search

OpenBMB / ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.
https://ollama.com
MIT License
11 stars 5 forks source link

CPM support function calling ability? #9

Closed yhyu13 closed 3 weeks ago

yhyu13 commented 1 month ago

Hi,

Would you like to create a model with Visual function calling abilities (like corping images, indexing items, so on and so forth) beyond visual QA?

Thanks!

tc-mb commented 1 month ago

Hi,

Would you like to create a model with Visual function calling abilities (like corping images, indexing items, so on and so forth) beyond visual QA?

Thanks!

Thank you for your question, we are very concerned about this kind of capabilities, and believe that this is also the direction of the development of multimodal models, but I am not sure when these features will really work.