How to use from
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 "jshhhh/PathReasoner-R1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jshhhh/PathReasoner-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
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 "jshhhh/PathReasoner-R1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jshhhh/PathReasoner-R1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'
Quick Links

PathReasoner-R1

Model weights for the paper PathReasoner-R1: Empowering Pathology Vision Language Models with Structured Diagnostic Reasoning.

Overview

PathReasoner-R1 is a pathology vision-language model trained to perform structured diagnostic reasoning over histopathology images. The model produces step-by-step reasoning grounded in a medical knowledge graph enabling clinically valid interpretations.

Model Details

  • Base model: Qwen2.5-VL-7B
  • Training data: PathReasoner Dataset
  • Task: Pathology image understanding with structured reasoning
  • Languages: English

License

This model is released under CC BY-NC 4.0 โ€” free for academic and research use, not for commercial use or clinical deployment.

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
0.2B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support