Instructions to use AMead10/Llama-3.1-SuperNova-Lite-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AMead10/Llama-3.1-SuperNova-Lite-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="AMead10/Llama-3.1-SuperNova-Lite-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AMead10/Llama-3.1-SuperNova-Lite-AWQ")
model = AutoModelForCausalLM.from_pretrained("AMead10/Llama-3.1-SuperNova-Lite-AWQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AMead10/Llama-3.1-SuperNova-Lite-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AMead10/Llama-3.1-SuperNova-Lite-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AMead10/Llama-3.1-SuperNova-Lite-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AMead10/Llama-3.1-SuperNova-Lite-AWQ

SGLang

How to use AMead10/Llama-3.1-SuperNova-Lite-AWQ 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 "AMead10/Llama-3.1-SuperNova-Lite-AWQ" \
    --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": "AMead10/Llama-3.1-SuperNova-Lite-AWQ",
		"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 "AMead10/Llama-3.1-SuperNova-Lite-AWQ" \
        --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": "AMead10/Llama-3.1-SuperNova-Lite-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AMead10/Llama-3.1-SuperNova-Lite-AWQ with Docker Model Runner:
```
docker model run hf.co/AMead10/Llama-3.1-SuperNova-Lite-AWQ
```

Overview

Llama-3.1-SuperNova-Lite is an 8B parameter model developed by Arcee.ai, based on the Llama-3.1-8B-Instruct architecture. It is a distilled version of the larger Llama-3.1-405B-Instruct model, leveraging offline logits extracted from the 405B parameter variant. This 8B variation of Llama-3.1-SuperNova maintains high performance while offering exceptional instruction-following capabilities and domain-specific adaptability.

The model was trained using a state-of-the-art distillation pipeline and an instruction dataset generated with EvolKit, ensuring accuracy and efficiency across a wide range of tasks. For more information on its training, visit blog.arcee.ai.

Llama-3.1-SuperNova-Lite excels in both benchmark performance and real-world applications, providing the power of large-scale models in a more compact, efficient form ideal for organizations seeking high performance with reduced resource requirements.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.73
IFEval (0-Shot)	80.17
BBH (3-Shot)	31.57
MATH Lvl 5 (4-Shot)	15.48
GPQA (0-shot)	7.49
MuSR (0-shot)	11.67
MMLU-PRO (5-shot)	31.97

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

I32

F16

Model tree for AMead10/Llama-3.1-SuperNova-Lite-AWQ

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(866)

this model

Dataset used to train AMead10/Llama-3.1-SuperNova-Lite-AWQ

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

80.170
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

31.570
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

15.480
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

7.490
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

11.670
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

31.970