Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Pre-training Resource Utilization on C4

12.55Model Weights Share

Full params

11.922512.2362512.5512.86375Mar 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
12.5512.5525.114.6664.86
2026.03
12.5512.551.734.431.23
2026.03
12.5512.551.734.431.23
2026.03
12.551.242.483.2919.56
2026.03
12.551.242.483.2919.56