search

Aisuko / generative-ai

The notebooks for generative AI by using PyTorch, Huggingface/diffusers, transforms. And the implementing of the algorithms in paper
https://www.kaggle.com/aisuko/code
Apache License 2.0
11 stars 5 forks source link
applemetal collaborate convolutional-neural-networks diffusers github hacktoberfest2023 kaggle mps neural-network pytorch

readme

PyTorch Fundamentals

Learn the fundamentals of deep learning with PyTorch! This beginner friendly learning path will introduce key concepts to building machine learning models in multiple domains include speech, vision, and natural language processing.

And if you are interested to know more, please check another repo Implementation for the different ML tasks on Kaggle platform with GPUs.

NOTE: There do have many bugs due to the different version of dependencies, please open new issue to discuss it.

Introduce to PyTorch

No Title Open in Sagemaker Open in Kaggle
1 What are Tensors? Open in SageMaker Kaggle
2 Loading and normalizing datasets Open in SageMaker Kaggle
3 Building the model layers Open in SageMaker Kaggle
4 Automatic differentiation Open in SageMaker Kaggle
5 About the optimization loop Open in SageMaker Kaggle
6 Load and run model predictions Open in SageMaker Kaggle
7 The full model building process Open in SageMaker Kaggle

Audio classification with PyTorch

No Title Open in SageMaker Open in Kaggle
1 Understand audio data and concepts Open in SageMaker Kaggle
2 Audio transforms and visualizations Open in SageMaker Kaggle

Natural language processing with PyTorch

No Title Open in SageMaker Open in Kaggle
1 Representing text as Tensors Open in SageMaker Kaggle
2 Represent words with embeddings Open in SageMaker Kaggle
3 Capture patterns with RNN Open in SageMaker Kaggle
4 Generate text with RNN Open in SageMaker Kaggle

Computer vision with PyTorch

No Title Open in SageMaker Open in Kaggle
1 Introduction to CV with PyTorch Open in SageMaker Kaggle
2 Training a simple sense neural network Open in SageMaker Kaggle
3 Convolutional Neural Networks Open in SageMaker Kaggle
4 Multilayer Dense Neural Network Open in SageMaker Kaggle
5 Pre-trained models and transfer learning Open in SageMaker Kaggle
6 Lightweight Networks and MobileNet Open in SageMaker Kaggle

Diffusion

No Title Open in SageMaker Open in Kaggle Open in Colab
1 Deconstruct the Stable Diffusion pipeline Open in SageMaker Kaggle Colab
2 Basic training model Open in SageMaker Kaggle Colab
3 Deconstruct the basic pipeline Open in SageMaker Kaggle
4 Details for models and schedulers Open in SageMaker Kaggle
5 Effective and Efficient diffusion Open in SageMaker Kaggle
6 Generting by using float16(sppeding up) Open in SageMaker Kaggle
7 Stable Diffusion v1.5 demo Open in SageMaker Kaggle
8 Load checkpoints models and schedulers Open in SageMaker Kaggle
9 Schedulers Performance Open in SageMaker Kaggle
10 Stable diffusion with diffusers Open in SageMaker Kaggle

Paper implementation

No Title Open in SageMaker Open in Kaggle Open in Colab Paper
1 The annotated diffusion model Open in SageMaker Kaggle 1503.03585
1907.05600
2006.11239
2 QLoRA Fine-tuning for Falcon-7B with PEFT Open in SageMaker Kaggle

On macOS

All the notebooks are support mps, except if the notebooks import fp16 speeding up:

mps

Contributing

Warm welcome for any contributions, please follow the contributing guidelines.

Acknowledgement