Instructions to use FINAL-Bench/Darwin-180B-RSI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-180B-RSI with Transformers:

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

pipe = pipeline("image-text-to-text", model="FINAL-Bench/Darwin-180B-RSI")
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-180B-RSI")
model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-180B-RSI", 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-180B-RSI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-180B-RSI"
# 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-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-180B-RSI

SGLang

How to use FINAL-Bench/Darwin-180B-RSI 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-180B-RSI" \
    --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-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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-180B-RSI" \
        --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-180B-RSI",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-180B-RSI with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-180B-RSI
```

Darwin-180B-RSI takes #1 on LEXam and LEXam-hard, with no legal training data

by SeaWolf-AI - opened 25 days ago

Discussion

SeaWolf-AI

FINAL_Bench org 25 days ago

Darwin-180B-RSI is now #1 on the Hugging Face official leaderboards for LEXam and LEXam-hard, two legal reasoning benchmarks.

LEXam (multiple choice, 1,655 questions): 68.94. Previous #1 was DeepSeek-R1 at 52.41.
LEXam-hard (open-ended, 518 questions): 45.72. Previous #1 was Inkling at 40.82.

LEXam was built from 340 real law school exams from Swiss universities, in German and English. It doesn't test whether a model has memorized statutes. It tests whether the model can apply the law to a set of facts and reason its way to a conclusion.

We never trained on legal data. Our self-improvement (RSI) runs used only math and science problems with verifiable answers. The model still took first place on a law exam, which suggests the reasoning habits it sharpened on math and science carry over to other domains.

How we measured:

LEXam: 4 samples per question, majority vote, 32,768-token thinking budget. A single sample alone scores 60.54.
LEXam-hard: 1 sample per question with a 32K thinking budget. The 60 answers that hit the limit were regenerated with 120K. Judged by DeepSeek-R1-0528, the judge specified in the benchmark's official eval.yaml.
All #1 results on the official leaderboards so far:

Math: AIME 2026 100, HMMT Feb 2026 100
Science: GPQA Diamond 94.44
General knowledge: MMLU-Pro 88.12
Visual reasoning: MMMU-Pro 79.48
Law: LEXam 68.94, LEXam-hard 45.72
Full measurement settings are on the model card, and the weights are open.
https://huggingface.co/FINAL-Bench/Darwin-180B-RSI

DedeProGames

25 days ago

•

This comment has been hidden (marked as Abuse)

SeaWolf-AI

FINAL_Bench org 25 days ago

A note on this thread.

We welcome criticism of our models, our numbers and our methods. That includes questions about evaluation protocols, reproducibility and comparisons. If you disagree, tell us why, and we'll answer on the substance.

What we won't host is abuse. Insults, name-calling and repeated hostile comments aimed at people rather than the work don't help anyone reading this page, so accounts that post them will be blocked.

Thanks to everyone who keeps the discussion technical.

DavidAU

25 days ago

@SeaWolf-AI

Absolutely the right thing to do.
Progress and the community must always be protected from those that attempt to stop it.
On ward and upward.

SeaWolf-AI

FINAL_Bench org 25 days ago

@SeaWolf-AI

Absolutely the right thing to do.
Progress and the community must always be protected from those that attempt to stop it.
On ward and upward.

Thank you, @DavidAU . That means a lot coming from you. Onward and upward.

Bc-AI

24 days ago

@SeaWolf-AI well done with the model! could you also maybe make a under 27B model using the same technique? some people like me don't have 128xB200s 🤣

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