allenai/SAGE-MM-Qwen3-VL-8B-SFT_RL

Partial fine-tune vs allenai/SAGE-MM-Qwen3-VL-8B-SFT. Partial change: 79% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/4, Norms 97/261, MLP 108/232, Attention 144/252, lm_head 0/1

3 derivatives checked

• mradermacher/SAGE-MM-Qwen3-VL-8B-SFT_RL-i1-GGUF: Quantization (fewer layers)
• mradermacher/SAGE-MM-Qwen3-VL-8B-SFT_RL-GGUF: Same weights, converted (fewer layers)
• prithivMLmods/SAGE-MM-Qwen3-VL-8B-SFT_RL-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse