Dealing with longer context websites?

#13

by salzubi401 - opened Mar 5

Mar 5

I've been trying to use ReaderLM for converting HTML to free-form content (no markdown), however the outputs seem to be chopped off and do not cover the entire website. Any ways to make it deal with the entire website? I've tried increasing max_tokens and context_size with no avail.

arkohut

Mar 15

There are some ways to make it produce longer output, but unfortunately, even when it generates lengthy content, it's accompanied by a lot of hallucinations, and you end up losing the original text.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment