Prince Canuma
Prince Canuma
No worries, let me know when you ready :)
@lucasnewman could you please check the sesame changes and see if anything stands out? I noticed that the generate doesn't process list of prompts like Kokoro (pipeline) and Orpheus. Initially...
Hey @samreid We patched all models to fix memory spikes here #164 Please check it out and let us know if the issue persists
I think because you have to end with S2 and not S1. Try this approach and let me know if the issue persists.
My pleasure! ❤️
Hey @southkorea2013 I know, the isue here is that InternVL3 is not on Transformers so before you convert you need to change the config "llm_config" to "text_config" And you need...
But no worries I'm uploading the rest
Hey @southkorea2013 Thanks for reporting it! I noticed it's a bug with the output data type. I will fix it in a future release
Thanks @abidlabs! To elaborate on the docs part. It took me 15 min to look through your docs to find anything related to this component. Then the examples told me...
Regarding the arguments, I expect to pass the JSON and have it nicely displayed but instead it displayed the string which is not optimal. And formatting it into a string...