Ongoing research training transformer models at scale

Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

Hackable and optimized Transformers building blocks, supporting a composable construction.

Proxy server to bypass Cloudflare protection

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Official implementation of OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on

Supercharge Your Model Training

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Modeling, training, eval, and inference code for OLMo

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Interact with your SQL database, Natural Language to SQL using LLMs

Agentic components of the Llama Stack APIs

PyTorch implementation of Contrastive Learning methods

tha3, but run 40fps on 3080 with virtural webcam support

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Automated CAPTCHA solver usage examples.

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

Stanford NLP Python Library for Understanding and Improving PyTorch Models via Interventions

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)

Artificial intelligence learn playing any game with watching you.

A python bot that plays candy crush

An implementation of masked language modeling for Pytorch, made as concise and simple as possible

Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification

Video streaming with FastAPI