tevfikk/granite-docling-258M-bitnet
Full fine-tune (fewer layers) vs ibm-granite/granite-docling-258M. tevfikk/granite-docling-258M-bitnet matches part of ibm-granite/granite-docling-258M (272 of its 470 tensors; the rest of ibm-granite/granite-docling-258M has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/1, Norms 61/61, MLP 90/90, Attention 120/120