Instructions to use nyunai/nyun-c2-llama3-56B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nyunai/nyun-c2-llama3-56B with Transformers:

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

pipe = pipeline("text-generation", model="nyunai/nyun-c2-llama3-56B", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nyunai/nyun-c2-llama3-56B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("nyunai/nyun-c2-llama3-56B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nyunai/nyun-c2-llama3-56B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nyunai/nyun-c2-llama3-56B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyunai/nyun-c2-llama3-56B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nyunai/nyun-c2-llama3-56B

SGLang

How to use nyunai/nyun-c2-llama3-56B 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 "nyunai/nyun-c2-llama3-56B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyunai/nyun-c2-llama3-56B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "nyunai/nyun-c2-llama3-56B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyunai/nyun-c2-llama3-56B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nyunai/nyun-c2-llama3-56B with Docker Model Runner:
```
docker model run hf.co/nyunai/nyun-c2-llama3-56B
```

🔹 Key Highlights:

20% Fewer Parameters: nyun-c2-llama3-56B comprises approximately 20% fewer parameters than the popular Llama-3-70B.
Better Performance: Despite having far fewer parameters, this model has better performance than Llama-3-70B.
No Fine-Tuning Required: This model undergoes no fine-tuning, showcasing the raw potential of our optimization techniques.

Pipeline and Collaboration

For insights into the pipeline and the list of methods used to optimize these models, check out our PruneGPT repository (https://github.com/nyunAI/PruneGPT). We invite companies and organizations interested in joining forces with us to release more such open-source variants to reach out at contact@nyunai.com.

Model Performance

Dataset	nyun-c2-llama3-56B	Meta-Llama3-70B	Meta-Llama2-70B	MBZUAI K2-65B
MMLU (5-shot)	78.4	79.5	69.7	67.9
Winogrande (5-shot)	85.5	83.1	81.8	77.0
BoolQ (0-shot)	85.1	79.0	73.1	83.0
Hellaswag (10-shot)	86.9	88.0	86.9	85.5
Arc Challenge (25-shot)	66.0	68.8	67.2	64.8
GSM8K (5-shot)	76.8	76.9	52.6	50.2
Average	79.8	79.2	71.9	71.4

Developed by: Nyun AI
Repository: Github

Downloads last month: 23

Safetensors

Model size

56B params

Tensor type

F16