mradermacher/NaviDrive-Qwen3-VL-2B-SFT-GGUF

Partial fine-tune (fewer layers) vs Ximeng0831/NaviDrive-Qwen3-VL-2B-SFT. mradermacher/NaviDrive-Qwen3-VL-2B-SFT-GGUF matches part of Ximeng0831/NaviDrive-Qwen3-VL-2B-SFT (310 of its 625 tensors; the rest of Ximeng0831/NaviDrive-Qwen3-VL-2B-SFT has no counterpart). On the shared part: mradermacher/NaviDrive-Qwen3-VL-2B-SFT-GGUF is a GGUF (F16) of different weights. Partial change: 82% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 80/113, MLP 84/84, Attention 112/112

On the Hub · Downloads on Model Pulse