Diffusion Large Language Models with a SOTA Accuracy–Parallelism Trade-off
-
SJTU-DENG-Lab/LightningRL-8B-b32-GSM8K
Text Generation • 8B • Updated • 56 -
SJTU-DENG-Lab/LightningRL-8B-b32-MATH500
Text Generation • 8B • Updated • 23 -
SJTU-DENG-Lab/LightningRL-8B-b32-MBPP
Text Generation • 8B • Updated • 21 -
SJTU-DENG-Lab/LightningRL-8B-b32-HumanEval
Text Generation • 8B • Updated • 18