How is it free to use llama even if we use the smaller model? What are the limitations?
@aiarcadecode15 күн бұрын
Well I guess the limits are imposed by the api providers in this case. For the smaller 70b model groq lists these limits. Groq doesn't have a paid tier yet. Requests per Minute 100 Requests per Day 14,400 Tokens per Minute 131,072 Tokens per Day 1,000,000 For the 405B, both Together.ai and Fireworks.ai have limited free tier as well as a paid tier.
@gshock148515 күн бұрын
@@aiarcadecode oh thanks for this. That's great
@coollad49Ай бұрын
thanks for this..
@aiarcadecodeАй бұрын
You're most welcome!
@inasal-qamaji7930Ай бұрын
Thank you for this video, I do all steps, then I upload to github repo, then I want to use AWS as hostinng with amplifier, but after I deploy give me the link I see the page but without any response ?
@aiarcadecodeАй бұрын
Not sure mate. Can you try checking the AWS console to see what error is being thrown?
@inasal-qamaji7930Ай бұрын
@@aiarcadecode thank you, I hope you make a video for that.