Mungert/SmolDocling-256M-preview-GGUF
Full fine-tune (fewer layers) vs HuggingFaceTB/SmolVLM-256M-Instruct. Mungert/SmolDocling-256M-preview-GGUF matches part of HuggingFaceTB/SmolVLM-256M-Instruct (273 of its 471 tensors; the rest of HuggingFaceTB/SmolVLM-256M-Instruct has no counterpart). On the shared part: Mungert/SmolDocling-256M-preview-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 61/61, MLP 90/90, Attention 120/120