blogpost-scaling-test-time-compute

Running

I cannot seem to understand how the compute-optimal line is computed

by vhug - opened 9 days ago

vhug

9 days ago

how is the compute optimal line plotted? which search strategy is used for plotting the green line in the final optimal-scaling graph for Llama 3.1 8B?

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

Tap or paste here to upload images

· Sign up or log in to comment