Instructions to use FINAL-Bench/Darwin-9B-MFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-9B-MFP4 with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-9B-MFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-9B-MFP4")
model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-9B-MFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Darwin-9B-MFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-9B-MFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FINAL-Bench/Darwin-9B-MFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-9B-MFP4

SGLang

How to use FINAL-Bench/Darwin-9B-MFP4 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 "FINAL-Bench/Darwin-9B-MFP4" \
    --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": "FINAL-Bench/Darwin-9B-MFP4",
		"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 "FINAL-Bench/Darwin-9B-MFP4" \
        --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": "FINAL-Bench/Darwin-9B-MFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-9B-MFP4 with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-9B-MFP4
```

SeaWolf-AI commited on Jul 23

Commit

e496830

verified ·

1 Parent(s): d54ecd4

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -17,6 +17,12 @@ tags:
 library_name: transformers
 ---
 # Darwin-9B-MFP4
 **Mixed-Precision FP4** quantization of [Darwin-9B-Opus](https://huggingface.co/FINAL-Bench/Darwin-9B-Opus), built on NVIDIA Blackwell-native NVFP4.

 library_name: transformers
 ---
+> ### 📱 Want it on your phone or a GPU-less PC? → **POCKET**
+> VIDRAFT's on-device family: a 35B model that runs on **iPhone** and on **CPU with no GPU** — stock `llama.cpp`, no fork.
+>
+> [![35B](https://img.shields.io/badge/POCKET--35B-GGUF-243456)](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) [![KR GGUF](https://img.shields.io/badge/POCKET--KR-GGUF-7A1F3D)](https://huggingface.co/FINAL-Bench/POCKET-KR-GGUF) [![KR MLX](https://img.shields.io/badge/POCKET--KR-MLX_iPhone-0f6e56)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) [![EN GGUF](https://img.shields.io/badge/POCKET--EN-GGUF-185fa5)](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF)
 # Darwin-9B-MFP4
 **Mixed-Precision FP4** quantization of [Darwin-9B-Opus](https://huggingface.co/FINAL-Bench/Darwin-9B-Opus), built on NVIDIA Blackwell-native NVFP4.