Instructions to use Intelligent-Internet/II-Medical-8B-1706 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intelligent-Internet/II-Medical-8B-1706 with Transformers:

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

pipe = pipeline("text-generation", model="Intelligent-Internet/II-Medical-8B-1706")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Intelligent-Internet/II-Medical-8B-1706")
model = AutoModelForCausalLM.from_pretrained("Intelligent-Internet/II-Medical-8B-1706")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Intelligent-Internet/II-Medical-8B-1706 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intelligent-Internet/II-Medical-8B-1706"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intelligent-Internet/II-Medical-8B-1706",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Intelligent-Internet/II-Medical-8B-1706

SGLang

How to use Intelligent-Internet/II-Medical-8B-1706 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 "Intelligent-Internet/II-Medical-8B-1706" \
    --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": "Intelligent-Internet/II-Medical-8B-1706",
		"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 "Intelligent-Internet/II-Medical-8B-1706" \
        --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": "Intelligent-Internet/II-Medical-8B-1706",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Intelligent-Internet/II-Medical-8B-1706 with Docker Model Runner:
```
docker model run hf.co/Intelligent-Internet/II-Medical-8B-1706
```

License?

by CyborgPaloma - opened Jun 24, 2025

Discussion

CyborgPaloma

Jun 24, 2025

Hi, I'm not seeing anywhere what license these model weights are released under?

Good work folks. If this doesn't immediately save lives it will pave the way for what does. IMO it's pretty critical these sorts of models are accessible and Qwen3 is permissive.

Emadhf

Intelligent Internet org Jun 24, 2025

This is released under an MIT license, should add to the HF

CyborgPaloma

Jun 24, 2025

WAY TO GO!!!! Love it. Thanks so much for releasing this ethically, this effort rules.

CyborgPaloma changed discussion title from Liscense? to License? Sep 9, 2025

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