Novaciano/Gemma3-UNCENSORED-V2-1B
LoRA-style vs Novaciano/Gemma3-UNCENSORED-1B. 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 103/104
4 derivatives checked
- mradermacher/Gemma3-UNCENSORED-V2-1B-i1-GGUF: Quantization
- mradermacher/Gemma3-UNCENSORED-V2-1B-GGUF: Same weights, converted
- UmbrellaInc/Parasite.NE-Alpha-1B: LoRA-style
- Novaciano/Gemma3-Omen-1B: LoRA-style