BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

免费开源的网易BUFF、悠悠有品、ECOsteam、C5Game、Steam的全自动收发货解决方案

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

Unsupervised text tokenizer for Neural Network-based text generation.

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

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Making large AI models cheaper, faster and more accessible

A Unified Library for Parameter-Efficient and Modular Transfer Learning

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

A curated list of research papers in Sentence Reprsentation Learning and a sts leaderboard of sentence embeddings.

Simplify your onnx model

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

Convert BART models to ONNX with quantization. 3X reduction in size, and upto 3X boost in inference speed

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

LightSeq: A High Performance Library for Sequence Processing and Generation

MLNLP社区用来更好进行论文搜索的工具。Fully-automated scripts for collecting AI-related papers

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

自然语言处理学习笔记：机器学习及深度学习原理和示例，基于 Tensorflow 和 PyTorch 框架，Transformer、BERT、ALBERT等最新预训练模型及源代码详解，及基于预训练模型进行各种自然语言处理任务。模型部署

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

pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。

An elegent pytorch implement of transformers