Instructions to use deca-ai/2-pro-medical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deca-ai/2-pro-medical with Transformers:

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

pipe = pipeline("text-generation", model="deca-ai/2-pro-medical")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deca-ai/2-pro-medical")
model = AutoModelForCausalLM.from_pretrained("deca-ai/2-pro-medical", device_map="auto")
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 Settings

vLLM

How to use deca-ai/2-pro-medical with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deca-ai/2-pro-medical"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deca-ai/2-pro-medical",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deca-ai/2-pro-medical

SGLang

How to use deca-ai/2-pro-medical 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 "deca-ai/2-pro-medical" \
    --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": "deca-ai/2-pro-medical",
		"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 "deca-ai/2-pro-medical" \
        --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": "deca-ai/2-pro-medical",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deca-ai/2-pro-medical with Docker Model Runner:
```
docker model run hf.co/deca-ai/2-pro-medical
```

2-pro-medical

Commit History

Update README.md

cf5d011
verified

system commited on Mar 13, 2025

Create LICENSE.md

c72d8b6
verified

system commited on Mar 11, 2025

Create README.md

c540e0c
verified

system commited on Mar 7, 2025

Delete README.md

501f234
verified

system commited on Mar 7, 2025

Delete mergekit_config.yml

0a7f620
verified

system commited on Mar 7, 2025

Upload folder using huggingface_hub

d4a8537
verified

system commited on Mar 5, 2025

initial commit

aebfbb7
verified

system commited on Mar 5, 2025

Commit History

Update README.md cf5d011 verified

Create LICENSE.md c72d8b6 verified

Create README.md c540e0c verified

Delete README.md 501f234 verified

Delete mergekit_config.yml 0a7f620 verified

Upload folder using huggingface_hub d4a8537 verified

initial commit aebfbb7 verified

Update README.md

cf5d011
verified

Create LICENSE.md

c72d8b6
verified

Create README.md

c540e0c
verified

Delete README.md

501f234
verified

Delete mergekit_config.yml

0a7f620
verified

Upload folder using huggingface_hub

d4a8537
verified

initial commit

aebfbb7
verified