adamm-hf/Qwen3.5-4B-NSFW-Literotica
LoRA-style (fewer layers) vs MuXodious/Qwen3.5-4B-ARA-heresy-v2. adamm-hf/Qwen3.5-4B-NSFW-Literotica matches part of MuXodious/Qwen3.5-4B-ARA-heresy-v2 (426 of its 723 tensors; the rest of MuXodious/Qwen3.5-4B-ARA-heresy-v2 has no counterpart). On the shared part: 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: Embeddings 0/1, Norms 0/105, Attention 32/224, MLP 96/96
2 derivatives checked
- mradermacher/Qwen3.5-4B-NSFW-Literotica-GGUF: Same weights, converted
- mradermacher/Qwen3.5-4B-NSFW-Literotica-i1-GGUF: Quantization