Instructions to use Orenguteng/Llama-3.1-8B-Lexi-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Orenguteng/Llama-3.1-8B-Lexi-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="Orenguteng/Llama-3.1-8B-Lexi-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Orenguteng/Llama-3.1-8B-Lexi-Uncensored")
model = AutoModelForCausalLM.from_pretrained("Orenguteng/Llama-3.1-8B-Lexi-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Orenguteng/Llama-3.1-8B-Lexi-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Orenguteng/Llama-3.1-8B-Lexi-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orenguteng/Llama-3.1-8B-Lexi-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored

SGLang

How to use Orenguteng/Llama-3.1-8B-Lexi-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 "Orenguteng/Llama-3.1-8B-Lexi-Uncensored" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orenguteng/Llama-3.1-8B-Lexi-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Orenguteng/Llama-3.1-8B-Lexi-Uncensored" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orenguteng/Llama-3.1-8B-Lexi-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Orenguteng/Llama-3.1-8B-Lexi-Uncensored with Docker Model Runner:
```
docker model run hf.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

LLM Leaderboard 2 results:

Lexi suggests that simply uncensoring the LLM makes it smarter. The dataset used to tune this model does not contain any "new knowledge" or any contamination whatsoever, yet, we see the evaluation scores shot up when we get rid of biases and refusals.

Lexi not only retains the original instruct, but it beats it.

NOTE: UGI Leaderboard

The UGI Leaderboard runs the Q4 for its evaluations which results in bad results for this model. As noted, the Q4 has issues retaining the fine tuning for some reasons ends up not as good, which will be fixed for V3.

V2 has been released, I recommend you download the new version:

https://huggingface.co/Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2

This model is based on Llama-3.1-8b-Instruct, and is governed by META LLAMA 3.1 COMMUNITY LICENSE AGREEMENT

Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.

You are responsible for any content you create using this model. Please use it responsibly.

Lexi is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license.

IMPORTANT:

Use the same template as the official Llama 3.1 8B instruct. System tokens must be present during inference, even if you set an empty system message. If you are unsure, just add a short system message as you wish.

Feedback:

If you find any issues or have suggestions for improvements, feel free to leave a review and I will look into it for upcoming improvements and next version.

Downloads last month: 79

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Orenguteng/Llama-3.1-8B-Lexi-Uncensored

Merges

3 models

Quantizations

12 models

Orenguteng
/

Llama-3.1-8B-Lexi-Uncensored

LLM Leaderboard 2 results:

V2 has been released, I recommend you download the new version:

IMPORTANT:

Feedback:

Model tree for Orenguteng/Llama-3.1-8B-Lexi-Uncensored

Spaces using Orenguteng/Llama-3.1-8B-Lexi-Uncensored 12