Using Extract-Thinker with Fine-tuned LLMs on Ollama

[praj-cs]

Hi, How can i use a Finetuned LLM vision model for the extraction?

[enoch3712]

Hello @praj-cs!

Do you mean finetuning with extractThinker? Thats not possible yet :)

But using finetuned models, that you already have, yes! Are you using Ollama?

https://enoch3712.github.io/ExtractThinker/examples/local-processing/

The llm component uses Litellm under the hood, so if you are using something else, make sure you check the docs:
https://docs.litellm.ai/docs/