←back to thread

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

(github.com)
166 points EarlyOom | 2 comments | 20 Feb 25 01:54 UTC | HN request time: 0.451s | source
1. kaushikbokka ◴[20 Feb 25 06:13 UTC] No.43111654[source]▶
Have you folks tried finetuning models for data extraction from visual data?
replies(1): >>43111724 #
2. EarlyOom ◴[20 Feb 25 06:25 UTC] No.43111724[source]▶
That's one of our main focuses, yes: https://docs.vlm.run/api-reference/v1/fine-tuning/post-finet...