user: EarlyOom

205 karma | created 4 years ago

recent submissions

(no title)

8 months ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

Replace OCR with Vision Language Models (github.com)

292 pts|1 year ago|125 comments

(no title)

1 year ago|discuss

Show HN: Visually parse an entire YouTube video frame by frame (github.com)

5 pts|1 year ago|discuss

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

1 pts|1 year ago|discuss

A Node.js SDK for calling Vision Language Models (github.com)

6 pts|1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

(no title)

1 year ago|discuss

Run structured extraction on documents/images locally with Ollama and Pydantic (github.com)

170 pts|1 year ago|29 comments

(no title)

1 year ago|discuss

Show HN: Vlm Run, Extract JSON from images, videos and documents in a simple API (vlm.run)

2 pts|1 year ago|discuss

(no title)

1 year ago|discuss