oldhag88/qwen3.5-9b-nsfw-captioning-v2
Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 78% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 153/208, Attention 206/332, Norms 1/215
2 derivatives checked
- mradermacher/qwen3.5-9b-nsfw-captioning-v2-GGUF: Same weights, converted
- mradermacher/qwen3.5-9b-nsfw-captioning-v2-i1-GGUF: Quantization