🧑‍🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.

Retrieval and Retrieval-augmented LLMs

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

前沿论文持续更新--视频时刻定位 or 时域语言定位 or 视频片段检索。

Repository for 23'MM accepted paper "Curriculum-Listener: Consistency- and Complementarity-Aware Audio-Enhanced Temporal Sentence Grounding"

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

This is the repo for the survey of LLM4IR.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

A java implementation of Bert Tokenizer.

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

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）

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

keras implement of transformers for humans

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

基于开源GPT2.0的初代创作型人工智能 | 可扩展、可进化

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Chinese GPT2: pre-training and fine-tuning framework for text generation

基于金融-司法领域(兼有闲聊性质)的聊天机器人，其中的主要模块有信息抽取、NLU、NLG、知识图谱等，并且利用Django整合了前端展示,目前已经封装了nlp和kg的restful接口

DeepLab v3+ model in PyTorch. Support different backbones.

Code for "Autoencoder as Assistant Supervisor: Improving Text Representation for Chinese Social Media Text Summarization"

Multiple implementations for abstractive text summurization , using google colab

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation