DGDGDG12/Qwen3.5-text-9B-NSFW-RP-RolePlay
LoRA-style vs techwithsergiu/Qwen3.5-text-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, MLP 96/96, Attention 32/224, Norms 0/105
5 derivatives checked
- mradermacher/Qwen3.5-text-9B-NSFW-RP-RolePlay-i1-GGUF: Quantization
- mradermacher/Qwen3.5-text-9B-NSFW-RP-RolePlay-GGUF: Same weights, converted
- DGDGDG12/Qwen3.5-text-9B-NSFW-RP-RolePlay-GGUF: Quantization
- mradermacher/Qwen3.5-9B-RolePlay-Merged-i1-GGUF: Quantization
- mradermacher/Qwen3.5-9B-RolePlay-Merged-GGUF: Same weights, converted