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)

# pip install -U transformers accelerate
# 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", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

Llama-3-8B-Instruct-abliterated-v2 / README.md

failspy

Update README.md

4c4c3cc verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.67 kB

	---
	library_name: transformers
	license: llama3
	---

	# 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!](https://discord.gg/cognitivecomputations)

	## 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](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/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](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/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](https://huggingface.co/failspy/Llama-3-8B-Instruct-abliterated-v2-GGUF).