Pinned Repositories
-
算法设计技巧与分析第一次大作业
ascend_qwen_cot_qlora
glow-mnist
GobangAi
place365classification
qwen2.5-qa-finetune
qwen2.5 QA问答
resnet50-demo-on-local
A demo implementation of resnet50 running locally. There are many benefits to using a local server instead of a swanhub server for inference, including the ability to use GPUs, or some demos that rely on special hardware.
speed_with_ddp
swanlab_stock_exp
swanlab的kaggle股票案例，参考https://docs.swanlab.cn/zh/examples/lstm_stock.html
transformers_from_scratch
pretrain a wiki llm using transformers
ShaohonChen's Repositories
ShaohonChen/transformers_from_scratch
pretrain a wiki llm using transformers
ShaohonChen/speed_with_ddp
ShaohonChen/place365classification
ShaohonChen/glow-mnist
ShaohonChen/qwen2.5-qa-finetune
qwen2.5 QA问答
ShaohonChen/resnet50-demo-on-local
A demo implementation of resnet50 running locally. There are many benefits to using a local server instead of a swanhub server for inference, including the ability to use GPUs, or some demos that rely on special hardware.
ShaohonChen/swanlab_stock_exp
swanlab的kaggle股票案例，参考https://docs.swanlab.cn/zh/examples/lstm_stock.html
ShaohonChen/ascend_qwen_cot_qlora
ShaohonChen/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.
ShaohonChen/cifar10_with_resnet50
resnet50 classification using mmengine
ShaohonChen/clip_zip
ShaohonChen/corenet
CoreNet: A library for training deep neural networks
ShaohonChen/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
ShaohonChen/hugging-multi-agent
A tutorial to quickly help you understand the concept of agent and muti-agent and get started with coding development
ShaohonChen/JoinInAfdian
加入爱发电
ShaohonChen/LeNet
ShaohonChen/llama
Inference code for Llama models
ShaohonChen/LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
ShaohonChen/llama3
The official Meta Llama 3 GitHub site
ShaohonChen/loss-of-plasticity
Demonstrations of Loss of Plasticity and Implementation of Continual Backpropagation
ShaohonChen/mindspore_imdb_train
本项目为使用mindspore实现的IMDB数据集情感分类任务。并使用SwanLab跟踪模型训练进展。
ShaohonChen/minimind
「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！
ShaohonChen/mmdetection
OpenMMLab Detection Toolbox and Benchmark
ShaohonChen/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
ShaohonChen/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
ShaohonChen/pykan
Kolmogorov Arnold Networks
ShaohonChen/Qwen2
Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.
ShaohonChen/SwanLab
🧐SwanLab: track and visualize all the pieces of your machine learning pipeline. Join our WeChat ⬇️
ShaohonChen/ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
ShaohonChen/Yi
A series of large language models trained from scratch by developers @01-ai