Instructions to use AQ-MedAI/MedResearcher-R1-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AQ-MedAI/MedResearcher-R1-32B with Transformers:

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

pipe = pipeline("text-generation", model="AQ-MedAI/MedResearcher-R1-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AQ-MedAI/MedResearcher-R1-32B")
model = AutoModelForCausalLM.from_pretrained("AQ-MedAI/MedResearcher-R1-32B")
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

vLLM

How to use AQ-MedAI/MedResearcher-R1-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AQ-MedAI/MedResearcher-R1-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AQ-MedAI/MedResearcher-R1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AQ-MedAI/MedResearcher-R1-32B

SGLang

How to use AQ-MedAI/MedResearcher-R1-32B 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 "AQ-MedAI/MedResearcher-R1-32B" \
    --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": "AQ-MedAI/MedResearcher-R1-32B",
		"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 "AQ-MedAI/MedResearcher-R1-32B" \
        --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": "AQ-MedAI/MedResearcher-R1-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AQ-MedAI/MedResearcher-R1-32B with Docker Model Runner:
```
docker model run hf.co/AQ-MedAI/MedResearcher-R1-32B
```

Improve model card: Add `transformers` compatibility, `text-generation` pipeline tag, and comprehensive details

by nielsr HF Staff - opened Sep 19, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+85

-12

nielsr

Sep 19, 2025

This PR significantly enhances the model card for MedResearcher-R1-32B by:

Adding library_name: transformers to the metadata, enabling the automated code snippet on the Hugging Face Hub, as confirmed by the model's config.json (Qwen2ForCausalLM architecture, transformers_version, and Qwen2Tokenizer class).
Setting pipeline_tag: text-generation to ensure the model is discoverable for relevant tasks at https://huggingface.co/models?pipeline_tag=text-generation, aligning with its role as an LLM-based agent.
Integrating a more comprehensive description of the MedResearcher-R1 framework, including its key features, performance highlights, and open-sourced dataset, directly sourced from the project's GitHub README. This provides a richer context for the model's capabilities.
Adding a "Quick start: Run Model for Evaluation" section with a sglang server setup, directly reflecting usage instructions found in the GitHub repository, to guide users on how to deploy and evaluate the model.
Correcting the BibTeX citation format for better parsing and consistency.
Including the Star History chart from the GitHub README for community engagement.

These changes aim to provide a more informative and user-friendly experience for anyone interacting with the model on the Hub. The existing arXiv paper link and GitHub repository link are maintained.

Improve model card: Add `transformers` compatibility, `text-generation` pipeline tag, and comprehensive detailsd0abc649

m1ngcheng

AQ org Sep 28, 2025

LGTM

m1ngcheng changed pull request status to merged Sep 28, 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