Revert "update readme"

This reverts commit 3e01b8a807b8d82ccecf09907ea2b547e7847c97.

README.md

@@ -7,21 +7,13 @@ sdk: streamlit
 app_file: app.py
 pinned: false
 license: mit
-short\_description: Real‑time webcam captioning with SmolVLM2 on CPU
-sdk\_version: 1.45.1
---------------------
-
-# SmolVLM2 Real‑Time Captioning Demo
-
-This Hugging Face Spaces app uses **Streamlit** + **WebRTC** to capture your webcam feed every *N* milliseconds and run it through the SmolVLM2 model on your CPU, displaying live captions below the video.
+short_description: SmolVLM2 on llama.cpp
+sdk_version: 1.45.1
+---
 
-## Features
+# SmolVLM2 Live Inference Demo
 
-* **CPU‑only inference** via `llama-cpp-python` wrapping `llama.cpp`.
-* **WebRTC camera input** for low‑latency, browser‑native video streaming.
-* **Adjustable interval slider** (100 ms to 10 s) for capture frequency.
-* **Automatic GGUF model download** from Hugging Face Hub when missing.
-* **Debug logging** in the terminal for tracing inference steps.
+This HuggingFace Spaces demo runs SmolVLM2 2.2B, 500M, or 256M Instruct GGUF models on CPU using `llama-cpp-python` (v0.3.9) which builds `llama.cpp` under the hood, and Gradio v5.33.2 for the UI. It captures frames from your webcam every N milliseconds and performs live inference, displaying the model's response in real time.
 
 ## Setup
 
@@ -38,38 +30,28 @@ This Hugging Face Spaces app uses **Streamlit** + **WebRTC** to capture your web
    pip install -r requirements.txt
    ```
 
-3. **(Optional) Pre‑download model files**
-   The app automatically downloads these files if they are not present:
-
-   * `SmolVLM2-500M-Video-Instruct.Q4_K_M.gguf`
-   * `mmproj-SmolVLM2-500M-Video-Instruct-Q8_0.gguf`
-
-   To skip download, manually place them in the repo root.
-
-## Usage
+3. **Add your GGUF models**
 
-1. **Launch the app**:
+   Create a `models/` directory in the root of the repo and upload your `.gguf` files:
 
    ```bash
-   streamlit run app.py
+   mkdir models
+   # then upload:
+   # - smolvlm2-2.2B-instruct.gguf
+   # - smolvlm2-500M-instruct.gguf
+   # - smolvlm2-256M-instruct.gguf
    ```
 
-2. **Open your browser** at the URL shown (e.g. `http://localhost:8501`).
-
-3. **Allow webcam access** when prompted by the browser.
-
-4. **Adjust the capture interval** using the slider.
-
-5. **Click **Start** to begin streaming and captioning.**
-
-6. **View live captions** in the panel below the video.
-
-## File Structure
+## Usage
 
-* `app.py` — Main Streamlit + WebRTC application.
-* `requirements.txt` — Python dependencies.
-* `.gguf` model files (auto‑downloaded or user‑provided).
+- **Select Model**: Choose one of the `.gguf` files you uploaded.
+- **System Prompt**: Customize the system-level instructions for the model.
+- **User Prompt**: Provide the user query or instruction.
+- **Interval (ms)**: Set how often (in milliseconds) to capture a frame and run inference.
+- **Live Camera Feed**: The demo will start your webcam and capture frames at the specified interval.
+- **Model Output**: See the model’s response below the camera feed.
 
-## License
+## Notes
 
-Licensed under the MIT License.
+- This demo runs entirely on CPU. Inference speed depends on the model size and your machine's CPU performance.
+- Make sure your browser has permission to access your webcam.