Instructions to use FINAL-Bench/Darwin-2B-Opus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-2B-Opus with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-2B-Opus")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FINAL-Bench/Darwin-2B-Opus")
model = AutoModelForCausalLM.from_pretrained("FINAL-Bench/Darwin-2B-Opus")
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

vLLM

How to use FINAL-Bench/Darwin-2B-Opus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-2B-Opus"
# 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-2B-Opus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-2B-Opus

SGLang

How to use FINAL-Bench/Darwin-2B-Opus 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-2B-Opus" \
    --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-2B-Opus",
		"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-2B-Opus" \
        --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-2B-Opus",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-2B-Opus with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-2B-Opus
```

Just a big thank you for all your hard work🙏

by Cheuv - opened Apr 21

Discussion

Cheuv

Apr 21

Hello Team,
I'm acting like a fanboy just to thank you for your models—they deserve more recognition/kudos!
I also created this post to suggest that you consider creating “offspring” for your models using these custom Qwen3.5 2B I've set aside :)

https://huggingface.co/DavidAU/Qwen3.5-2B-GPT-5.1-HighIQ-INSTRUCT
https://huggingface.co/ertghiu256/Qwen3.5-2b-Kimi-and-Opus-Distillation
https://huggingface.co/Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled
I am convinced that, despite its small size, it can be a real driving force behind a whole range of self-hosted projects.
Thanks again!

SeaWolf-AI

FINAL_Bench org Apr 22

Hello Team,
I'm acting like a fanboy just to thank you for your models—they deserve more recognition/kudos!
I also created this post to suggest that you consider creating “offspring” for your models using these custom Qwen3.5 2B I've set aside :)

https://huggingface.co/DavidAU/Qwen3.5-2B-GPT-5.1-HighIQ-INSTRUCT

https://huggingface.co/ertghiu256/Qwen3.5-2b-Kimi-and-Opus-Distillation

https://huggingface.co/Jackrong/Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled
I am convinced that, despite its small size, it can be a real driving force behind a whole range of self-hosted projects.
Thanks again!

Thank you so much for the kind words and the thoughtful curation! 🙏

You're absolutely right that 2B-class models are underrated for self-hosted workflows — they're where Darwin's efficiency story really shines. Jackrong's 2B is especially interesting to us since we already have a successful breeding history with their 27B Opus-distilled line (Darwin-27B-Opus, GPQA #6 on the official leaderboard).

We'll add these three to our evolutionary breeding queue. The Darwin-2B recipe would run in about an hour on our current setup, so we can share results soon. Any specific benchmarks you'd like us to prioritize for edge/self-hosted use cases?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment