-
University of Toronto
- Toronto
-
21:27
(UTC -05:00) - https://rexxxx1234.github.io/
- @RexMa9
- in/rex-ma-20a455113
Stars
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
The official PyTorch implementation of Google's Gemma models
Model interpretability and understanding for PyTorch
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
GLIDE: a diffusion-based text-conditional image synthesis model
Official repository for the Boltz biomolecular interaction models
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf
Graphormer is a general-purpose deep learning backbone for molecular modeling.
Biomni: a general-purpose biomedical AI agent
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
Unifying Variational Autoencoder (VAE) implementations in Pytorch (NeurIPS 2022)
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
Chai-1, SOTA model for biomolecular structure prediction
Keep track of internships for Summer 2020 for undergraduates interested in tech./SWE/related fields
Meta-Transformer for Unified Multimodal Learning
To eventually become an unofficial Pytorch implementation / replication of Alphafold2, as details of the architecture get released
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Implementation of Alphafold 3 from Google Deepmind in Pytorch
Bringing BERT into modernity via both architecture changes and scaling
Deep probabilistic analysis of single-cell and spatial omics data
OctoTools: An agentic framework with extensible tools for complex reasoning
A trainable PyTorch reproduction of AlphaFold 3.
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
Cramming the training of a (BERT-type) language model into limited compute.