Instructions to use grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B")
model = AutoModelForCausalLM.from_pretrained("grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B")
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 grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B

SGLang

How to use grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B 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 "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B" \
    --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": "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B",
		"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 "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B" \
        --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": "grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B with Docker Model Runner:
```
docker model run hf.co/grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3.1-SuperNova-Lite-lorabilterated-8B

An experiment in model safety:

This repo contains a merge of pre-trained language models created using mergekit.

Application of the abliteration LoRA derived from Llama 3 was partially successful in reducing refusals, with increased compliance in the qualified contexts of hypotheticals and roleplay. Baseline safety appears intact. We hypothesize that the distillation process transferred additional safety encoded in a way that differed from the abliteration originally targeted by failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 against Llama 3. The partial effectiveness is proof of a common model ancestry between Llama 3 and Llama 3.1, though we are not privy to the specific details.

Built with Llama.

Merge Details

Merge Method

This model was merged using the passthrough merge method using arcee-ai/Llama-3.1-SuperNova-Lite + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Example of mergekit CLI command for illustrative purposes:

mergekit-yaml mergekit_config.yml model_directory/llama-model-8B --cuda --lora-merge-cache lora_merge_cache

Configuration

The following YAML configuration was used to produce this model:

base_model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
merge_method: passthrough
models:
  - model: arcee-ai/Llama-3.1-SuperNova-Lite+grimjim/Llama-3-Instruct-abliteration-LoRA-8B