Image-Text-to-Text
Transformers
Safetensors
English
medical
pathology
vision-language
reasoning
multimodal
vlm
Instructions to use jshhhh/PathReasoner-R1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jshhhh/PathReasoner-R1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="jshhhh/PathReasoner-R1")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jshhhh/PathReasoner-R1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jshhhh/PathReasoner-R1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jshhhh/PathReasoner-R1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/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
docker model run hf.co/jshhhh/PathReasoner-R1
- SGLang
How to use jshhhh/PathReasoner-R1 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 "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 }' - Docker Model Runner
How to use jshhhh/PathReasoner-R1 with Docker Model Runner:
docker model run hf.co/jshhhh/PathReasoner-R1
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
tags:
|
| 7 |
+
- medical
|
| 8 |
+
- pathology
|
| 9 |
+
- vision-language
|
| 10 |
+
- reasoning
|
| 11 |
+
- multimodal
|
| 12 |
+
- vlm
|
| 13 |
+
library_name: transformers
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
# PathReasoner-R1
|
| 17 |
+
|
| 18 |
+
Model weights for the paper *PathReasoner-R1: Empowering Pathology Vision Language Models with Structured Diagnostic Reasoning*.
|
| 19 |
+
|
| 20 |
+
## Overview
|
| 21 |
+
|
| 22 |
+
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.
|
| 23 |
+
|
| 24 |
+
## Model Details
|
| 25 |
+
|
| 26 |
+
- **Base model**: *Qwen2.5-VL-7B*
|
| 27 |
+
- **Training data**: [PathReasoner Dataset](https://huggingface.co/datasets/jshhhh/PathReasoner)
|
| 28 |
+
- **Task**: Pathology image understanding with structured reasoning
|
| 29 |
+
- **Languages**: English
|
| 30 |
+
|
| 31 |
+
## License
|
| 32 |
+
|
| 33 |
+
This model is released under CC BY-NC 4.0 — free for academic and research use, **not for commercial use or clinical deployment**.
|