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:
https://huggingface.co/Bertug1911/Br-T-t2t-CoT-mini/blob/main/README.md