FinMTEB: Finance Massive Text Embedding Benchmark

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

MTEB: Massive Text Embedding Benchmark

KURE: 고려대학교에서 개발한, 한국어 검색에 특화된 임베딩 모델

A modular graph-based Retrieval-Augmented Generation (RAG) system

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

A course on aligning smol models.

Take advantage of WME Structured-Contents APIs to seed a LLM RAG search engine

Supercharge Your Model Training

KSS: Korean String processing Suite

g2pK: g2p module for Korean

Official inference framework for 1-bit LLMs

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.

Code for the paper "UVDoc: Neural Grid-based Document Unwarping" - Dataset capture and creation

The Model Zoo of Knowledge Tracing Models

Implementation of paper "A Self-Attentive model for Knowledge Tracing"

SAINT PyTorch implementation

pyKT: A Python Library to Benchmark Deep Learning based Knowledge Tracing Models

🦜🔗 Build context-aware reasoning applications

llama3.np is a pure NumPy implementation for Llama 3 model.

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

[ICCV 2023] A large-scale high-resolution dataset satisfies all important data features about document shadow, covers a large number of document shadow images.

ShadowFormer (AAAI2023), Pytorch implementation

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Google Research