My new model: "Br-T-t2t-CoT-Mini"

#1
by Bertug1911 - opened

Param.(s): 49.5 M
n of Transformer blocks: 6
Number of attention heads: 8
MMLU Score: %22 (GPT-2 = %20-24)
Model link:
Figure_1.png
https://huggingface.co/Bertug1911/Br-T-t2t-CoT-mini/blob/main/README.md

Sign up or log in to comment