Expressive Anechoic Recordings of Speech (EARS)

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Repository for paper scMulan: a multitask generative pre-trained language model for single-cell analysis.

Lecture notes for a course on writing proofs, on paper and in the Lean proof assistant

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Tools for merging pretrained large language models.

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Towards a general-purpose foundation model for computational pathology - Nature Medicine

[ICML'24 Oral] The official code of "DiJiang: Efficient Large Language Models through Compact Kernelization", a novel DCT-based linear attention mechanism.

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

This repository contains the implementation for the paper "EMP-SSL: Towards Self-Supervised Learning in One Training Epoch."

⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

Unbearably fast near-real-time hybrid runtime-static type-checking in pure Python.

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

The user home repository for the Mathematics in Lean tutorial.

Export Segment Anything Models to ONNX

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

Implementation of SoundStorm built upon SpeechTokenizer.

Robust recipes to align language models with human and AI preferences

Real-time transcription using faster-whisper

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

SMILES Pair Encoding: A data-driven substructure representation of chemicals