llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic
LoRA-style vs llmfan46/gemma-4-31B-it-uncensored-heretic. 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 49 of 60 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/523, other 0/62, MLP 145/261, Attention 184/338
8 derivatives checked
- llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF: Same weights, converted (fewer layers)
- mradermacher/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-GGUF: Quantization (fewer layers)
- llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-NVFP4-GGUF: Quantization
- llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-NVFP4: Quantization
- McG-221/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-mlx-8Bit: Quantization
- cookietimeh/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-mlx-8Bit: Quantization
- MRockatansky/Gemma-4-31B-Storymaxxed3: LoRA-style