machine-learning

[🏆Outstanding Paper Award at ACL 2024] MMToM-QA: Multimodal Theory of Mind Question Answering

Unified storage framework for the entire machine learning lifecycle

Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper

Triple Branch BERT Siamese Network for fake news classification on LIAR-PLUS dataset in PyTorch

Vector search demo with the arXiv paper dataset, RedisVL, HuggingFace, OpenAI, Cohere, FastAPI, React, and Redis.

Loop until it's better — drop-in agentic loops (autoresearch, scientific writing, data analysis, code/SQL/prompt optimization, red-teaming) as open-standard Agent Skills. Verification-gated; native on Claude Code, portable across Codex, Cursor & other Skills hosts.

Implementation of paper "Uni-3DAR: Unified 3D Generation and Understanding via Autoregression on Compressed Spatial Tokens"

This is an advanced Python tool that empowers you to effortlessly draft customizable PowerPoint slides using the Generative Pre-trained Transformer (GPT) of your choice. Leveraging the capabilities of Large Language Models (LLM), odin-slides enables you to turn the lengthiest Word documents into well organized presentations.

A multi-modal CLIP model trained on the medical dataset ROCO

Swarming algorithms like PSO, Ant Colony, Sakana, and more in PyTorch 😊

This is the corresponding code for the book Transformers in Action

A framework for fine-tuning retrieval-augmented generation (RAG) systems.

Upload your data → Get a fine-tuned SLM. Free.

transformers go brrr...

Easiest way of fine-tuning HuggingFace video classification models

⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.

[Course-2020-2023] taught at Duke MIDS. This is also a Coursera Course that covers MLOps, ML Engineering and the foundations of Cloud Computing for Data Science.

Implementation of PALI3 from the paper PALI-3 VISION LANGUAGE MODELS: SMALLER, FASTER, STRONGER"

BERT classification model for processing texts longer than 512 tokens. Text is first divided into smaller chunks and after feeding them to BERT, intermediate results are pooled. The implementation allows fine-tuning.

<트랜스포머를 활용한 자연어 처리> 예제 코드를 위한 저장소입니다.