Not-For-All-Audiences

Instructions to use KoboldAI/Mistral-7B-Erebus-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KoboldAI/Mistral-7B-Erebus-v3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="KoboldAI/Mistral-7B-Erebus-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KoboldAI/Mistral-7B-Erebus-v3")
model = AutoModelForCausalLM.from_pretrained("KoboldAI/Mistral-7B-Erebus-v3", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KoboldAI/Mistral-7B-Erebus-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KoboldAI/Mistral-7B-Erebus-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/Mistral-7B-Erebus-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KoboldAI/Mistral-7B-Erebus-v3

SGLang

How to use KoboldAI/Mistral-7B-Erebus-v3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "KoboldAI/Mistral-7B-Erebus-v3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/Mistral-7B-Erebus-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "KoboldAI/Mistral-7B-Erebus-v3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KoboldAI/Mistral-7B-Erebus-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KoboldAI/Mistral-7B-Erebus-v3 with Docker Model Runner:
```
docker model run hf.co/KoboldAI/Mistral-7B-Erebus-v3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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: <comma-separated list of genres>] 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!

Downloads last month: 23

Safetensors

Model size

7B params

Tensor type

F16

Model tree for KoboldAI/Mistral-7B-Erebus-v3

Finetunes

1 model

Merges

10 models

Quantizations

5 models