Stars
Code for the WASSA 2021 paper (oral) "An End-to-End Network for Emotion-Cause Pair Extraction"
Unofficial PyTorch Reimplementation of RandAugment.
Examples and demos on how to use Retrieval Augmented Generation with Large Language Models
Official repository of Agent Attention (ECCV2024)
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
Run Large Language Models on RK3588 with GPU-acceleration
一键中文数据增强包 ; NLP数据增强、bert数据增强、EDA:pip install nlpcda
ACL2021:Position Bias Mitigation: A Knowledge-Aware Graph Model for EmotionCause Extraction
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
liuzc188 / OpenCV3-Computer-Vision-Application-Programming-Cookbook-Third-Edition
Forked from PacktPublishing/OpenCV3-Computer-Vision-Application-Programming-Cookbook-Third-EditionCode repository for OpenCV 3 Computer Vision Application Programming Cookbook, Third Edition, published by Packt
Code repository for OpenCV 3 Computer Vision Application Programming Cookbook, Third Edition, published by Packt
Modeling, training, eval, and inference code for OLMo
✨✨Latest Advances on Multimodal Large Language Models
Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.
Dobb·E: An open-source, general framework for learning household robotic manipulation
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation me…
[EMNLP2020] End-to-End Emotion-Cause Pair Extraction based on SlidingWindow Multi-Label Learning
A Consistent Dual-MRC Framework for Emotion-Cause Pair Extraction
Python module which allows you to specify timeouts when calling any existing function, and support for stoppable threads
用于大模型 RLHF 进行人工数据标注排序的工具。A tool for manual response data annotation sorting in RLHF stage.
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
Let ChatGPT teach your own chatbot in hours with a single GPU!
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)