avianion

Is this fixed? How to we go about sending a custom HTML email? ``` email_message = self.email_message( user, self.invitation_subject, self.invitation_body, sender, **kwargs ) ``` Where "invitation_body" here is a custom...

@HamidShojanazeri I just want to know if function / tool calling is on the native pipeline. As we've already built our own finetune with that, but it would be easier...

Yep you're right! It does! Would be nice to have a more formal, polished fine tune though. I think that and long context are on everyones radar in the OSS...

Yes, in terms of long context, there are some rope theta possibilities as well as the above algorithm, but of course an official long context model from Meta would be...

@HamidShojanazeri https://docs.mistral.ai/capabilities/function_calling/ SOmething like this would be real nice.

@Apezdr are you using --turbo here?

Did you end up fixing this @adrianocr Full working code would be appreciated.

"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '' + message['role'] + '\n\n'+ message['content'] | trim + '' %}{% if loop.index0 == 0...

ok great. @npuichigo but what is the model name? it keeps saying to me model not found and i have tried many model names. with llama 3 70b

Should skip_special_tokens be True or False? and same with add_special_tokens in the preprocessing config.pbtxt?