Neural networks are all you need
mini_DiT. minimal diffusion transformer in pytorch.
17ripple_net. image retrieval/tagging with CLIP
13dit_flow. DiT (training + flow matching) in Jax
12shira_audio. A neural audio search/retrieval library
9mini_pixart. minimal implementation of Pixart text-to-image model
9nnx_save. checkpointing for flax models (nnx)
6studyassist. AI + RAG chat for documents
4moonvid. hacky video captioning with moondream
4web_chat. RAG application for webpages
4aaliyah. my experimental garden for vision models
4shiryoku. A vision model for image captioning built with Pytorch [incomplete]
4paintbrush. my playground for diffusion/image gen
2vidtext. A transcription web app for video and audio files
2sentiment_classifier. Tweet/Review sentiment classifier
2mini_diffusion. tiny latent diffusion model
2microvid. video generation with microdiffusion framework
2lila. ViT/MAE in pytorch
2play_jax. sandbox for different JAX projects
2snowpark. multimodal experiments/adaptation
2audio_class. audio model for classification
2storybook. text narration to visual stories with image generation models
1katara. my custom dev toolkit
1microdit_jax. trainable Jax implementation of MicroDiT
1mini_transformer. Transformer from scratch in Pytorch, for English-Italian translation
1arxivcs_text. Scraping and dataset code for arxivcs-text dataset
1Agric_vision_model. Python
1mini_clip. Implementation of CLIP, in pytorch
1vivy_. a tiny generative model for audio/music
1js-converter. HTML
1mini_yolo. pytorch implementation of the YOLO model, from the paper You Only Look Once: Unified, Real-Time Object Detection
1