DavidAU/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored
LoRA-style vs DreamFast/gemma-3-12b-it-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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/400, MLP 144/252, Attention 192/408, other 0/1
4 derivatives checked
- mradermacher/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-i1-GGUF: Quantization (fewer layers)
- McG-221/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-mlx-8Bit: Quantization
- mradermacher/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-GGUF: Quantization (fewer layers)
- Markobes/gemma-3-12b-it-vl-Polaris-GLM-4.7-Flash-VAR-Thinking-Instruct-Heretic-Uncensored-Q8_0-GGUF: Quantization (fewer layers)