anlp-a2-part2-sophia

Dense decoder-only transformer pretrained from scratch on browndw/human-ai-parallel-corpus (1x the training split) with a from-scratch sophia optimizer.

Load with src.part2.model.Transformer.from_pretrained("DunkRonit/anlp-a2-part2-sophia") from the assignment repo.

Downloads last month
22
Safetensors
Model size
17M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support