Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Repository Index
47,133 repositories indexed
1–24 of 27 · Most stars
Learn AI Engineering! Learn it. Build it. Ship it for others.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
CVPR 2026 论文和开源项目合集
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Machine Learning Engineering Open Book
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
Ongoing research training transformer models at scale
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
A PyTorch-based Speech Toolkit
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Open-source offline translation library written in Python
Superduper: End-to-end framework for building custom AI applications and agents.
Seamlessly integrate LLMs into scikit-learn.
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
MLeap: Deploy ML Pipelines to Production
This Word Does Not Exist
A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.
Python package implementing ML feature engineering and pre-processing for polars or pandas dataframes.