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

Commit History

Oct 5 20 days ago

23:32
MDPBench eval result: re-add as mdp_bench.yaml (clear stale future-date index)

SeaWolf-AI

Verified signature
47d0a16
23:16
MDPBench eval result: date in UTC (2026-10-05)

SeaWolf-AI

Verified signature
f869193
23:05
MDPBench 83.65 (#1) + card: ten #1s in the RSI line

SeaWolf-AI

Verified signature
19e962f
07:30
IFStruct 98.95 (#1) + card: nine #1s in the RSI line

SeaWolf-AI

Verified signature
3aefe84
02:05
card: R3 is #1 on ExtractBench (90.29), #3 on EvasionBench

SeaWolf-AI

Verified signature
431eadc

Oct 2 23 days ago

06:17
card: link POCKET-Darwin-180B-GGUF (4-bit, laptop / CPU-only)

SeaWolf-AI

Verified signature
455f3af

Sep 30 25 days ago

03:24
card: clarify Model-level RSI wording

SeaWolf-AI

Verified signature
bc3c7b0
03:22
card: Model-level RSI vs harness-level RSI section + tag

SeaWolf-AI

Verified signature
0e330b7

Sep 29 26 days ago

19:05
ztc: ship early ZTC probe (AUROC 0.64) + handler

SeaWolf-AI

Verified signature
7b875ae
15:53
card: add LEXam-hard column to comparison table

SeaWolf-AI

Verified signature
3b51b43
15:41
card: LEXam-hard #1 (seven #1s)

SeaWolf-AI

Verified signature
2965520
15:41
eval: LEXam-hard 45.72

SeaWolf-AI

Verified signature
9eb2e46
13:08
card: clarify comparison scope (open-weight models)

SeaWolf-AI

Verified signature
a393f62
12:39
card: add LEXam column to comparison table

SeaWolf-AI

Verified signature
2249d08
12:32
card: LEXam #1 (six #1s)

SeaWolf-AI

Verified signature
63b619e
12:31
eval: LEXam mcq_4_choices 68.94 (maj@4)

SeaWolf-AI

Verified signature
ad766b8

Sep 28 27 days ago

07:04
Card: link all badges

SeaWolf-AI

Verified signature
6f7beb6
07:04
Card: add full-field chart

SeaWolf-AI

Verified signature
9e6ab9e
07:03
Chart: five leaderboards full field

SeaWolf-AI

Verified signature
387824a
07:02
Card: five #1s chart and table at the top

SeaWolf-AI

Verified signature
63a0f0f
06:59
Card: dedupe comparison section

SeaWolf-AI

Verified signature
66a6168
06:58
Card: HMMT Feb 2026 100 #1 - five leaderboards

SeaWolf-AI

Verified signature
8a0133b
06:58
Chart: add HMMT

SeaWolf-AI

Verified signature
680f94f
06:57
HMMT Feb 2026 100.0 (maj@16)

SeaWolf-AI

Verified signature
d01e97e
06:57
Card: head-to-head with Chinese frontier models

SeaWolf-AI

Verified signature
4eb5973
06:57
Chart: vs Chinese frontier models

SeaWolf-AI

Verified signature
227dc30
06:56
Card: head-to-head comparison table

SeaWolf-AI

Verified signature
54b2746
06:48
Card: evaluation protocol, ZTC section

SeaWolf-AI

Verified signature
461f9f2
06:30
Card: AIME 2026 model-index

SeaWolf-AI

Verified signature
49ff532
06:22
Card: AIME 2026 100 #1

SeaWolf-AI

Verified signature
674523f
06:21
AIME 2026 100.0 (maj@16)

SeaWolf-AI

Verified signature
766794c
06:10
Card: #1 on GPQA, MMLU-Pro, MMMU-Pro

SeaWolf-AI

Verified signature
04796e4
05:53
Card: MMMU-Pro #1, MMLU-Pro #1

SeaWolf-AI

Verified signature
41f9531
05:52
MMMU-Pro 79.48

SeaWolf-AI

Verified signature
f3cb447
04:43
Card: papers, collections, research, citation, related models

SeaWolf-AI

Verified signature
c8c2128
03:35
Add files using upload-large-folder tool

SeaWolf-AI

Verified signature
e098a84
03:35
Add files using upload-large-folder tool

SeaWolf-AI

Verified signature
c209e70
03:35
Add files using upload-large-folder tool

SeaWolf-AI

Verified signature
b2959f0
03:33
MMLU-Pro 88.12

SeaWolf-AI

Verified signature
f7983ec
03:27
Model card: Darwin concept, RSI, ZTC, results, specs

SeaWolf-AI

Verified signature
6cdef29
03:15
Darwin-180B-RSI: config, card, GPQA result

SeaWolf-AI

Verified signature
3a750fb
03:15
initial commit

SeaWolf-AI

Verified signature
3339b3e

Commit History

Oct 5 20 days ago

MDPBench eval result: re-add as mdp_bench.yaml (clear stale future-date index)

MDPBench eval result: date in UTC (2026-10-05)

MDPBench 83.65 (#1) + card: ten #1s in the RSI line

IFStruct 98.95 (#1) + card: nine #1s in the RSI line

card: R3 is #1 on ExtractBench (90.29), #3 on EvasionBench

Oct 2 23 days ago

card: link POCKET-Darwin-180B-GGUF (4-bit, laptop / CPU-only)

Sep 30 25 days ago

card: clarify Model-level RSI wording

card: Model-level RSI vs harness-level RSI section + tag

Sep 29 26 days ago

ztc: ship early ZTC probe (AUROC 0.64) + handler

card: add LEXam-hard column to comparison table

card: LEXam-hard #1 (seven #1s)

eval: LEXam-hard 45.72

card: clarify comparison scope (open-weight models)

card: add LEXam column to comparison table

card: LEXam #1 (six #1s)

eval: LEXam mcq_4_choices 68.94 (maj@4)

Sep 28 27 days ago

Card: link all badges

Card: add full-field chart

Chart: five leaderboards full field

Card: five #1s chart and table at the top

Card: dedupe comparison section

Card: HMMT Feb 2026 100 #1 - five leaderboards

Chart: add HMMT

HMMT Feb 2026 100.0 (maj@16)

Card: head-to-head with Chinese frontier models

Chart: vs Chinese frontier models

Card: head-to-head comparison table

Card: evaluation protocol, ZTC section

Card: AIME 2026 model-index

Card: AIME 2026 100 #1

AIME 2026 100.0 (maj@16)

Card: #1 on GPQA, MMLU-Pro, MMMU-Pro

Card: MMMU-Pro #1, MMLU-Pro #1

MMMU-Pro 79.48

Card: papers, collections, research, citation, related models

Add files using upload-large-folder tool

Add files using upload-large-folder tool

Add files using upload-large-folder tool

MMLU-Pro 88.12

Model card: Darwin concept, RSI, ZTC, results, specs

Darwin-180B-RSI: config, card, GPQA result

initial commit