Skip to content
View hari-huynh's full-sized avatar
πŸ€—
πŸ€—

Highlights

  • Pro

Block or report hari-huynh

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
hari-huynh/README.md

πŸ‘‹ Hello, AI World!

Profile views

πŸ€– About Me

AI Engineer passionate about pushing the boundaries of what's possible with Generative AI and Natural Language Processing. My work focuses on developing innovative solutions that leverage the latest advancements in transformer architectures, large language models, and multimodal systems.

  • 🌱 I’m currently learning Web Scraping, GenAI, LLMs, Agentics AI & Graphs
def introduce_myself():
    me = {
        "name": "Your Name",
        "role": "AI Engineer",
        "specialties": ["Generative AI", "NLP", "LLMs", "MLOps"],
        "languages": ["Python", "PyTorch", "TensorFlow", "JAX"],
        "current_research": "Efficient fine-tuning techniques for domain-specific LLMs"
    }
    return me

πŸ’» Tech Stack

Languages

πŸ“ˆ My GitHub Stats

GitHub Stats Top Languages

πŸ” Featured Projects

πŸ€— LLM-RAG Pipeline

GitHub Repo

A production-ready Retrieval-Augmented Generation system using vector databases and LLMs to provide accurate, context-aware responses.

graph LR
    A[Document Corpus] --> B[Chunking]
    B --> C[Embedding Generation]
    C --> D[Vector Database]
    E[User Query] --> F[Query Embedding]
    F --> G[Vector Search]
    D --> G
    G --> H[Context Assembly]
    H --> I[LLM Prompt]
    I --> J[Response Generation]
Loading

πŸ”„ Fine-tuning Framework

GitHub Repo

A framework for efficient fine-tuning of LLMs using techniques like LoRA, QLoRA, and parameter-efficient training methods.

πŸ§ͺ LLM Evaluation Suite

GitHub Repo

Comprehensive evaluation suite for benchmarking LLMs across various dimensions including factuality, harmlessness, helpfulness, and domain-specific capabilities.

🌟 Interactive AI Demo

Try my latest AI demo!

πŸ“« How to Reach Me

Pinned Loading

  1. viVQA-voice-assistant viVQA-voice-assistant Public

    Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper

    Python 4 4

  2. Face-Image-Retrieval Face-Image-Retrieval Public

    Forked from TaiQuach123/Face-Image-Retrieval

    Face Image Retrieval with CelebA dataset

    Jupyter Notebook

  3. mlops-zoomcamp mlops-zoomcamp Public

    Forked from DataTalksClub/mlops-zoomcamp

    Free MLOps course from DataTalks.Club

    Jupyter Notebook

  4. JobQA-KnowledgeGraph JobQA-KnowledgeGraph Public

    Python 3

  5. vietnam-speech-diarization vietnam-speech-diarization Public

    Python

  6. ViSEDia ViSEDia Public

    Vietnamese Speech Emotion Diarization

    Python