Models and examples built with TensorFlow

A Gradio web UI for Large Language Models with support for multiple inference backends.

A high-throughput and memory-efficient inference and serving engine for LLMs

Fully open reproduction of DeepSeek-R1

Image augmentation for machine learning experiments.

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Statsmodels: statistical modeling and econometrics in Python

Uplift modeling and causal inference with machine learning algorithms

PyTorch native post-training library

An implementation of a deep learning recommendation model (DLRM)

Open source Structure-from-Motion pipeline

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

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

Message Passing Neural Networks for Molecule Property Prediction

A statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima function.

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

Visual Attention based OCR

Docker image for Graphite & Statsd

Recipe for a General, Powerful, Scalable Graph Transformer

Gaussian word embeddings

Exphormer: Sparse Transformer for Graphs

CIDNN: Encoding Crowd Interaction with Deep Neural Network