Skip to content
View evertonhsg's full-sized avatar

Block or report evertonhsg

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse

Popular repositories Loading

  1. everton_MIT everton_MIT Public archive

    Digital Transformation Repository

    HTML

  2. llm-reasoning-grpo-finetuning llm-reasoning-grpo-finetuning Public

    Fine-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

  3. Last-Mile-Delivery-RAG-Assistant Last-Mile-Delivery-RAG-Assistant Public

    Retrieval-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

  4. llm-multimodal-ai-project llm-multimodal-ai-project Public

    Multi-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

  5. AI-Travel-Assistant AI-Travel-Assistant Public

    LLM-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