Top New Best Ask Show Jobs

EarlyOom

205 karma · joined March 22, 2022

submissions comments

Replace OCR with Vision Language Models

github.com·292 pts·EarlyOom·

Show HN: Visually parse an entire YouTube video frame by frame

github.com·5 pts·EarlyOom·

Ask HN: What are folks using to train/fine-tune Vision Language Models

1 pts·EarlyOom·

A Node.js SDK for calling Vision Language Models

github.com·6 pts·EarlyOom·

Run structured extraction on documents/images locally with Ollama and Pydantic

github.com·170 pts·EarlyOom·

Show HN: Vlm Run, Extract JSON from images, videos and documents in a simple API

vlm.run·2 pts·EarlyOom·

Fine-grained Visual Transcription for YouTube videos

vlm-docs.nos.run·9 pts·EarlyOom·

"Ok Computer, why are you slow?"

scottloftin.substack.com·2 pts·EarlyOom·

Show HN: NOS – A fast, and ergonomic PyTorch inference server

github.com·3 pts·EarlyOom·