News for hackers. Stuff that matters.
Re:Qwen2.5-1M: Deploy your own Qwen with context length up t... by nejsjsjsbsb on Monday January 27, 2025 @02:44AM (#42838434)
Isn't input/output lengths an arbitrary distinction. Under the hood, output becomes the input for the next token at each step. OpenAI may charge you more $$ by forcing you to add output to the input and call the API again. But running local you don't have that issue.

There are no comments on this comment yet.