Adun

/

typhoon_ocr-7b-v1.2

like 0

Hi Adun,

I'm really impressed by your fine-tuned Adun/typhoon_ocr-7b-v1.2. I am currently conducting pipeline for Thai app.

I would love to gain more insights into your training procedure:

Version Iteration: Regarding the relationship among typhoon_ocr-7b and typhoon_ocr-7b-v1.2, were they fine-tuned independently from the same base model, or were they developed sequentially (i.e., V1.2 is a further fine-tune of typhoon_ocr-7b)?

Your insights would be invaluable for my research. We can discuss here, or if you prefer a more detailed technical exchange, I’d be happy to follow up via email.

Thanks for your great contribution to the community!