Update README.md

README.md

@@ -1,19 +1,28 @@
----
-title: Text Summarizer
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
----
+# 📝 BitNet Text Summarizer (Streamlit)
 
-# Welcome to Streamlit!
+An open‑source text summarizer running on **microsoft/bitnet-b1.58-2B-4T** with a map‑reduce strategy for long inputs. Deployed on **Hugging Face Spaces** using **Streamlit**.
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+## Features
+- **BitNet (local)** inference inside the Space (GPU recommended)
+- **HF Inference API fallback** (optional) if you provide `HF_TOKEN`
+- **Map‑Reduce** summarization for long documents
+- Adjustable generation parameters (temperature, top_p, token budgets)
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## How it works
+For long text, we:
+1. **Chunk** the text by tokens with overlap to preserve context.
+2. **Summarize** each chunk with BitNet.
+3. **Reduce** (merge) partial summaries into a final cohesive summary.
+
+## Quickstart (Spaces)
+1. Click **Duplicate Space** (top‑right) or create a new Space with SDK: *Streamlit*.
+2. Add these files: `app.py`, `utils.py`, `requirements.txt`, `README.md`.
+3. In **Settings → Hardware**, select a **GPU** for faster cold‑start (T4 or better). CPU works but is slower.
+4. (Optional) Set a repository secret `HF_TOKEN` if you want to enable the Inference API fallback.
+5. Open the app, paste text, and click **Summarize**.
+
+## Local Dev (optional)
+```bash
+python -m venv .venv && source .venv/bin/activate  # Windows: .venv\\Scripts\\activate
+pip install -r requirements.txt
+streamlit run app.py