katafiek/Katarau-9B-ru-RP-nsfw
Partial fine-tune (fewer layers) vs Qwen/Qwen3.5-9B. katafiek/Katarau-9B-ru-RP-nsfw matches part of Qwen/Qwen3.5-9B (427 of its 775 tensors; the rest of Qwen/Qwen3.5-9B has no counterpart). On the shared part: Partial change: 77% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 96/96, Attention 152/224, Norms 24/105
3 derivatives checked
- mradermacher/Katarau-9B-ru-RP-nsfw-GGUF: Same weights, converted
- mradermacher/Katarau-9B-ru-RP-nsfw-i1-GGUF: Quantization
- katafiek/Katarau-9B-ru-RP-nsfw-GGUF: Quantization