This is a visualization of a finetuned LLaMA LLM model solving an ARC-AGI problem. Utilizing the code from the arc prize 2024 winners, where the LLM is used in conjunction with a Depth-first search tree to explore possibilities ordinary sampling would miss. A lower score means the LLM is more certain, if adding the next possible token would make the score go over ~2.2 then that route is no longer valid. Notice how the tree branches at point where the LLM has to make a colour decision.

DFS Tree View

Training Examples

Test Example

Loading DFS tree data...
Hover over boxes to preview tokens, click to add them to the grid. Single-choice tokens will be automatically selected on hover.

Current Grid

Hover over any node to preview its grid state. Click a node to jump to that point in the sequence.