The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本

YaRN: Efficient Context Window Extension of Large Language Models

An Experiment on Dynamic NTK Scaling RoPE

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

Download Youtube Video in Golang

Python library & examples for Masked Language Model Scoring (ACL 2020)

Unicoder model for understanding and generation.

BETO - Spanish version of the BERT model

sentence embedding by Smooth Inverse Frequency weighting scheme

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

SimCSE在中文任务上的简单实验

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

(AAAI'20) The source code for the paper "Controlling the Amount of Verbatim Copying in Abstractive Summarization".

(AAAI'20) The source code for the paper "Controlling the Amount of Verbatim Copying in Abstractive Summarization".

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

书籍《现代自然语言生成》介绍

A Python wrapper for the ROUGE summarization evaluation package

Calculating ROUGE score between two files (line-by-line)

Speech and Language Processing, 2nd Edition in PDF format

CodeXGLUE

Code for the book Grokking Algorithms (https://www.amazon.com/dp/1633438538)

Unsupervised text tokenizer for Neural Network-based text generation.

OCNLI: 中文原版自然语言推理任务

A Large-scale Chinese Short-Text Conversation Dataset and Chinese pre-training dialog models

AI education materials for Chinese students, teachers and IT professionals.

Finetune CPM-1

Chinese Pre-Trained Language Models (CPM-LM) Version-I