About Dave Lage
^ that's me.About
Web Product Engineer, Community Builder, Computer Vision, Naturalist
Developing tools for building image and captioning datasets, training computer vision models, and building analysis tools.
Experience building social networks, distributed pipelines, website builders, e-commerce websites, software architecture (ORM, MVC), CI/CD systems.
Working on
- Building parameter efficient model analysis and tokenizer tools in the browser
- Building aesthetic prediction models (Preference, Rating)
- Enhancing training systems for Stable Diffusion
- Building Image captioning models using LoRA and other parameter efficient methods.
- Building dataset creation, filtering, captioning pipeline tools
- Building image rating and preference capturing tooling for aesthetic modeling (DPO, Aesthetic Predictor)
- Building stable diffusion scripts for analysis, conversion, pruning, scaling, evaluation
- Building transformers cross-attention visualization tooling with flexibility (DAAM)
- Experimenting with Rust candle ML for training, inference, and WASM
- Teaching and helping others learn to fine-tune foundation models
Find me elsewhere
- GitHub — https://github.com/rockerBOO
- LinkedIn — https://linkedin.com/in/rockerBOO
- Civitai — https://civitai.com/user/rockerBOO
- Discord — rockerBOO
- YouTube — https://youtube.com/c/rockerBOO
- Twitch — https://twitch.tv/rockerBOO
- GitLab — https://gitlab.com/rockerBOO