K_S.gguf	Q3_K_S	2.95GB
Mistral-7B-Holodeck-1.IQ3_M.gguf	IQ3_M	3.06GB
Mistral-7B-Holodeck-1.Q3_K.gguf	Q3_K	3.28GB
Mistral-7B-Holodeck-1.Q3_K_M.gguf	Q3_K_M	3.28GB
Mistral-7B-Holodeck-1.Q3_K_L.gguf	Q3_K_L	3.56GB
Mistral-7B-Holodeck-1.IQ4_XS.gguf	IQ4_XS	3.67GB
Mistral-7B-Holodeck-1.Q4_0.gguf	Q4_0	3.83GB
Mistral-7B-Holodeck-1.IQ4_NL.gguf	IQ4_NL	3.87GB
Mistral-7B-Holodeck-1.Q4_K_S.gguf	Q4_K_S	3.86GB
Mistral-7B-Holodeck-1.Q4_K.gguf	Q4_K	4.07GB
Mistral-7B-Holodeck-1.Q4_K_M.gguf	Q4_K_M	4.07GB
Mistral-7B-Holodeck-1.Q4_1.gguf	Q4_1	4.24GB
Mistral-7B-Holodeck-1.Q5_0.gguf	Q5_0	4.65GB
Mistral-7B-Holodeck-1.Q5_K_S.gguf	Q5_K_S	4.65GB
Mistral-7B-Holodeck-1.Q5_K.gguf	Q5_K	4.78GB
Mistral-7B-Holodeck-1.Q5_K_M.gguf	Q5_K_M	4.78GB
Mistral-7B-Holodeck-1.Q5_1.gguf	Q5_1	5.07GB
Mistral-7B-Holodeck-1.Q6_K.gguf	Q6_K	5.53GB
Mistral-7B-Holodeck-1.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 language:

• en pipeline_tag: text-generation inference: true tags:
• pytorch
• mistral
• finetuned

---

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).