rmgogogo
Follow
Stars
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch
Official PyTorch implementation of SegFormer
Train high-quality text-to-image diffusion models in a data & compute efficient manner
大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP
Lab assignments for Introduction to Data-Centric AI, MIT IAP 2024 👩🏽💻
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Official JAX implementation of MAGVIT: Masked Generative Video Transformer
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
A modern and customizable python UI-library based on Tkinter
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Simple, safe way to store and distribute tensors
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
High-Resolution Image Synthesis with Latent Diffusion Models
Tensorflow implementation of DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
Painter & SegGPT Series: Vision Foundation Models from BAAI
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
A natural language interface for computers