aisingapore/Qwen-SEA-Guard-8B-2602
Partial fine-tune vs aisingapore/Qwen-SEA-LION-v4-8B-VL. Partial change: 86% of the weights changed (attention, lm_head, mlp, norms), in 36 of 36 layers.
Tensors changed: Embeddings 0/4, Norms 127/261, MLP 108/232, Attention 144/252, lm_head 1/1
2 derivatives checked
- mradermacher/Qwen-SEA-Guard-8B-2602-i1-GGUF: Quantization (fewer layers)
- mradermacher/Qwen-SEA-Guard-8B-2602-GGUF: Same weights, converted (fewer layers)