Update README.md

README.md

@@ -6,202 +6,248 @@ tags:
 - base_model:adapter:Qwen/Qwen2.5-VL-3B-Instruct
 - lora
 - transformers
+- image-to-text
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Qwen2.5-VL-Diagrams2SQL
 
+A fine-tuned **Qwen2.5-VL-3B-Instruct** model specialized for converting database schema diagrams into structured JSON format. This model dramatically improves upon the base model's ability to understand and extract information from ER diagrams, database schemas, and other structured database documentation.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+This model addresses a common pain point in database documentation and migration projects: manually transcribing database schema diagrams is time-consuming and error-prone. While the base Qwen2.5-VL model struggled with structured diagram interpretation (often missing tables, incorrectly identifying relationships, or producing malformed outputs), this fine-tuned version shows significant improvements across all metrics.
 
+The model uses **LoRA (Low-Rank Adaptation)** for parameter-efficient fine-tuning, targeting attention layers for optimal performance while maintaining efficiency.
 
+- **Developed by:** zodiac2525
+- **Model type:** Vision-Language Model (Fine-tuned)
+- **Language(s):** English
+- **License:** Same as base model (Qwen2.5-VL-3B-Instruct)
+- **Finetuned from model:** [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
 
-- **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
 
-### Model Sources [optional]
+- **Repository:** [GitHub Repository](https://github.com/zodiac2525/DB-Diagram-to-JSON-Schema)
+- **Base Model:** [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct)
 
-<!-- Provide the basic links for the model. -->
+## Performance Improvements
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+The fine-tuned model shows significant improvements over the base model:
 
-## Uses
+| Metric | Base Qwen2.5-VL | Fine-tuned Model | Improvement |
+|--------|------------------|------------------|-------------|
+| **Table Detection Accuracy** | 65.2% | 89.7% | **+24.5%** |
+| **Relationship Accuracy** | 58.9% | 84.3% | **+25.4%** |
+| **Overall Schema Score** | 62.1% | 87.0% | **+24.9%** |
+| **JSON Format Compliance** | 78.1% | 96.2% | **+18.1%** |
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+## Uses
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+This model is designed to:
+- Convert database ER diagrams to structured JSON schemas
+- Extract table structures, column definitions, and relationships from visual diagrams
+- Automate database documentation processes
+- Assist in database migration and reverse engineering tasks
 
-[More Information Needed]
+### Supported Diagram Types
 
-### 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]
+The model has been trained on diverse schema types including:
+- **E-commerce**: Products, orders, customers, payments
+- **Healthcare**: Patients, appointments, medical records  
+- **Education**: Students, courses, grades, enrollment
+- **Finance**: Accounts, transactions, investments
+- **IoT/Social Media**: Users, posts, device data
 
 ### 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.
+- Not suitable for non-database diagrams (flowcharts, network diagrams, etc.)
+- Does not generate actual SQL DDL statements (outputs JSON schema only)
+- Not trained for natural language database queries
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+### Installation
+
+```bash
+pip install transformers torch pillow
+```
+
+### Basic Usage
+
+```python
+from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
+from PIL import Image
+import torch
+import json
+
+# Load the fine-tuned model
+model_id = "zodiac2525/Qwen2.5-VL-Diagrams2SQL"
+processor = AutoProcessor.from_pretrained(model_id)
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    model_id, 
+    torch_dtype=torch.bfloat16, 
+    device_map="auto"
+)
+
+# Load your ER diagram
+image = Image.open("path/to/your/diagram.png").convert("RGB")
+
+# Prepare the input
+messages = [
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": image},
+            {"type": "text", "text": "Extract data in JSON format"}
+        ]
+    }
+]
+
+# Process and generate
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=[text], images=[image], return_tensors="pt").to("cuda")
+
+# Generate schema
+with torch.no_grad():
+    generated_ids = model.generate(
+        **inputs,
+        max_new_tokens=1024,
+        do_sample=False,
+        temperature=0.0
+    )
+
+# Extract and parse JSON
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+json_start = generated_text.find('{')
+if json_start != -1:
+    schema_json = json.loads(generated_text[json_start:])
+    print(json.dumps(schema_json, indent=2))
+```
+
+### Expected Output Format
+
+The model outputs JSON schemas in the following structure:
+
+```json
+{
+  "tables": [
+    {
+      "name": "users",
+      "columns": [
+        {
+          "name": "id",
+          "type": "INT",
+          "constraints": ["PRIMARY KEY", "AUTO_INCREMENT"]
+        },
+        {
+          "name": "email",
+          "type": "VARCHAR(255)",
+          "constraints": ["UNIQUE", "NOT NULL"]
+        }
+      ]
+    }
+  ],
+  "relationships": [
+    {
+      "from_table": "orders",
+      "from_column": "user_id",
+      "to_table": "users",
+      "to_column": "id",
+      "relationship_type": "FOREIGN KEY"
+    }
+  ]
+}
+```
 
 ## 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]
+The model was fine-tuned on a custom dataset of 400+ database schema diagrams with corresponding JSON annotations, covering various domains and complexity levels.
 
 ### 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 -->
+**Fine-tuning Method:** LoRA (Low-Rank Adaptation)
+- **LoRA Rank:** 16
+- **LoRA Alpha:** 32
+- **Target Modules:** q_proj, v_proj, k_proj, o_proj (attention layers)
 
-#### Speeds, Sizes, Times [optional]
+**Training Hyperparameters:**
+- **Learning Rate:** 1e-4
+- **Batch Size:** 4
+- **Gradient Accumulation Steps:** 8
+- **Max Epochs:** 8
+- **Optimizer:** AdamW
+- **Weight Decay:** 0.01
+- **LR Scheduler:** Cosine
+- **Mixed Precision:** bf16
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+### Training Infrastructure
 
-[More Information Needed]
+- **Framework:** PyTorch with Transformers
+- **Experiment Tracking:** Comet ML
+- **Hardware:** GPU-optimized training setup
 
 ## 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]
+The model was evaluated on a held-out test set using multiple metrics:
+- **Table Detection Accuracy**: Percentage of correctly identified tables
+- **Relationship Accuracy**: Percentage of correctly identified relationships
+- **JSON Format Compliance**: Percentage of valid JSON outputs
+- **Overall Schema Score**: Composite metric combining all aspects
 
-#### 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:**
+## Bias, Risks, and Limitations
 
-[More Information Needed]
+**Limitations:**
+- Performance may vary with diagram quality, resolution, and formatting
+- Best results achieved with clear, well-structured diagrams
+- May struggle with hand-drawn or heavily stylized diagrams
+- Limited to database schema diagrams (not general-purpose diagram understanding)
 
-**APA:**
+**Recommendations:**
+- Use high-quality, clear diagram images for best results
+- Verify generated schemas for critical applications
+- Consider the model as an assistive tool rather than fully automated solution
 
-[More Information Needed]
+## Technical Specifications
 
-## Glossary [optional]
+### Model Architecture
+- **Base Architecture:** Qwen2.5-VL (Vision-Language Model)
+- **Vision Encoder:** Processes input images to visual tokens
+- **Language Model:** Qwen2.5 transformer backbone
+- **Multi-modal Fusion:** Integrates visual and textual representations
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+### Compute Requirements
+- **Minimum VRAM:** 8GB (for inference)
+- **Recommended:** 16GB+ for optimal performance
+- **CPU Inference:** Supported but slower
 
-[More Information Needed]
+## Framework Versions
 
-## More Information [optional]
+- **PEFT:** 0.16.0
+- **Transformers:** 4.49.0+
+- **PyTorch:** 2.0+
+- **Python:** 3.8+
 
-[More Information Needed]
+## Citation
 
-## Model Card Authors [optional]
+If you use this model in your research or applications, please cite:
 
-[More Information Needed]
+```bibtex
+@misc{qwen25vl-diagrams2sql,
+  title={Qwen2.5-VL-Diagrams2SQL: Fine-tuned Vision-Language Model for Database Schema Extraction},
+  author={zodiac2525},
+  year={2024},
+  howpublished={\url{https://huggingface.co/zodiac2525/Qwen2.5-VL-Diagrams2SQL}}
+}
+```
 
 ## Model Card Contact
 
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.16.0
+For questions, issues, or collaboration opportunities, please:
+- Open an issue on the GitHub repository
+- Contact via Hugging Face model discussions