Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View Tekraj15's full-sized avatar
87 followers · 51 following
  • Ex- Incedo Inc. | Ex- Ascendion | Bungee Tech
  • Munich, Germany
  • 09:22 (UTC +01:00)
  • Codestin Search App @trawasthi_ai
  • Codestin Search App in/tekraj15

Achievements

Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLOAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull Sharkx3Achievement: QuickdrawAchievement: YOLOAchievement: StarstruckAchievement: Arctic Code Vault Contributor

Block or report Tekraj15

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Tekraj15/README.md

Hi 👋, I'm Tek Raj Awasthi

An AI & Machine Learning Engineer from the land of Majestic Mountains who loves to find the Altitude of data and leverage its full potential by adopting the innovative AI & Machine Learning techniques.

tekraj15

  • 🎓 Pursuing MS Data Science with a major in AI & ML at Friedrich-Alexander University, Erlangen, Germany
  • 🧑‍💻 🚀 Technical Skills: Python, AWS, SQL, PostgreSQL, Pinecone VectorDB, Machine Learning, Deep Learning, MLOps, ETL, Data Pipeline development, Chatbot Development, Generative AI, RAG, LLM
  • 💻 🛠️ Framework/tools: PySpark, Numpy, Pandas, Scikit-learn, TensorFlow, PyTorch, RASA, Flask, Apache Spark, Apace Airflow, MlFlow, DagsHub, DVC, LangChain

🚀 Currently building around LLM, VLM, RAG, Agentic AI, Stable Diffusion, etc. Find my live projects in Hugging Face Space

🌊 Diving into the depths of Fine-Tuning, Post-training, and Compression of LLM and Multimodal AIs(VLM, Vision RAG), and Reinforcement Learning, etc.

dotpyarmy tekrajawasthi15 @tekrajawasthi15

Pinned Loading

  1. QLoRA-MiniSAM QLoRA-MiniSAM Public

    A lightweight, 4-bit quantized, and LoRA-adapted version of the Segment Anything Model (SAM) tailored for medical image segmentation (MIS)

    Python 1

  2. Sketch-to-Render Sketch-to-Render Public

    Real-Time Design Studio - A generative AI designed to transform rough sketches into high-fidelity, photorealistic 3D images/renders in real-time, powered by Stable Diffusion.

    Python

  3. VisWanda-Eco-VLM VisWanda-Eco-VLM Public

    Smashing" VLM for the Edge: Hardware aware Hybrid Wanda Pruning(2:4 Structured Sparsity) of Vision Transformer for image Classification with zero Post-Training

    Python

  4. Ecommerce-Support-Agentic-RAG Ecommerce-Support-Agentic-RAG Public

    Hybrid LLM and Agentic RAG Powered E-commerce Customer Support Chatbot built with Langchain, Pinecone Vector DB, Rasa chatbot framework and, integrated with DeepSeek-r1

    Python 2 1

  5. LLM-and-RAG-Powered-MedBot LLM-and-RAG-Powered-MedBot Public

    LLM and RAG suported Medical ChatBot based RASA Dialogue management and Medical Knowledge Base, equipped with Intelligent Query Routing, Sefety Validation, and Self-correction.

    Python 4

  6. Bonsai-LLaVA Bonsai-LLaVA Public

    The art of miniaturization without losing the essence. Distilling the visual reasoning capabilities of LLaVA-v1.5-7B into a compact 490M param student model, optimized for consumer hardware and edg…

    Python