Instructions to use Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF

SGLang

How to use Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF 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 "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF" \
    --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": "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF",
		"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 "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF" \
        --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": "Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF
```

Sphinx 8B v0 Jbliterated GGUF

Preview for upcoming Gemma/Mistral 12B finetune [in progress]. The dataset is around 450 entries of various occult sources, philosophy, and psychology.

This is a finetune of ApolloRaines/Llama-3.3-8B-Instruct-128K-Jbliterated made using 1 epoch, 1e-4 LR and the PMPF tool.

Fully uncensored. Uses llama 3 chat template

Update

The model is unstable and broken

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for Naphula-Archives/Sphinx-8B-v0-Jbliterated-GGUF

Base model

allura-forge/Llama-3.3-8B-Instruct

Finetuned

shb777/Llama-3.3-8B-Instruct-128K

Finetuned

ApolloRaines/Llama-3.3-8B-Instruct-128K-Jbliterated

Finetuned

(1)

this model