coder3101/gemma-3-27b-it-heretic
Full fine-tune vs google/gemma-3-27b-pt. Fine-tune: 98% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 1/4, Norms 374/484, MLP 186/294, Attention 248/464, other 1/1
10 derivatives checked
- mradermacher/gemma-3-27b-it-heretic-i1-GGUF: Full fine-tune (fewer layers)
- mradermacher/gemma-3-27b-it-heretic-GGUF: Full fine-tune (fewer layers)
- Justbackup/Gemma-3-27b-it-Uncensored-HERETIC-Gemini-Deep-Reasoning: LoRA-style
- Mimoniske/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking: Full fine-tune
- DavidAU/Gemma3-27B-it-vl-GLM-4.7-Uncensored-Heretic-Deep-Reasoning: LoRA-style
- DavidAU/gemma-3-it-vl-40B-Gemini-Heretic-Uncensored-Thinking: Full fine-tune
- DavidAU/Gemma-3-27b-it-Uncensored-HERETIC-Gemini-Deep-Reasoning: LoRA-style
- DavidAU/Gemma-3-27b-it-Gemini-Heretic-Uncensored-Deeper-Reasoning-Series2: LoRA-style
- DavidAU/Gemma-3-27b-it-vl-SuperBrain7x-High-Reasoning-ULTRAMIND-Heretic-Uncensored: LoRA-style
- DavidAU/Gemma3-27B-it-vl-Polaris-HI16-Heretic-Uncensored-INSTRUCT: LoRA-style