-
University of Sydney
- Sydney
-
05:58
- 11h ahead - https://orcid.org/0009-0007-6066-5492
- https://huggingface.co/XavierSpycy
- in/jiarui-xu-xavierspycy98
- https://blog.csdn.net/NJ_Xavier
Highlights
- Pro
-
-
NumPy-Keras Public
A Multilayer Perceptron from scratch using NumPy. Offers almost all basic functionalities . Suitable for classification and regression tasks. 一个用NumPy从零实现的多层感知机。提供几乎所有基本功能。适用于分类和回归任务。
-
EMNIST-Classifier Public
Handwritten character recognition on EMNIST ByClass using Convolutional Neural Networks with PyTorch.
-
hands-on-lora Public
Explore practical fine-tuning of LLMs with Hands-on Lora. Dive into examples that showcase efficient model adaptation across diverse tasks.
-
beginner.c Public
Description: Useful coding notes for the "C Programming for Everybody" Specialization.
C MIT License UpdatedOct 8, 2024 -
tabtransformers Public
A PyTorch-based implementation that leverages Transformer architectures to enhance the handling and design of tabular data. With the capabilities of Transformer models, we aim to provide data scien…
-
nn4sa Public
Neural Networks for Sentiment Analysis: Comprehensive Hands-on Practices with RNN, BERT, and Advanced Embeddings for Aspiring NLP Beginners
Python MIT License UpdatedJul 15, 2024 -
llama-ops Public
A step-by-step cookbook on fine-tuning and deploying Llama3. 一部关于Llama3微调和部署的分步手册。
Python Apache License 2.0 UpdatedJul 2, 2024 -
NumPyNMF Public
NumPyNMF implements nine different Non-negative Matrix Factorization (NMF) algorithms using NumPy library and compares the robustness of each algorithm to five various types of noise in real-world …
-
MultiCLIP Public
MultiCLIP: A framework for multimodal-multilabel-multistage classification utilizing advanced pretrained models like CLIP and BLIP. 一个多模态多标签多阶段分类框架,利用像CLIP和BLIP这样的先进预训练模型。
-
OCTIS Public
Forked from MIND-Lab/OCTISOCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
Python MIT License UpdatedJun 15, 2024 -
CAT-ImageTextIntegrator Public
An innovative deep learning framework leveraging the CAT (Convolutions, Attention & Transformers) architecture to seamlessly integrate visual and textual modalities. This model exploits the prowess…
-
This experiments with ResNet34 on highly noisy (50%+) FashionMNIST and CIFAR datasets. Focuses on Forward Loss Correction, CoTeaching, initial trials with JoCoR, O2UNet, and Dual-T for unknown tran…
Python MIT License UpdatedNov 28, 2023