Update README.md

README.md

@@ -2,201 +2,115 @@
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
 library_name: peft
 ---
+# 🩺 PointDetectCount-Qwen2.5-VL-7B-LoRA
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
-
-
-## Model Details
-
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-
-## How to Get Started with the Model
-
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
+**Model:** `SimulaMet/PointDetectCount-Qwen2.5-VL-7B-LoRA`  
+**Base model:** [`Qwen/Qwen2.5-VL-7B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct)  
+**Library:** `peft` (LoRA)  
+**Paper:** [arXiv:2505.16647](https://doi.org/10.48550/arXiv.2505.16647)  
+**Code:** [GitHub - simula/PointDetectCount](https://github.com/simula/PointDetectCount)  
+**Dataset:** [`SimulaMet/MedMultiPoints`](https://huggingface.co/datasets/SimulaMet/MedMultiPoints)
 
+---
 
+## 📌 Model Summary
 
-## Model Examination [optional]
+`PointDetectCount-Qwen2.5-VL-7B-LoRA` is a **multi-task medical vision-language model** fine-tuned using **LoRA** on top of **Qwen2.5-VL-7B-Instruct**, a vision-language instruction-following model. This model performs **pointing (localization), bounding box detection**, and **object counting** on medical images using natural language prompts and structured JSON outputs.
 
-<!-- Relevant interpretability work for the model goes here -->
+It is trained on the [MedMultiPoints dataset](https://huggingface.co/datasets/SimulaMet/MedMultiPoints), a multimodal collection of endoscopic and microscopic images with clinical annotations.
 
-[More Information Needed]
+---
 
-## Environmental Impact
+## 🧠 Intended Uses
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+- **Medical image localization**: Predict spatial locations (points/bounding boxes) of anatomical/clinical findings.
+- **Object counting**: Accurately estimate number of objects like polyps, clusters, or cells in medical images.
+- **Instruction-tuned VQA**: Accepts natural language queries prompting multimodal image understanding.
 
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+This model is designed for **research purposes**, particularly in **medical vision-language modeling**, and should not be used directly for clinical diagnosis.
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+---
 
-## Technical Specifications [optional]
+## 🚀 How to Use
 
-### Model Architecture and Objective
+```python
+from transformers import AutoProcessor, AutoModelForVision2Seq
+import torch
+from PIL import Image
 
-[More Information Needed]
+model = AutoModelForVision2Seq.from_pretrained("SimulaMet/PointDetectCount-Qwen2.5-VL-7B-LoRA")
+processor = AutoProcessor.from_pretrained("SimulaMet/PointDetectCount-Qwen2.5-VL-7B-LoRA")
 
-### Compute Infrastructure
+image = Image.open("example.jpg").convert("RGB")
+prompt = "Return bounding boxes for each polyp in the image and the total count."
 
-[More Information Needed]
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+with torch.no_grad():
+    outputs = model.generate(**inputs, max_new_tokens=512)
 
-#### Hardware
+print(processor.batch_decode(outputs, skip_special_tokens=True)[0])
+```
 
-[More Information Needed]
+---
 
-#### Software
+## 📊 Training Details
 
-[More Information Needed]
+- **Fine-tuning method:** [LoRA](https://arxiv.org/abs/2106.09685) (`rank=16`)
+- **Frozen components:** Vision encoder (ViT)
+- **Trained components:** LLM layers (excluding final LM head)
+- **Loss function:** Language modeling loss (cross-entropy over tokens)
+- **Format:** Instruction → JSON response (`{"bbox": [...], "count": n, "points": [...]}`)
+- **Hardware:** Single NVIDIA A100 (80GB)
+- **Epochs:** 5  
+- **Batch size:** 4 (gradient accumulation used)  
+- **Learning rate:** 2e-4
 
-## Citation [optional]
+---
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+## 📁 Repository Structure
 
-**BibTeX:**
+- `create_datasetJSON.py`: Converts raw annotations into instruction-response format
+- `evaluate_qwen.py`: Parses and evaluates model outputs vs. ground truth
+- `MedMultiPoints-images/`: Folder containing the training/validation images
 
-[More Information Needed]
+---
 
-**APA:**
+## 🧪 Evaluation
 
-[More Information Needed]
+Each model output is parsed to extract:
+- Bounding box coordinates
+- Point coordinates
+- Object count
 
-## Glossary [optional]
+The parsed outputs are compared against the ground truth for each modality (GI tract, sperm, clusters, etc.). Accuracy is measured through precision/recall on detection, mean absolute error for counting, and proximity scores for pointing.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+---
 
-[More Information Needed]
+## 🛑 Limitations
 
-## More Information [optional]
+- Trained only on limited domains (GI endoscopy, microscopy).
+- Not certified for real-world clinical use.
+- Output format depends on correct JSON generation—parsing may fail with malformed outputs.
 
-[More Information Needed]
+---
 
-## Model Card Authors [optional]
+## 📚 Citation
 
-[More Information Needed]
+```bibtex
+@article{Gautam2025May,
+  author = {Gautam, Sushant and Riegler, Michael A. and Halvorsen, Pål},
+  title = {Point, Detect, Count: Multi-Task Medical Image Understanding with Instruction-Tuned Vision-Language Models},
+  journal = {arXiv},
+  year = {2025},
+  month = {may},
+  eprint = {2505.16647},
+  doi = {10.48550/arXiv.2505.16647}
+}
+```
 
-## Model Card Contact
+---
 
-[More Information Needed]
-### Framework versions
+## 🤝 Acknowledgements
 
-- PEFT 0.14.0
+Developed by researchers at **SimulaMet**, **Simula Research Laboratory**, and **OsloMet**.  
+Part of ongoing efforts to enhance **instruction-tuned medical VLMs** for robust multimodal reasoning.