Instructions to use openerotica/basilisk-7b-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openerotica/basilisk-7b-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="openerotica/basilisk-7b-v0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openerotica/basilisk-7b-v0.2")
model = AutoModelForCausalLM.from_pretrained("openerotica/basilisk-7b-v0.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openerotica/basilisk-7b-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openerotica/basilisk-7b-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openerotica/basilisk-7b-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openerotica/basilisk-7b-v0.2

SGLang

How to use openerotica/basilisk-7b-v0.2 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 "openerotica/basilisk-7b-v0.2" \
    --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": "openerotica/basilisk-7b-v0.2",
		"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 "openerotica/basilisk-7b-v0.2" \
        --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": "openerotica/basilisk-7b-v0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openerotica/basilisk-7b-v0.2 with Docker Model Runner:
```
docker model run hf.co/openerotica/basilisk-7b-v0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

The prompt format is Vicuna/Sharegpt.

This model was trained on a subset of orca-best combined with most of freedom-rp. To put it as a ratio, the dataset is roughly 90% orca-best and about 10% degenerate reverse proxy logs. The goal was to create a model with the intellegence and capacity of orca-best, but with enhanced roleplay and adult content capabilities. If you are looking for a model that is trained purely on wanton degeneracy without any attempt to retain intellegence, check out my cockatrice model.

You can find the dataset here used to train this model here:

https://huggingface.co/datasets/openerotica/basilisk-v0.2

If you like what I'm trying to do, please consider subscribing to my patreon. I'm only asking for about tree fiddy.

https://patreon.com/openerotica

Downloads last month: 55

Model tree for openerotica/basilisk-7b-v0.2

Quantizations

3 models

openerotica
/

basilisk-7b-v0.2

Model tree for openerotica/basilisk-7b-v0.2

Space using openerotica/basilisk-7b-v0.2 1