Instructions to use FINAL-Bench/Darwin-4B-Genesis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-4B-Genesis with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-4B-Genesis")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("FINAL-Bench/Darwin-4B-Genesis")
model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-4B-Genesis", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FINAL-Bench/Darwin-4B-Genesis with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-4B-Genesis"
# 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-4B-Genesis",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-4B-Genesis

SGLang

How to use FINAL-Bench/Darwin-4B-Genesis 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-4B-Genesis" \
    --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-4B-Genesis",
		"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-4B-Genesis" \
        --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-4B-Genesis",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-4B-Genesis with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-4B-Genesis
```

Darwin-4B-Genesis

Commit History

May 16

03:35
Improve model card metadata and link to paper⁠

nielsr HF Staff

Verified signature
7aba7f7

May 15

02:16
Update README.md

SeaWolf-AI

Verified signature
ea2fc28
02:14
Update README.md

SeaWolf-AI

Verified signature
4d89077
02:11
Update README.md

SeaWolf-AI

Verified signature
1399093
02:08
Update README.md

SeaWolf-AI

Verified signature
7176b3e

May 9

23:54
fix: add stop_strings to handle cross-arch chat template artifacts (rikunarita-2 issue)

SeaWolf-AI

Verified signature
ef8b5d4

Apr 11

03:14
Rename tree.webp to tree.png

SeaWolf-AI

Verified signature
80633b3
03:13
Update README.md

SeaWolf-AI

Verified signature
de47cbb
03:11
Rename ffe25cfe-4e95-4398-bc6d-94d78c566316.webp to tree.webp

SeaWolf-AI

Verified signature
f26ccb5
03:11
Upload ffe25cfe-4e95-4398-bc6d-94d78c566316.webp

SeaWolf-AI

Verified signature
2aad285
03:06
Rename readme.md to README.md

SeaWolf-AI

Verified signature
ea63576
03:04
Create readme.md

SeaWolf-AI

Verified signature
abae97a
02:14
Rename 이문세 원곡.mp3 to music.mp3

SeaWolf-AI

Verified signature
908e7b7
02:14
Upload 이문세 원곡.mp3

SeaWolf-AI

Verified signature
8a2bb46

Apr 10

23:06
Upload folder using huggingface_hub

SeaWolf-AI

Verified signature
fca0820
23:03
initial commit

SeaWolf-AI

Verified signature
5f4bf8c

Commit History

May 16

Improve model card metadata and link to paper⁠

May 15

Update README.md

Update README.md

Update README.md

Update README.md

May 9

fix: add stop_strings to handle cross-arch chat template artifacts (rikunarita-2 issue)

Apr 11

Rename tree.webp to tree.png

Update README.md

Rename ffe25cfe-4e95-4398-bc6d-94d78c566316.webp to tree.webp

Upload ffe25cfe-4e95-4398-bc6d-94d78c566316.webp

Rename readme.md to README.md

Create readme.md

Rename 이문세 원곡.mp3 to music.mp3

Upload 이문세 원곡.mp3

Apr 10

Upload folder using huggingface_hub

initial commit