tap a token to focus every view on it
Eight tokens, three distinct words. Note the first "red" has no leading space and gets a different id from the later ones.
This view needs the model. In v1 it is precomputed for the preset prompts – pick one from the strip above. The tokeniser stays live for anything you type.
This view needs the model. In v1 it is precomputed for the preset prompts – pick one from the strip above. The tokeniser stays live for anything you type.
This view needs the model. In v1 it is precomputed for the preset prompts – pick one from the strip above. The tokeniser stays live for anything you type.