Upload README.md with huggingface_hub

README.md

@@ -34,17 +34,17 @@ model-index:
       config: mixed-domains
       split: test
     metrics:
-    - type: completeness-score
-      value: 0.640
-      name: Overall Completeness
     - type: pii-detection-rate
-      value: 0.203
+      value: 1.000
       name: PII Detection Rate
+    - type: completeness-score
+      value: 0.650
+      name: Completeness Score
     - type: semantic-preservation
-      value: 0.109
+      value: 0.811
       name: Semantic Preservation
     - type: latency
-      value: 492.4
+      value: 477.0
       name: Average Latency (ms)
 ---
 
@@ -83,26 +83,42 @@ model-index:
 
 1. **Install llama.cpp** (if not already installed):
    ```bash
+   # Clone and build llama.cpp
    git clone https://github.com/ggerganov/llama.cpp
-   cd llama.cpp && make
+   cd llama.cpp
+   make
+
+   # Return to project directory
+   cd ../de-id-small
    ```
 
-2. **Download and run the model**:
+2. **Download the GGUF model**:
    ```bash
-   # Download model files
+   # Download model files from HuggingFace
    wget https://huggingface.co/Minibase/DeId-Small/resolve/main/model.gguf
    wget https://huggingface.co/Minibase/DeId-Small/resolve/main/deid_inference.py
+   wget https://huggingface.co/Minibase/DeId-Small/resolve/main/config.json
+   wget https://huggingface.co/Minibase/DeId-Small/resolve/main/tokenizer_config.json
+   wget https://huggingface.co/Minibase/DeId-Small/resolve/main/generation_config.json
+   ```
 
-   # Make executable and run
-   chmod +x run_server.sh
-   ./run_server.sh
+3. **Start the model server**:
+   ```bash
+   # Start llama.cpp server with the GGUF model
+   ../llama.cpp/llama-server \
+     -m model.gguf \
+     --host 127.0.0.1 \
+     --port 8000 \
+     --ctx-size 2048 \
+     --n-gpu-layers 0 \
+     --chat-template
    ```
 
-3. **Make API calls**:
+4. **Make API calls**:
    ```python
    import requests
 
-   # De-identify text
+   # De-identify text via REST API
    response = requests.post("http://127.0.0.1:8000/completion", json={
        "prompt": "Instruction: De-identify this text by replacing all personal information with placeholders.\n\nInput: Patient John Smith, born 1985-03-15, lives at 123 Main St.\n\nResponse: ",
        "max_tokens": 256,
@@ -110,22 +126,63 @@ model-index:
    })
 
    result = response.json()
-   print(result["content"])  # "Patient [FIRSTNAME_1] [LASTNAME_1], born [DOB_1], lives at [BUILDINGNUMBER_1] [STREET_1]."
+   print(result["content"])
+   # Output: "Patient [FIRSTNAME_1] [LASTNAME_1], born [DOB_1], lives at [BUILDINGNUMBER_1] [STREET_1]."
    ```
 
-### Python Client
+### Python Client (Recommended)
 
 ```python
+# Download and use the provided Python client
 from deid_inference import DeIdClient
 
-# Initialize client
+# Initialize client (connects to local server)
 client = DeIdClient()
 
-# De-identify text
+# De-identify sensitive text
 sensitive_text = "Dr. Sarah Johnson called from (555) 123-4567 about patient Michael Brown."
 clean_text = client.deidentify_text(sensitive_text)
 
-print(clean_text)  # "Dr. [FIRSTNAME_1] [LASTNAME_1] called from [PHONE_1] about patient [FIRSTNAME_2] [LASTNAME_2]."
+print(clean_text)
+# Output: "Dr. [FIRSTNAME_1] [LASTNAME_1] called from [PHONE_1] about patient [FIRSTNAME_2] [LASTNAME_2]."
+
+# Batch processing
+texts = [
+    "Employee John Doe earns $85,000 annually.",
+    "Contact jane.smith@company.com for details."
+]
+clean_texts = client.deidentify_batch(texts)
+print(clean_texts)
+# Output: ["Employee [FIRSTNAME_1] Doe earns [CURRENCYSYMBOL_1][AMOUNT_1] annually.", "Contact [EMAIL_1] for details."]
+```
+
+### Direct llama.cpp Usage
+
+```python
+# Alternative: Use llama.cpp directly without server
+import subprocess
+import json
+
+def deidentify_with_llama_cpp(text: str) -> str:
+    prompt = f"Instruction: De-identify this text by replacing all personal information with placeholders.\n\nInput: {text}\n\nResponse: "
+
+    # Run llama.cpp directly
+    cmd = [
+        "../llama.cpp/llama-cli",
+        "-m", "model.gguf",
+        "--prompt", prompt,
+        "--ctx-size", "2048",
+        "--n-predict", "256",
+        "--temp", "0.1",
+        "--log-disable"
+    ]
+
+    result = subprocess.run(cmd, capture_output=True, text=True, cwd=".")
+    return result.stdout.strip()
+
+# Usage
+result = deidentify_with_llama_cpp("Patient Sarah Johnson, DOB 05/12/1980.")
+print(result)
 ```
 
 ## 📊 Benchmarks & Performance
@@ -135,9 +192,9 @@ print(clean_text)  # "Dr. [FIRSTNAME_1] [LASTNAME_1] called from [PHONE_1] about
 | Metric | Score | Description |
 |--------|-------|-------------|
 | **PII Detection Rate** | **100%** | **Perfect detection when PII is present in input** |
-| **Completeness Score** | **67.0%** | **Percentage of texts fully de-identified** |
-| Semantic Preservation | 10.9% | How well original meaning is preserved |
-| **Average Latency** | **484ms** | **Response time performance** |
+| **Completeness Score** | **65.0%** | **Percentage of texts fully de-identified** |
+| **Semantic Preservation** | **81.1%** | **How well original meaning is preserved** |
+| **Average Latency** | **477ms** | **Response time performance** |
 
 ### Performance Insights
 
@@ -370,17 +427,11 @@ If you use DeId-Small in your research, please cite:
 }
 ```
 
-## 📞 Contact & Community
+## 🤝 Community & Support
 
 - **Website**: [minibase.ai](https://minibase.ai)
-- **Discord Community**: [Join our Discord](https://discord.com/invite/BrJn4D2Guh)
-- **GitHub Issues**: [Report bugs or request features](https://github.com/minibase-ai/deid-small/issues)
-- **Email**: hello@minibase.ai
-
-### Support
-- 📖 **Documentation**: [docs.minibase.ai](https://docs.minibase.ai)
-- 💬 **Community Forum**: [forum.minibase.ai](https://forum.minibase.ai)
-- 🐛 **Bug Reports**: [GitHub Issues](https://github.com/minibase-ai/deid-small/issues)
+- **Discord**: [Join our community](https://discord.com/invite/BrJn4D2Guh)
+- **Documentation**: [docs.minibase.ai](https://docs.minibase.ai)
 
 ## 📋 License