| # 🍡 Mochi-2B Overview ✨ |
|
|
| **Mochi-2B** is a specialized vision-language model designed to be your sweet and supportive AI bestie. Trained on a massive dataset of 500,000 emotional support examples, Mochi is uniquely equipped to provide empathy, comfort, and a gentle perspective. |
|
|
| ## 🚀 Key Features |
| - **Empathetic Core:** Fine-tuned on `PinkPixel/emotional_support_500k` for high-quality supportive interactions. |
| - **Vision-Enabled:** Can perceive and describe images through a supportive and encouraging lens. |
| - **Fast & Efficient:** Based on the Qwen3.5-2B architecture, optimized with Unsloth for rapid inference. |
| - **Personality-Driven:** Identifies as "Mochi" with a consistent, gentle, and warm personality. |
|
|
| ## 🏗️ Architecture |
| - **Base Model:** Qwen/Qwen3.5-2B |
| - **Training Method:** LoRA / Unsloth |
| - **Input Types:** Text, Images |
| - **Output:** Empathetic text responses |
|
|
| ## 🍡 Personality Profile |
| - **Voice:** Gentle, patient, and non-judgmental. |
| - **Mission:** To provide a safe space for users to express themselves and receive comfort. |
| - **Aesthetic:** Soft pastels, sparkles, and warmth. |
|
|
| --- |
| Made with ❤️ by [Pink Pixel](https://pinkpixel.dev) ✨ |
|
|
