allenai/SAGE-MM-Qwen2.5-VL-7B-SFT_RL
Partial fine-tune vs allenai/SAGE-MM-Qwen2.5-VL-7B-SFT. Partial change: 78% of the weights changed (attention, mlp, norms), in 28 of 32 layers.
Tensors changed: Embeddings 0/2, Norms 52/122, MLP 83/280, Attention 196/324, lm_head 0/1
3 derivatives checked
- mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-i1-GGUF: Quantization (fewer layers)
- mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF: Same weights, converted (fewer layers)