-
Xi'an Jiao Tong university
-
-
-
mla-fuse Public
MLA的设计可以保证效果与传统的MHA效果相同的情况下,实现更低的kv-cache开销。但是官方并没有给出矩阵融合后的推理代码,这对于对齐论文中的效果是必要的一步。本仓库的代码用来实现MLA的参数融合,以及融合后的pytorch推理代码。
-
Lancer Public
Lancer是一个基于pyqt6开发的PC端copilot工具,它非常精简sharp,可以根据前台软件改变功能。
-
-
Awesome-Mixture-of-Experts-Papers Public
Forked from codecaution/Awesome-Mixture-of-Experts-PapersA curated reading list of research in Mixture-of-Experts(MoE).
Apache License 2.0 UpdatedSep 4, 2023 -
DeepSpeed Public
Forked from microsoft/DeepSpeedDeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Python Apache License 2.0 UpdatedAug 9, 2023 -
DeepSpeedExamples Public
Forked from microsoft/DeepSpeedExamplesExample models using DeepSpeed
Python Apache License 2.0 UpdatedApr 13, 2023 -
-
-
Research Public
Forked from PaddlePaddle/Researchnovel deep learning research works with PaddlePaddle
Python Apache License 2.0 UpdatedMar 29, 2022 -
transformers Public
Forked from huggingface/transformers🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
Python Apache License 2.0 UpdatedAug 21, 2021 -
tensor2tensor Public
Forked from tensorflow/tensor2tensorLibrary of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Python Apache License 2.0 UpdatedDec 15, 2020 -
FastBERT Public
Forked from autoliuweijie/FastBERTThe score code of FastBERT (ACL2020)
Python UpdatedMay 13, 2020 -
image_manipulation_detector Public
A tensorflow implementation of paper "A Deep Learning Approach To Universal Image Manipulation Detection Using A New Convolutional Layer"
-
NLP-progress Public
Forked from sebastianruder/NLP-progressRepository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.