Instructions to use FINAL-Bench/Darwin-218B-Delphi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FINAL-Bench/Darwin-218B-Delphi with Transformers:

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

pipe = pipeline("text-generation", model="FINAL-Bench/Darwin-218B-Delphi")
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-218B-Delphi")
model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/Darwin-218B-Delphi")
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-218B-Delphi with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FINAL-Bench/Darwin-218B-Delphi"
# 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-218B-Delphi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FINAL-Bench/Darwin-218B-Delphi

SGLang

How to use FINAL-Bench/Darwin-218B-Delphi 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-218B-Delphi" \
    --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-218B-Delphi",
		"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-218B-Delphi" \
        --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-218B-Delphi",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FINAL-Bench/Darwin-218B-Delphi with Docker Model Runner:
```
docker model run hf.co/FINAL-Bench/Darwin-218B-Delphi
```

SeaWolf-AI commited on 16 days ago

Commit

b3680b1

verified ·

1 Parent(s): c47eb81

Remove DELPHI cascade internals (trade secret); keep score table + family tree only

Browse files

Files changed (1) hide show

README.md +0 -14

README.md CHANGED Viewed

@@ -129,20 +129,6 @@ DELPHI improvement                           | +4.04pp (+8 questions)
 ---
-## DELPHI 5-Phase Cascade (signature inference mode)
-The VIDRAFT DELPHI cascade routes each question through 5 progressively deeper inference stages:
-1. **P1** — greedy single-shot (temperature 0)
-2. **P2** — MAJ@8 majority vote (temperature 0.7)
-3. **P3** — 16-vote tiebreak for close calls
-4. **P4** — Multi-Turn Inference (MTI): 3-turn self-critique × 8 chains
-5. **P5** — weighted global tiebreak across all phases
-Compute-optimal: most questions resolve at P1/P2; only ambiguous ones escalate.
----
 ## Usage
 ### vLLM (recommended)

 ---
 ## Usage
 ### vLLM (recommended)