mradermacher/ShotVL-3B-GGUF
Partial fine-tune (fewer layers) vs Vchitect/ShotVL-3B. mradermacher/ShotVL-3B-GGUF matches part of Vchitect/ShotVL-3B (434 of its 824 tensors; the rest of Vchitect/ShotVL-3B has no counterpart). On the shared part: mradermacher/ShotVL-3B-GGUF is a GGUF (F16) of different weights. Partial change: 90% of the weights changed (attention, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 70/73, MLP 108/108, Attention 251/252