mradermacher/Zero-To-CAD-Qwen3-VL-2B-GGUF
Full fine-tune (fewer layers) vs ADSKAILab/Zero-To-CAD-Qwen3-VL-2B. mradermacher/Zero-To-CAD-Qwen3-VL-2B-GGUF matches part of ADSKAILab/Zero-To-CAD-Qwen3-VL-2B (310 of its 625 tensors; the rest of ADSKAILab/Zero-To-CAD-Qwen3-VL-2B has no counterpart). On the shared part: mradermacher/Zero-To-CAD-Qwen3-VL-2B-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 100/113, MLP 84/84, Attention 112/112