Update README.md

README.md

@@ -7,9 +7,10 @@ tags:
 - transformers
 ---
 
-# Model Card for Model ID
+# MedGemma Temporal Change Detection (LoRA Adapter)
 
-<!-- Provide a quick summary of what the model is/does. -->
+This repository provides **LoRA adapters** fine-tuned on top of **google/medgemma-1.5-4b-it** for exploring **temporal change detection in dermatoscopic image pairs**.
+The project investigates whether lightweight parameter-efficient fine-tuning can adapt a multimodal medical foundation model to a **novel temporal reasoning task**.
 
 
 
@@ -17,57 +18,48 @@ tags:
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+This repository contains LoRA adapters only, not a full model checkpoint.
 
+- **Developed and shared by:** Dung Claire Tran ([@dunktra](https://huggingface.co/dunktra))
+- **Base Model:** [google/medgemma-1.5-4b-it](https://huggingface.co/google/medgemma-1.5-4b-it)
+- **Fine-Tuning Method:** LoRA (Low-Rank Adaptation, PEFT)
+- **Model type:** Vision–Language Model (VLM) adapter
+- **Task:** Binary classification of temporal change in skin lesion image pairs
+- **Dataset:** dunktra/dermacheck-temporal-pairs (synthetic temporal pairs)
+- **Language(s) (NLP):** English
+- **License:** Inherits license from google/medgemma-1.5-4b-it 
 
+### Model Sources
 
-- **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]
+- **Repository:** [Kaggle notebook (training & evaluation)](https://www.kaggle.com/code/dungclairetran/dermacheck-medgemma-lora-fine-tuning)
 
-### 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]
+- Research and experimentation with **temporal reasoning in medical imaging**
+- Evaluation of **LoRA fine-tuning feasibility** on multimodal medical foundation models
+- Educational and benchmarking purposes
 
-<!-- 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
+- Clinical diagnosis or medical decision-making
+- Deployment in real-world healthcare settings without clinical validation
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+This model is **not a medical device**.
 
-[More Information Needed]
+## Limitations
 
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+- Fine-tuning effects may not surface when using **keyword-based label extraction**
+- Binary classification may mask improvements in:
+  - reasoning structure
+  - explanatory language
+  - uncertainty expression
+- Synthetic temporal data limits real-world generalization
+- Inherits all limitations of the base MedGemma model
 
 Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 
@@ -75,132 +67,91 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 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]
+```
+from transformers import AutoModelForVision2Seq, AutoProcessor
+from peft import PeftModel
+import torch
 
-### Training Procedure
+base_model = AutoModelForVision2Seq.from_pretrained(
+    "google/medgemma-1.5-4b-it",
+    torch_dtype=torch.bfloat16,
+    device_map="auto"
+)
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+model = PeftModel.from_pretrained(
+    base_model,
+    "dunktra/medgemma-temporal-lora"
+)
 
-#### Preprocessing [optional]
+processor = AutoProcessor.from_pretrained(
+    "dunktra/medgemma-temporal-lora"
+)
+```
 
-[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]
+## Training Details
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+### Training Data
 
-[More Information Needed]
+- **Source:** [dunktra/dermacheck-temporal-pairs](https://huggingface.co/datasets/dunktra/dermacheck-temporal-pairs)
+- **Description:** Synthetic before/after dermatoscopic image pairs labeled for temporal change
+- **Splits:**
+  - **Training:** ~630 pairs
+  - **Validation:** ~135 pairs
+  - **Test:** 135 pairs
+**Note:** *The dataset consists of **synthetic temporal pairs**, not real longitudinal patient data.*
+
+### Training Configuration
+
+- **LoRA Rank (r):** 8
+- **LoRA Alpha:** 16
+- **Target Modules:** q_proj, k_proj, v_proj, o_proj
+- **LoRA Dropout:** 0.05
+- **Epochs:** 3
+- **Effective Batch Size:** 16
+- **Learning Rate:** 2e-4
+- **Precision:** bfloat16
+- **Frameworks:** Transformers + PEFT
 
 ## 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 Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-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).
-
-- **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]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## 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. -->
-
-**BibTeX:**
-
-[More Information Needed]
+- Precision
+- Recall
+- F1 score (binary classification)
 
-**APA:**
+### Results (Test Set: 135 temporal pairs)
 
-[More Information Needed]
+| Metric     | Base MedGemma | Fine-Tuned (LoRA) | Change |
+|------------|---------------|-------------------|--------|
+| F1 Score   | 0.8797        | 0.8797            | +0.00% |
+| Precision  | 0.7852        | 0.7852            | +0.00% |
+| Recall     | 1.0000        | 1.0000            | +0.00% |
 
-## Glossary [optional]
+LoRA fine-tuning **did not** yield measurable improvements under the current evaluation protocol.
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+### Qualitative Analysis
 
-[More Information Needed]
+- No test cases were found where the fine-tuned model corrected errors made by the base model.
+- Fine-tuning did not alter binary decision outcomes given the current response-parsing heuristic.
+  
 
-## More Information [optional]
+## License
 
-[More Information Needed]
+- This adapter inherits the license and usage restrictions of:
+  - **google/medgemma-1.5-4b-it**
+  - Underlying datasets used by the base model
+- Non-commercial research use only.
 
-## Model Card Authors [optional]
+## Acknowledgements
 
-[More Information Needed]
+- Google MedGemma team
+- PEFT / Hugging Face ecosystem
+*Created for the **MedGemma Impact Challenge 2026 – Novel Task Exploration**.*
 
 ## Model Card Contact
 
-[More Information Needed]
+[dunktra](https://huggingface.co/dunktra)
 ### Framework versions
 
 - PEFT 0.18.1