-
Peking University
- Beijing
Stars
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 and reasoning techniques.
A generative speech model for daily dialogue.
[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
Paddle Large Scale Classification Tools,supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.
Beyond Accuracy: Behavioral Testing of NLP models with CheckList
Python suite to construct benchmark machine learning datasets from the MIMIC-III clinical database.
Easy-to-use,Modular and Extendible package of deep-learning based CTR models .
An elegant \LaTeX\ résumé template. 大陆镜像 https://gods.coding.net/p/resume/git
Facilitating the design, comparison and sharing of deep text matching models.
pytorch implementation of transformer for 1D data
PyTorch implementations of several SOTA backbone deep neural networks (such as ResNet, ResNeXt, RegNet) on one-dimensional (1D) signal/time-series data.
A list of papers on Generative Adversarial (Neural) Networks
Deep Learning on ECG, the First place in the PhysioNet/CinC Challenge 2017 (F1=0.83)
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals, IJCAI 2019
A curated list of network embedding techniques.
A collection of AWESOME things about domian adaptation
A curated list of ML|NLP resources for healthcare.