pretrain

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料

Firefly中文LLaMA-2大模型，支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型

An official implementation for " UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"

Paper Lists, Notes and Slides, Focus on NLP. For summarization, please refer to https://github.com/xcfcode/Summarization-Papers

BERT-CCPoem is an BERT-based pre-trained model particularly for Chinese classical poetry

Bert-based models(BERT, MTB, CP) for relation extraction.

MatDGL is a neural network package that allows researchers to train custom models for crystal modeling tasks. It aims to accelerate the research and application of material science.

code for paper "Masked Frequency Modeling for Self-Supervised Visual Pre-Training" (https://arxiv.org/pdf/2206.07706.pdf)

Official code repository for the paper "Pushing the Limits of Pre-training for Time Series Forecasting in the CloudOps Domain"

[CCIR 2023] Self-supervised learning for Sequential Recommender Systems

ALBERT trained on Mongolian text corpus

Make your Generative AI LM model from the scratch (Including pretraining / SFT with LoRA)

macrogpt大模型全量预训练(1b3,32层), 多卡deepspeed/单卡adafactor

GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation

Parsing Hoyoverse game text corpus from public wikipedia

This repository provides code solution for Data Fusion Contest task 1

Running Large Language Model easily.

Understanding "A Lite BERT". An Transformer approach for learning self-supervised Language Models.