GitMylo/nsfwvision-v4_qwen3.5-9b-sft
Full fine-tune vs Qwen/Qwen3.5-9B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 3/5, MLP 156/211, Attention 265/336, other 1/1, Norms 113/221
2 derivatives checked
- mradermacher/nsfwvision-v4_qwen3.5-9b-sft-i1-GGUF: Quantization
- mradermacher/nsfwvision-v4_qwen3.5-9b-sft-GGUF: Same weights, converted