🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…

A data visualization curriculum of interactive notebooks.

Machine Learning Systems

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

Democratizing Reinforcement Learning for LLMs

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

A framework for few-shot evaluation of language models.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

Python package for Sentential Decision Diagrams (SDD)

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

OLMoE: Open Mixture-of-Experts Language Models

The Python PSDD Package

Official Implementation for paper: Negative Token Merging: Image-based Adversarial Feature Guidance

Official Repo for Open-Reasoner-Zero

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks (ICML 2024)

Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

Implementation of CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation

A full Python Implementation of the ROUGE Metric (not a wrapper)

A curated list of awesome vision and language resources (still under construction... stay tuned!)

Parallel data preprocessing for NLP and ML.

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.

Reading list for research topics in multimodal machine learning

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

机器学习/深度学习/Python/Go语言面试题笔试题(Machine learning Deep Learning Python and Golang Interview Questions)