Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mistral-7B-Erebus-v3 - GGUF

• Model creator: https://huggingface.co/KoboldAI/
• Original model: https://huggingface.co/KoboldAI/Mistral-7B-Erebus-v3/

Name	Quant method	Size
Mistral-7B-Erebus-v3.Q2K.gguf	Q2K	2.53GB
Mistral-7B-Erebus-v3.IQ3XS.gguf	IQ3XS	2.81GB
Mistral-7B-Erebus-v3.IQ3S.gguf	IQ3S	2.96GB
Mistral-7B-Erebus-v3.Q3KS.gguf	Q3K_S	2.95GB
Mistral-7B-Erebus-v3.IQ3M.gguf	IQ3M	3.06GB
Mistral-7B-Erebus-v3.Q3K.gguf	Q3K	3.28GB
Mistral-7B-Erebus-v3.Q3KM.gguf	Q3K_M	3.28GB
Mistral-7B-Erebus-v3.Q3KL.gguf	Q3K_L	3.56GB
Mistral-7B-Erebus-v3.IQ4XS.gguf	IQ4XS	3.67GB
Mistral-7B-Erebus-v3.Q40.gguf	Q40	3.83GB
Mistral-7B-Erebus-v3.IQ4NL.gguf	IQ4NL	3.87GB
Mistral-7B-Erebus-v3.Q4KS.gguf	Q4K_S	3.86GB
Mistral-7B-Erebus-v3.Q4K.gguf	Q4K	4.07GB
Mistral-7B-Erebus-v3.Q4KM.gguf	Q4K_M	4.07GB
Mistral-7B-Erebus-v3.Q41.gguf	Q41	4.24GB
Mistral-7B-Erebus-v3.Q50.gguf	Q50	4.65GB
Mistral-7B-Erebus-v3.Q5KS.gguf	Q5K_S	4.65GB
Mistral-7B-Erebus-v3.Q5K.gguf	Q5K	4.78GB
Mistral-7B-Erebus-v3.Q5KM.gguf	Q5K_M	4.78GB
Mistral-7B-Erebus-v3.Q51.gguf	Q51	5.07GB
Mistral-7B-Erebus-v3.Q6K.gguf	Q6K	5.53GB
Mistral-7B-Erebus-v3.Q80.gguf	Q80	7.17GB

Original model description:

---

license: apache-2.0
language:
- en
pipeline_tag: text-generation
inference: false
tags:
- pytorch
- mistral
- finetuned
- not-for-all-audiences

---

Mistral-7B-Erebus

Model description

This is the third generation of the original Shinen made by Mr. Seeker. The full dataset consists of 8 different sources, all surrounding the "Adult" theme. The name "Erebus" comes from the greek mythology, also named "darkness". This is in line with Shin'en, or "deep abyss". For inquiries, please contact the KoboldAI community. Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.

Training procedure

Mistral-7B-Erebus was trained on 8x A6000 Ada GPU's for a single epoch. No special frameworks have been used.

Training data

The data can be divided in 8 different datasets:

• Literotica (everything with 3.0/5 or higher)
• Sexstories (everything with 70 or higher)
• Dataset-G (private dataset of X-rated stories)
• Doc's Lab (all stories)
• Lushstories (Editor's pick)
• Swinglifestyle (all stories)
• Pike-v2 Dataset (novels with "adult" rating)
• SoFurry (collection of various animals)

The dataset uses [Genre: ] for tagging.

The full dataset is 2.3B tokens in size.

Limitations and biases

Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion). Warning: This model has a very strong NSFW bias!