Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: IncarnaMind-Chat with your multiple docs using LLMs. Parent comment
Goes from 20 tokens per second to 15 tokens per second nearing the ~3k token context length, with similar quality in output to chatgpt 3.5.
There are no comments on this comment yet.
Goes from 20 tokens per second to 15 tokens per second nearing the ~3k token context length, with similar quality in output to chatgpt 3.5.