Pinned Loading

1. LLM-finetuning-on-kubernetes LLM-finetuning-on-kubernetes Public

   End-to-end LLM fine-tuning pipeline using Kubernetes, QLoRA, and GPU orchestration. Fine-tune TinyLlama on Alpaca dataset and deploy as a production-ready chat API.

   Jupyter Notebook

2. RAG-Enhanced-Multi-Agent-Code-Generation-System-Using-RL RAG-Enhanced-Multi-Agent-Code-Generation-System-Using-RL Public

   An RL-orchestrated multi-agent system with RAG for intelligent code generation. Uses Q-Learning + Thompson Sampling to coordinate Planner, Coder, Tester, and Debugger agents.

   Python

3. BESS-Coding-Agent BESS-Coding-Agent Public

   This project aims to build a Coding Agent for the energy market. Based on the user’s goals and the tools provided, the coding agent intelligently selects and executes the appropriate actions to com…

   Python

4. Scaling-with-Kubernetes Scaling-with-Kubernetes Public

   Production-ready Kubernetes cluster with GPU support for deploying scalable LLM inference APIs on AWS. Automated setup with Kubespray, NVIDIA device plugin, and FastAPI-powered language model serving.

   Shell

5. Deep-Q-Learning-Galaxian Deep-Q-Learning-Galaxian Public

   Deep Q-Learning agent trained on Atari Seaquest with systematic hyperparameter experiments and comprehensive RL analysis

   Python

6. n8n-Agentic-AI-Customer-Support-Orchestrator n8n-Agentic-AI-Customer-Support-Orchestrator Public

   A "Hub-and-Spoke" agentic AI system implementation using n8n. It simulates a technical support team with a central Controller Agent routing issues to specialized experts (Python Backend vs. General…