allenai/SAGE-MM-Qwen3-VL-8B-SFT
Partial fine-tune vs Qwen/Qwen3-VL-8B-Instruct. Partial change: 86% of the weights changed (attention, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/4, Norms 131/261, MLP 108/232, Attention 144/252, lm_head 1/1
4 derivatives checked
- mradermacher/SAGE-MM-Qwen3-VL-8B-SFT-i1-GGUF: Quantization (fewer layers)
- mradermacher/SAGE-MM-Qwen3-VL-8B-SFT-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/SAGE-MM-Qwen3-VL-8B-SFT-GGUF: Same weights, converted (fewer layers)
- allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL: Partial fine-tune