👋 Hi there! I'm passionate about exploring the intersections of technology, artificial intelligence, and creativity.
🔭 Currently working on: Advanced AI pipelines and generative models for real-world applications.
💡 Areas of expertise:
- Large Language Models (LLMs)
- Generative AI (Text-to-Image, Video, Code Generation)
- Object Tracking Pipelines
- Multi-modal AI Systems
🌱 Learning: Constantly diving deeper into the world of foundation models like GPT, SAM, and the latest advancements in neural architectures.
🌟 Open to: Collaborations on innovative AI solutions, research projects, and creating impactful AI tools.
| Technology | Expertise Level | Description |
|---|---|---|
| 🧠 LLMs | 🔥 Experienced | Building applications powered by models like GPT and Groq. |
| 🖼️ Generative AI | ⭐ Advanced | Text-to-image/video pipelines with diffusion models. |
| 📊 Data Science | 🚀 Skilled | Advanced analytics, object tracking, and model optimization. |
| 🌐 Open-Source AI | 🌟 Advocate | Utilizing models like LLaMA, Stable Diffusion, and Whisper. |
As a strong advocate for open-source AI, I frequently explore and implement models that democratize access to cutting-edge technology:
- LLaMA (Large Language Model Meta AI): Powerful language models for NLP tasks.
- Stable Diffusion: Revolutionizing generative art and image synthesis.
- Whisper: Robust speech recognition and translation.
- SAM (Segment Anything Model): Versatile object segmentation for diverse applications.
Here are some cool projects I've been working on:
- 🎯 Creating facial expressions in images
- 🖼️ Making choppy videos smooth by interpolating between frames using AI
💬 Reach out to me for collaborations or just to talk AI!
📫 Email: [email protected]
🌐 Website: Personal Project Site
⚡ Fun fact: Open-source AI is shaping the future—empowering developers worldwide to innovate freely! 🚀