Chat (OctoAI - gemma-7b-it)
POST https://text.octoai.run/v1/chat/completions
Request Body
{"messages"=>[{"role"=>"user", "content"=>"Explain the importance of low latency LLMs"}], "model"=>"gemma-7b-it", "temperature"=>0.5, "max_tokens"=>1024, "top_p"=>1, "stream"=>true, "stop"=>nil}