Tags: #pytorch

Streamlines complex deep learning engineering, enabling scalable AI model training and finetuning across diverse hardware with minimal code changes.

An educational project providing step-by-step code to build a ChatGPT-like Large Language Model (LLM) from scratch using PyTorch.

A KVCache-centric disaggregated architecture for high-performance LLM serving, powering leading AI services.

A PyTorch library enabling accessible large language models through k-bit quantization, significantly reducing memory consumption for both inference and training.

A low-code, declarative framework for building and deploying custom large language models (LLMs) and other deep neural networks with ease and efficiency.

A comprehensive and curated collection of deep learning study notes, integrating content from leading educators like Andrew Ng, Li Mu, and TuDui, covering CV, NLP, and Large Language Models.

A PyTorch-based framework to adapt Meta AI's Segment Anything Model (SAM) for improved performance on challenging downstream computer vision tasks using adapters and prompts.

A unified library extending HuggingFace Transformers for parameter-efficient and modular transfer learning in NLP.

A comprehensive collection of PyTorch implementations for over 60 deep learning papers, featuring side-by-side annotated notes for enhanced understanding.

A Python library implementing LoRA (Low-Rank Adaptation) to efficiently fine-tune large language models by significantly reducing trainable parameters and storage requirements.

A modular PyTorch library for state-of-the-art diffusion models, enabling easy inference and training for image, video, and audio generation.

A PyTorch implementation for generating 3D models from text or images, leveraging NeRF and diffusion models like Stable Diffusion.

A fast, minimal PyTorch port of DALL·E Mini for efficient text-to-image generation.

A PyTorch implementation of Google's Imagen, a state-of-the-art text-to-image neural network, enabling advanced generative AI capabilities.

A PyTorch implementation of OpenAI's DALL-E 2, a state-of-the-art neural network for text-to-image synthesis.

An open-source PyTorch implementation and replication of OpenAI's DALL-E, a text-to-image transformer, including CLIP for generation ranking.

A scalable generative AI framework for researchers and developers focused on Large Language Models, Multimodal, and Speech AI (ASR, TTS).

A collection of pre-trained, end-to-end text-to-speech models designed for simplicity, speed, and natural-sounding speech across multiple languages.

A real-time voice cloning toolkit that allows users to replicate a voice in 5 seconds and generate arbitrary speech.

A PyTorch implementation of BitNet, enabling highly efficient 1-bit transformers for large language models.

A modular and scalable PyTorch-based framework for state-of-the-art vision and language multimodal research from Facebook AI Research.

A high-performance, comprehensive face recognition library built on PaddlePaddle and PyTorch.

An open-source PyTorch-based framework for NLP pre-training and fine-tuning, offering modularity, reproducibility, and a comprehensive model zoo for various downstream tasks.

A toolkit for finetuning ChatGLM series models (ChatGLM-6B, ChatGLM2-6B, ChatGLM3-6B) using various methods like Freeze, Lora, P-tuning, and full parameter training for downstream NLP tasks.

A unified platform simplifying instruction-tuning for Large Language Models by integrating diverse data, LLMs, and parameter-efficient methods.

DiffSinger is an official PyTorch implementation of a singing voice synthesis (SVS) and text-to-speech (TTS) system, leveraging a shallow diffusion mechanism for high-quality audio generation.

A deep learning library for advanced, high-quality, and efficient Text-to-Speech (TTS) synthesis, supporting multiple languages and models.

LyCORIS is a library implementing various parameter-efficient fine-tuning (PEFT) algorithms for Stable Diffusion, extending beyond conventional LoRA methods to enhance model adaptation.

An open-source, theoretical reconstruction of the Claude Mythos LLM architecture, featuring a Recurrent-Depth Transformer and sparse Mixture of Experts for advanced reasoning.

A high-performance, no-abstraction toolkit providing recipes for pretraining, finetuning, and deploying over 20 large language models at scale.

MMPreTrain is an OpenMMLab project providing a comprehensive, open-source PyTorch-based toolbox for pre-training and benchmarking various computer vision and multi-modal models.

A PyTorch library providing advanced foundation architectures to efficiently and effectively scale Transformers for large language models and general-purpose AI.