ProofNet dataset ported into Lean 4

State-of-the-art bilingual open-sourced Math reasoning LLMs.

Retrieval-Augmented Theorem Provers for Lean

ChatGPT plugin for theorem proving in Lean

[COLM 2024] A Survey on Deep Learning for Theorem Proving

miniF2F dataset ported into Lean 4

Resources of deep learning for mathematical reasoning (DL4MATH).

train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism

《特师文集》——大咕咕咕鸡著

Awesome-LLM: a curated list of Large Language Model

A machine learning tool for fishing entities

StableLM: Stability AI Language Models

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

Plain pytorch implementation of LLaMA

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Repo for Aspire - A scientific document similarity model based on matching fine-grained aspects of scientific papers.

For developers, who are building real-time data-driven applications, Redis is the preferred, fastest, and most feature-rich cache, data structure server, and document and vector query engine.

Official code and data repository for our EMNLP 2020 long paper "Reformulating Unsupervised Style Transfer as Paraphrase Generation" (https://arxiv.org/abs/2010.05700).

Pytorch implementation of "A Probabilistic Formulation of Unsupervised Text Style Transfer" by He. et. al. at ICLR 2020

Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer (IJCAI 2019)

Science Parse parses scientific papers (in PDF form) and returns them in structured form.

🤗 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.

A machine learning software for extracting information from scholarly documents

Companion code to the paper "Extracting Scientific Figures with Distantly Supervised Neural Networks" 🤖

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

深度学习经典、新论文逐段精读

iTerm2 is a terminal emulator for Mac OS X that does amazing things.

You like pytorch? You like micrograd? You love tinygrad! ❤️