Stars
MTEB: Massive Text Embedding Benchmark
Making large AI models cheaper, faster and more accessible
ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Instruct-tune LLaMA on consumer hardware
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.
ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型
Video Copy Segment Localization (VCSL) dataset and benchmark [CVPR2022]
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
程序员延寿指南 | A programmer's guide to live longer
收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中
Source code for the paper "PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction" in ACL2021
EMNLP 2020: "Dialogue Response Ranking Training with Large-Scale Human Feedback Data"
A Knowledge Grounded Conversation (KGC) Paper Reading List Maintained by Chuan Meng.
"Conversations Powered by Cross-Lingual Knowledge" in SIGIR'21
Gradually-Warmup Learning Rate Scheduler for PyTorch
Code for Findings of ACL 2021 paper "Addressing Inquiries about History: An Efficient and Practical Framework for Evaluating Open-domain Chatbot Consistency".
A crowdsourced dataset of dialogues grounded in social contexts involving utilization of commonsense.
code associated with ACL 2021 DExperts paper
The released codes for ACL 2021 paper 'BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data'
Evaluation code for various unsupervised automated metrics for Natural Language Generation.