from-our-page/llama3.1-8b-refinedbase-checkpoint-5120
Updated
llama3.1-8b-refinedbase v1
continued pretraining of llama3.1 8b on refinedweb for ~80M tokens to try to undo the annealing step and make it act more like an actual base model
Note this is the final checkpoint, more info soon
-
from-our-page/llama3.1-8b-refinedbase-checkpoint-4480
Updated -
from-our-page/llama3.1-8b-refinedbase-checkpoint-3840
Updated -
from-our-page/llama3.1-8b-refinedbase-checkpoint-3200
Updated • 3 -
from-our-page/llama3.1-8b-refinedbase-checkpoint-2560
Updated -
from-our-page/llama3.1-8b-refinedbase-checkpoint-1920
Updated • 1 -
from-our-page/llama3.1-8b-refinedbase-checkpoint-1280
Updated -
from-our-page/llama3.1-8b-refinedbase-checkpoint-640
Updated • 2