Skip to content
View xinli95's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Seattle
  • 03:10 (UTC -08:00)

Block or report xinli95

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
xinli95/README.md

Hi there, I'm Xin! 👋

I am an Applied Scientist focused on the intersection of Large Language Models (LLMs) and Reinforcement Learning (RL). I'm passionate about making complex AI concepts accessible and turning AI learning into a fun experience.

📖 My Book: AI-101

I am currently writing AI-101, an open-resource book born from my personal learning notes. It is designed to be an accessible guide for anyone—from curious beginners to fellow practitioners—looking to demystify the mechanics of modern AI.

Latest Updates:

  • Transformers: Deep dive into architectures.
  • RLHF: Explaining theory behind PPO.
  • RLVR: Understanding Reinforcement Learning from Verifiable Rewards.
  • 🚧 Evaluation (WIP): Benchmarks, metrics, and frameworks for LLMs and Agent systems.
  • 🚧 Responsible AI (WIP): Model safety eval, Moderation, Safeguard LLM.
  • 🚧 More chapters in progress—stay tuned!

🛠 Tech Stack & Interests

  • Research interests: LLM, Fine-tuning (SFT/RLHF/RLVR), Topic modeling, Evaluation, Inference optimization.
  • Tools: PyTorch, Transformers, Unsloth, Smolagents, OpenJudge.

🤝 Connect with me

Pinned Loading

  1. AI-101 AI-101 Public

    Deep dive into AI

    TeX

  2. nanoVLM nanoVLM Public

    Forked from huggingface/nanoVLM

    The simplest, fastest repository for training/finetuning small-sized VLMs.

    Python

  3. open-r1 open-r1 Public

    Forked from huggingface/open-r1

    Fully open reproduction of DeepSeek-R1

    Python

  4. smolagents smolagents Public

    Forked from huggingface/smolagents

    🤗 smolagents: a barebones library for agents that think in code.

    Python

  5. nanochat nanochat Public

    Forked from karpathy/nanochat

    The best ChatGPT that $100 can buy.

    Python