mst272's starred repositories
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
CVPR2024-Papers-with-Code
CVPR 2024 论文和开源项目合集
PhotoMaker
PhotoMaker [CVPR 2024]
segmentation_models.pytorch
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
pycorrector
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
mamba-minimal
Simple, minimal implementation of the Mamba SSM in one file of PyTorch.
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.
Machine-Mindset
An MBTI Exploration of Large Language Models
Focal-Loss-Pytorch
全中文注释.(The loss function of retinanet based on pytorch).(You can use it on one-stage detection task or classifical task, to solve data imbalance influence).用于one-stage目标检测算法,提升检测效果.你也可以在分类任务中使用该损失函数,解决数据不平衡问题.
SenseEarth2020-ChangeDetection
1st place solution to the Satellite Remote Sensing Image Change Detection Challenge hosted by SenseTime
core-pytorch-utils
Yet another PyTorch Trainer and some core components for deep learning.
grouped-query-attention-pytorch
(Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)
codefuse-evaluation
Industrial-level evaluation benchmarks for Coding LLMs in the full life-cycle of AI native software developing.企业级代码大模型评测体系,持续开放中
Semantic-Change-Detection
This repository is for semantic change detection.
dfc2021-msd-baseline
A baseline for the "Multitemporal Semantic Change Detection" track of the 2021 IEEE GRSS Data Fusion Competition.
baby-llama2-chinese_fix
使用单个24G显卡，从0开始训练LLM
transformer-pytorch
A pytorch Implementation of the Transformer: Attention Is All You Need