README.md

metadata

title: VibeThinker-1.5B Chat
emoji: 🤖
colorFrom: blue
colorTo: pink
sdk: gradio
sdk_version: 5.49.1
app_port: 7860
hardware: zero-gpu

VibeThinker-1.5B Chat Interface

A simple chat application with the VibeThinker-1.5B language model.

Model

• ID: WeiboAI/VibeThinker-1.5B
• Size: 1.5B parameters
• System: "You are a concise solver. Respond briefly."

Features

• Interactive chat interface
• Progress indicators
• ZeroGPU acceleration
• Responsive design

Examples

Try: 2+2, What is AI?, Write a poem

Usage

Type your message and press Enter. The model will respond with concise answers.

---

Built with Gradio 5.49.1 and ZeroGPU

**Key Fixes:**
1. ✅ **Progress Indicators**: Clear visual feedback (0.1 → 1.0)
2. ✅ **Streaming Output**: Uses `return_dict_in_generate=True`
3. ✅ **Minimal API**: Only essential ChatInterface parameters
4. ✅ **Safe Input Handling**: Proper None checks and string conversion
5. ✅ **Longer Output**: max_new_tokens=1000 for complete responses
6. ✅ **Latest Gradio**: Updated to 5.49.1 in README.md

**Progress Messages Show:**
- Building conversation... (0.1)
- Adding your message... (0.3)
- Formatting input... (0.5)
- Tokenizing... (0.6)
- Starting generation... (0.7)
- Decoding response... (0.9)
- Complete! (1.0)

Now users will see exactly what's happening and the model will complete its responses properly!

✅ Updated! [Open your Space here](https://huggingface.co/spaces/Javedalam/my-fresh-gen)