Instructions to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF", dtype="auto")

llama-cpp-python

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF",
	filename="llama-3.1-70b-instruct-lorablated.Q2_K.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 mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

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 mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

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 mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Ollama:
```
ollama run hf.co/mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
```

Unsloth Studio new

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-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 mlabonne/Llama-3.1-70B-Instruct-lorablated-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 mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF to start chatting

Pi new

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Docker Model Runner:
```
docker model run hf.co/mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M
```

Lemonade

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.1-70B-Instruct-lorablated-GGUF-Q4_K_M

List all available models

lemonade list

🦙 Llama-3.1-70B-Instruct-lorablated

🦙 Llama 3.1 8B Instruct abliterated

This is an uncensored version of Llama 3.1 70B Instruct created with abliteration (see this article to know more about it) using @grimjim's recipe.

More precisely, this is a LoRA-abliterated (lorablated) model:

Extraction: We extract a LoRA adapter by comparing two models: a censored Llama 3 and an abliterated Llama 3
Merge: We merge this new LoRA adapter using task arithmetic to a censored Llama 3.1 to abliterate it.

I adapted this recipe to Llama 3.1 70B using failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 and optimized the LoRA rank.

The model is fully uncensored in my tests and maintains a high level of quality. A more rigorous evaluation is still needed to measure the impact of this process on benchmarks.

Special thanks to @grimjim for this technique (see his 8B model) and @FailSpy for his 70B abliterated model. Please follow them if you're interested in abliterated models.

In addition, thanks to brev.dev for providing me with compute!

🧩 Configuration

This model was merged using the task arithmetic merge method using ./meta-llama/Meta-Llama-3.1-70B-Instruct + Llama-3-70B-Instruct-abliterated-LORA as a base.

The following YAML configuration was used to produce this model:

base_model: meta-llama/Meta-Llama-3.1-70B-Instruct+Llama-3-70B-Instruct-abliterated-LORA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 80]
    model: meta-llama/Meta-Llama-3.1-70B-Instruct+Llama-3-70B-Instruct-abliterated-LORA
    parameters:
      weight: 1.0

You can reproduce this model using the following commands:

# Setup
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit && pip install -e .
pip install bitsandbytes

# Extraction
mergekit-extract-lora failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5 meta-llama/Meta-Llama-3-70B-Instruct Llama-3-70B-Instruct-abliterated-LORA --rank=64

# Merge using previous config
mergekit-yaml config.yaml Llama-3.1-70B-Instruct-lorablated --allow-crimes --lora-merge-cache=./cache