sensenova/SenseNova-SI-1.3-Qwen3-VL-8B
Partial fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Partial change: 86% of the weights changed (attention, embeddings, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 3/4, Norms 152/261, MLP 211/232, Attention 252/252, lm_head 0/1
2 derivatives checked
- mradermacher/SenseNova-SI-1.3-Qwen3-VL-8B-GGUF: Same weights, converted (fewer layers)
- mradermacher/SenseNova-SI-1.3-Qwen3-VL-8B-i1-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.