A differentiable PDE solving framework for machine learning

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

🐚 OpenDevin: Code Less, Make More

From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

a research paper for generative cartoon interpolation

4M: Massively Multimodal Masked Modeling

Official code for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)

A Native-PyTorch Library for LLM Fine-tuning

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

A native PyTorch Library for large model training

Official repo for "iVideoGPT: Interactive VideoGPTs are Scalable World Models", https://arxiv.org/abs/2405.15223

LOFT: A 1 Million+ Token Long-Context Benchmark

LLM training in simple, raw C/CUDA

Code and data for the benchmark "Multimodal Needle in a Haystack (MMNeedle): Benchmarking Long-Context Capability of Multimodal Large Language Models"

The official Meta Llama 3 GitHub site

Official Code Release for HOIDiffusion (CVPR 2024)

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

EVE: Encoder-Free Vision-Language Models from BAAI

Code&Data for Grounded 3D-LLM with Referent Tokens

Some information about parameters and options available in COLMAP - SfM & MVS software. https://colmap.github.io

code for "PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction"

Code for "LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model", CVPR 2024 Highlight

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

[BSQ-ViT] Image and Video Tokenization with Binary Spherical Quantization

Simulating SMPL humanoid, supporting PHC/PHC-MJX/PULSE/SimXR code bases.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation