ConradZimsky's starred repositories
baby-llama2-chinese
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.
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
transition-amr-parser
SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
Graph2Tree
Code for Graph-to-Tree Learning for Solving Math Word Problems (ACL 2020)
w266-commonsenseqa
W266 CommonsenseQA
mosaic-leaderboard
Leaderboard implementations for datasets produced by the Mosaic Team.
Share-SSR-V2ray
机场推荐/SSR V2ray节点订阅机场/镜像直连/工具推荐
PromptPapers
Must-read papers on prompt-based tuning for pre-trained language models.
OpenLearning4DeepRecsys
Some deep learning based recsys for open learning.
AAAI_2020_CommonsenseQA
Code for "Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering. (published at AAAI 2020)"