Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

使用deepspeed从头开始训练一个LLM,经过pretrain和sft阶段,验证llm学习知识、理解语言、回答问题的能力

A collection of 150+ surveys on LLMs

Grok open release

Stable Diffusion, SDXL, LoRA Training, DreamBooth Training, Automatic1111 Web UI, DeepFake, Deep Fakes, TTS, Animation, Text To Video, Tutorials, Guides, Lectures, Courses, ComfyUI, Google Colab, R…

LoRA training scripts & GUI use kohya-ss's trainer, for diffusion model.

Adapted from https://note.com/kohya_ss/n/nbf7ce8d80f29 for easier cloning

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image …

Attention is all you need implementation

An autoregressive character-level language model for making more things

GLIDE: a diffusion-based text-conditional image synthesis model

This is a guide that presents how Fine tuning Stable diffusion's models work. This is an entry level guide for newcomers, but also establishes most of the concepts of training in a single place.

An Open Toolkit for Knowledge Graph Extraction and Construction published at EMNLP2022 System Demonstrations.

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。

text-summarization

transformers ocr for chinese

Explore different chinese nlp tasks by using t5/mt5/t5-pegasus like text-classification, text-summary and so on.

Best Practices on Recommendation Systems

公众号【浅梦学习笔记】文章汇总:包含 排序&CXR预估，召回匹配，用户画像&特征工程，推荐搜索综合 计算广告，大数据，图算法，NLP&CV，求职面试 等内容

TensorFlow code and pre-trained models for BERT

🧑‍🏫 50! Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cycle…

Robust fine-tuning of zero-shot models

wordrank, context-aware term weighting for for documents and queries. 词权重计算，结合词文本特征、统计特征、语言模型特征对词权重分级。

A deep matching model library for recommendations & advertising. It's easy to train models and to export representation vectors which can be used for ANN search.

Easy-to-use,Modular and Extendible package of deep-learning based CTR models .

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

基于GOOGLE T5中文生成式模型的摘要生成/指代消解，支持batch批量生成，多进程