Instructions to use Tap-M/Luna-AI-Llama2-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tap-M/Luna-AI-Llama2-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="Tap-M/Luna-AI-Llama2-Uncensored")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Tap-M/Luna-AI-Llama2-Uncensored")
model = AutoModelForCausalLM.from_pretrained("Tap-M/Luna-AI-Llama2-Uncensored")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Tap-M/Luna-AI-Llama2-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tap-M/Luna-AI-Llama2-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tap-M/Luna-AI-Llama2-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tap-M/Luna-AI-Llama2-Uncensored

SGLang

How to use Tap-M/Luna-AI-Llama2-Uncensored 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 "Tap-M/Luna-AI-Llama2-Uncensored" \
    --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": "Tap-M/Luna-AI-Llama2-Uncensored",
		"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 "Tap-M/Luna-AI-Llama2-Uncensored" \
        --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": "Tap-M/Luna-AI-Llama2-Uncensored",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tap-M/Luna-AI-Llama2-Uncensored with Docker Model Runner:
```
docker model run hf.co/Tap-M/Luna-AI-Llama2-Uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Description

“Luna AI Llama2 Uncensored” is a Llama2 based Chat model
fine-tuned on over 40,000 long form chat discussions
This model was fine-tuned by Tap, the creator of Luna AI.

Model Training

The fine-tuning process was performed on an 8x a100 80GB machine.
The model was trained on synthetic outputs which include multiple rounds of chats between Human & AI.

4bit GPTQ Version provided by @TheBloke - for GPU inference
GGML Version provided by @TheBloke - For CPU inference

Prompt Format

The model follows the Vicuna 1.1/ OpenChat format:

USER: I have difficulties in making friends, and I really need someone to talk to. Would you be my friend?

ASSISTANT: Of course! Friends are always here for each other. What do you like to do?

Benchmark Results


Task	Version	Metric	Value	Stderr
arc_challenge	0	acc_norm	0.5512	0.0146
hellaswag	0
mmlu	1	acc_norm	0.46521	0.036
truthfulqa_mc	1	mc2	0.4716	0.0155
Average	-	-	0.5114	0.0150

Downloads last month: 159

Model tree for Tap-M/Luna-AI-Llama2-Uncensored

Finetunes

2 models

Quantizations

8 models

Tap-M
/

Luna-AI-Llama2-Uncensored

Model Description

Model Training

Prompt Format

Benchmark Results

Model tree for Tap-M/Luna-AI-Llama2-Uncensored

Spaces using Tap-M/Luna-AI-Llama2-Uncensored 50