-
Microsoft
- Seattle, WA
Stars
A framework for few-shot evaluation of language models.
Helpful tools and examples for working with flex-attention
This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small langua…
[ICLR 2024 & ECCV 2024] The All-Seeing Projects: Towards Panoptic Visual Recognition&Understanding and General Relation Comprehension of the Open World"
Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
Fast and memory-efficient exact attention
Minimalistic large language model 3D-parallelism training
GPU programming related news and material links
Zero Bubble Pipeline Parallelism
Development repository for the Triton language and compiler
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
Chat with GitHub Copilot in Neovim
[3DV 2025] iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
SVIT: Scaling up Visual Instruction Tuning
LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following
Research code for NeurIPS 2023 paper "Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser"
An Open-source Toolkit for LLM Development
An efficient video loader for deep learning with smart shuffling that's super easy to digest
[NeurIPS 2023] Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models
Make-A-Protagonist: Generic Video Editing with An Ensemble of Experts
EVA Series: Visual Representation Fantasies from BAAI
A playbook for systematically maximizing the performance of deep learning models.