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

Libraries

How to use nbeerbower/Llama-3.1-Nemotron-lorablated-70B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B

SGLang

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

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

Llama-3.1-Nemotron-lorablated-70B

An uncensored version of nvidia/Llama-3.1-Nemotron-70B-Instruct-HF created by merging mlabonne/Llama-3-70B-Instruct-abliterated-LORA using task arithmetic.

Method

This model was created using mergekit.

From Ubuntu 24.04 (as root):

apt update
apt install pipx
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit && pipx install -e .

mergekit-yaml config.yaml Llama-3.1-Nemotron-lorablated-70B --allow-crimes --lora-merge-cache=./cache

See @mlabonne's Llama-3.1-70B-Instruct-lorablated for more details on how the LoRA was extracted.

Configuration

The following YAML configuration was used to produce this model:

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