VatsaDev's starred repositories
gemma_pytorch
The official PyTorch implementation of Google's Gemma models
RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.
quiet-star
Code for Quiet-STaR
TPU-Alignment
Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free
othello_mamba
Evaluating the Mamba architecture on the Othello game
quartic-transformer
Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)
tiny-asic-4bit-matrix-mul
Tiny matrix multiplication ASIC with 4-bit math
TransformerMath
Can transformers learn math, like patterns?
2024-Swerve-concept
Describing Swerve functionality, mockup math
NCPT-Lilith
A retrain of the old nanogpt, but with the lilith optimizer