Fix README short_description

README.md

@@ -1,17 +1,35 @@
 ---
 title: Zeeb
-emoji: 👁
+emoji: 🎬
 colorFrom: purple
 colorTo: pink
 sdk: gradio
-sdk_version: 6.14.0
-python_version: '3.13'
+sdk_version: 5.0.0
+python_version: '3.10'
 app_file: app.py
 pinned: false
-short_description: Image generation model powered stable diffusion 3.5
-hf_oauth: true
-hf_oauth_scopes:
-- inference-api
+short_description: LoRA fine-tune OLMo 2 1B for video token generation
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Zeeb — Video-LLM Trainer
+
+Fine-tune **OLMo 2 1B Instruct** with **LoRA (r=4)** to generate video tokens using visual tokenization.
+
+## Pipeline
+```
+Text Prompt → LLM (OLMo 2 1B + LoRA) → Visual Tokens → VQ-VAE Decoder → Video
+```
+
+## How It Works
+1. Click **"Start Training"** to begin
+2. The model downloads OLMo 2 1B Instruct from HuggingFace
+3. Expands vocabulary with 1,024 visual tokens
+4. Applies LoRA (r=4) for memory-efficient fine-tuning
+5. Trains for 3 epochs on tokenized video data
+6. Merges LoRA weights and pushes to [EeshaAI/zeeb](https://huggingface.co/EeshaAI/zeeb)
+
+## Files
+- `app.py` — Gradio training interface
+- `train_on_hf_spaces.py` — Training logic (OLMo 2 1B + LoRA)
+- `tokenized_dataset.json` — Tokenized video-text training data
+- `requirements.txt` — Python dependencies