Popular repositories Loading
-
-
llm-reasoning-grpo-finetuning
llm-reasoning-grpo-finetuning PublicFine-tuning Qwen 2.5 3B with GRPO (reinforcement learning) to teach step-by-step letter-counting reasoning. Uses Unsloth, LoRA, vLLM, and custom reward functions.
Jupyter Notebook
-
Last-Mile-Delivery-RAG-Assistant
Last-Mile-Delivery-RAG-Assistant PublicRetrieval-Augmented Generation assistant for last-mile delivery ops Q&A. Phase 1 (chunking, embeddings, FAISS) is implemented; full RAG chain, fine-tuning, evaluation, and UI are designed as the ro…
Jupyter Notebook
-
llm-multimodal-ai-project
llm-multimodal-ai-project PublicMulti-agent content moderation system for text, image, video, and audio, built with Google Gemini, Pydantic AI structured outputs, a Gradio chat UI, a FastAPI backend, and Arize Phoenix observability.
Python
-
AI-Travel-Assistant
AI-Travel-Assistant PublicLLM-powered travel-planning agent (AgentsVille Trip Planner) demonstrating agentic AI patterns: structured Pydantic outputs, tool calling, ReAct reasoning loops, and evaluator-optimizer self-correc…
Jupyter Notebook
If the problem persists, check the GitHub status page or contact support.