DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored
Full fine-tune vs DreamFast/gemma-3-12b-it-heretic. Fine-tune: 97% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/4, Norms 0/400, MLP 144/252, Attention 192/408, other 0/1
2 derivatives checked
- mradermacher/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-3-12b-it-vl-GLM-4.7-Flash-INSTRUCT-Thinking-Hybrid-Heretic-Uncensored-GGUF: Quantization (fewer layers)
1 other repos hold byte-for-byte identical weight files.