Novaciano/Heretic_Amoral_Abl-Gemma3-1B
LoRA-style vs DavidAU/gemma-3-1b-it-heretic-extreme-uncensored-abliterated. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, v_proj changed, in 26 of 26 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/157, MLP 25/78, Attention 104/104
3 derivatives checked
- mradermacher/Heretic_Amoral_Abl-Gemma3-1B-i1-GGUF: Quantization
- mradermacher/Heretic_Amoral_Abl-Gemma3-1B-GGUF: Same weights, converted
- Novaciano/Gemma3-UNCENSORED-1B: LoRA-style