Stars
Exploring differentiation with respect to hyperparameters
For optimization algorithm research and development. Submodule & Py38 ready
Medical Graph RAG: Graph RAG for the Medical Data
Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
Exploring the GLUE benchmark and fine tuning tasks on pre-trained BERT model using Hugging Face on PyTorch..
This helps you to submit job with multinode & multgpu in Slurm in Torchrun
Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"
Codes for theoretical study of learning rate scheduling in non-convex problems.
94% on CIFAR-10 in 2.6 seconds 💨 96% in 27 seconds
Granite Time Series Cookbook
A tiny neural network for CIFAR-10 dataset
General tips to drive your research at Mila
A curated list of awesome Distributed Deep Learning resources.
Efficient Triton Kernels for LLM Training
Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"
The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open sourced AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SL…
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration (TMLR 2024)
Implementation of Faithfulness measurable masked language models
Official code for "Distributed Deep Learning in Open Collaborations" (NeurIPS 2021)
A native PyTorch Library for large model training
Model Stock: All we need is just a few fine-tuned models
🌱🚿🔆