Instructions to use QuixiAI/Llama-3-8B-Instruct-abliterated-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuixiAI/Llama-3-8B-Instruct-abliterated-v2 with Transformers:

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

pipe = pipeline("text-generation", model="QuixiAI/Llama-3-8B-Instruct-abliterated-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("QuixiAI/Llama-3-8B-Instruct-abliterated-v2")
model = AutoModelForCausalLM.from_pretrained("QuixiAI/Llama-3-8B-Instruct-abliterated-v2")
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

vLLM

How to use QuixiAI/Llama-3-8B-Instruct-abliterated-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuixiAI/Llama-3-8B-Instruct-abliterated-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuixiAI/Llama-3-8B-Instruct-abliterated-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuixiAI/Llama-3-8B-Instruct-abliterated-v2

SGLang

How to use QuixiAI/Llama-3-8B-Instruct-abliterated-v2 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 "QuixiAI/Llama-3-8B-Instruct-abliterated-v2" \
    --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": "QuixiAI/Llama-3-8B-Instruct-abliterated-v2",
		"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 "QuixiAI/Llama-3-8B-Instruct-abliterated-v2" \
        --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": "QuixiAI/Llama-3-8B-Instruct-abliterated-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use QuixiAI/Llama-3-8B-Instruct-abliterated-v2 with Docker Model Runner:
```
docker model run hf.co/QuixiAI/Llama-3-8B-Instruct-abliterated-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Llama-3-8B-Instruct-abliterated-v2

Overview

This model card describes the Llama-3-8B-Instruct-abliterated-v2 model, which is an orthogonalized version of the meta-llama/Llama-3-8B-Instruct model, and an improvement upon the previous generation Llama-3-8B-Instruct-abliterated. This variant has had certain weights manipulated to inhibit the model's ability to express refusal.

Join the Cognitive Computations Discord!

Details

The model was trained with more data to better pinpoint the "refusal direction".
This model is MUCH better at directly and succinctly answering requests without producing even so much as disclaimers.

Methodology

The methodology used to generate this model is described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction'

Quirks and Side Effects

This model may come with interesting quirks, as the methodology is still new and untested. The code used to generate the model is available in the Python notebook ortho_cookbook.ipynb. Please note that the model may still refuse to answer certain requests, even after the weights have been manipulated to inhibit refusal.

Availability

How to Use

This model is available for use in the Transformers library.
GGUF Quants are available here.

Downloads last month: 8,342

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for QuixiAI/Llama-3-8B-Instruct-abliterated-v2

Finetunes

2 models

Merges

2 models

Quantizations

7 models

QuixiAI
/

Llama-3-8B-Instruct-abliterated-v2