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

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

pipe = pipeline("text-generation", model="mlabonne/Llama-3.1-70B-Instruct-lorablated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/Llama-3.1-70B-Instruct-lorablated")
model = AutoModelForCausalLM.from_pretrained("mlabonne/Llama-3.1-70B-Instruct-lorablated")
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 mlabonne/Llama-3.1-70B-Instruct-lorablated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/Llama-3.1-70B-Instruct-lorablated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/Llama-3.1-70B-Instruct-lorablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use mlabonne/Llama-3.1-70B-Instruct-lorablated 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 "mlabonne/Llama-3.1-70B-Instruct-lorablated" \
    --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": "mlabonne/Llama-3.1-70B-Instruct-lorablated",
		"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 "mlabonne/Llama-3.1-70B-Instruct-lorablated" \
        --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": "mlabonne/Llama-3.1-70B-Instruct-lorablated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlabonne/Llama-3.1-70B-Instruct-lorablated with Docker Model Runner:
```
docker model run hf.co/mlabonne/Llama-3.1-70B-Instruct-lorablated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🦙 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!

🔍 Applications

General-purpose, role-play (see feedback from McUH). Use the Llama 3 chat template.

⚡️ Quantization

GGUF: https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-lorablated-GGUF
Bartowski: https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF (with IQ quants)

🧩 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