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

Libraries

How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("failspy/Llama-3-8B-Instruct-abliterated-GGUF", dtype="auto")

llama-cpp-python

How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="failspy/Llama-3-8B-Instruct-abliterated-GGUF",
	filename="Llama-3-8B-Instruct-abliterated-fp16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

Use Docker

docker model run hf.co/failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with Ollama:
```
ollama run hf.co/failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
```

Unsloth Studio new

How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for failspy/Llama-3-8B-Instruct-abliterated-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for failspy/Llama-3-8B-Instruct-abliterated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for failspy/Llama-3-8B-Instruct-abliterated-GGUF to start chatting

Docker Model Runner
How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0
```

Lemonade

How to use failspy/Llama-3-8B-Instruct-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull failspy/Llama-3-8B-Instruct-abliterated-GGUF:Q8_0

Run and chat with the model

lemonade run user.Llama-3-8B-Instruct-abliterated-GGUF-Q8_0

List all available models

lemonade list

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

This is meta-llama/Llama-3-8B-Instruct with orthogonalized bfloat16 safetensor weights, generated with the methodology that was described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction' which I encourage you to read to understand more.

TL;DR: this model has had certain weights manipulated to "inhibit" the model's ability to express refusal. It is not in anyway guaranteed that it won't refuse you, understand your request, it may still lecture you about ethics/safety, etc. It is tuned in all other respects the same as the original 8B instruct model was, just with the strongest refusal direction orthogonalized out.

GGUF quants

Uploaded quants:

fp16 (in main) - good for converting to other platforms or getting the quantization you actually want, not recommended for inference but obviously highest quality

q8_0 (in main)

q4_k (in main)

Quirkiness awareness notice

This model may come with interesting quirks, as I obviously haven't extensively tested it, and the methodology being so new. I encourage you to play with the model, and post any quirks you notice in the community tab, as that'll help us further understand what this orthogonalization has in the way of side effects. The code I used to generate it (and my published 'Kappa-3' model which is just Phi-3 with the same methodology applied) is available in the Python notebook ortho_cookbook.ipynb.

If you manage to develop further improvements, please share! This is really the most primitive way to use ablation, but there are other possibilities that I believe are as-yet unexplored.

Downloads last month: 1,908

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

8-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support