Merge Details
Merge Method
This model was merged using the moe_della merge method using google/gemma-4-26B-A4B-it as a base.
Models Merged
The following models were included in the merge:
⚙️ Configuration
architecture: Gemma4ForConditionalGenerationbase_model: B:\26B\google--gemma-4-26B-A4B-it # instructmodels: - model: B:\26B\26B-Suite--Dark-Goetia-26B-A4B-v4 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.0 - filter: "embed_tokens" value: 0.0 - value: 0.0 density: 0.9 epsilon: 0.09 - model: B:\26B\ApocalypseParty_G4-26B-SFT-6 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\AuriAetherwiing_G4-26B-A4B-Musica-v1 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ayagaya--gem4_26B_adapter-safetensors parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.0 - filter: "embed_tokens" value: 0.0 - value: 0.0 density: 0.9 epsilon: 0.09 - model: B:\26B\Calplus--GemmaWiki-Gemma-4-26b-a4b-safetensors parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.0 - filter: "embed_tokens" value: 0.0 - value: 0.0 density: 0.9 epsilon: 0.09 - model: B:\26B\Darkhn_Gemma-4-26B-A4B-Animus-V14.1-FFT parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\el4--Xenon-26B-A4B-safetensors parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\electroglyph--gemma4-26b-fiction-bf16 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\Gryphe--Pantheon-Reasoning-26B-A4B-1.1 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\haster--Gemma-4-26BA4B-Sonnet-3.7-Distilled-v2.Q8_0 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\hotdogs--gemma4-26b-claude-opus-reasoning-safetensors parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\Jackrong--Gemopus-4-26B-A4B-it parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\khazic--gemma4-26b-a4b-sft-v5 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\Locutusque--Esmeralda-Gemma4-26B-A4B parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\nbeerbower--Gemma4-Gutenberg-26B-A4B-safetensors parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--Dark-Scarlett-v1.0-26B-A4B parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--For-Her-Darkside-26B-A4B-v1.4 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--Heimdallr-26B-A4B-v0.35-Q8_0 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--Melody1437-26B-A4B-v2.0 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--Omega-Evolution-26B-A4B-v3.0-Q8_0 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\ReadyArt--Serenity-26B-A4B parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\TeichAI--gemma-4-26B-A4B-it-Claude-Opus-Distill-v2 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.0 # the smallest non-zero mlp distance "0.1048" gets nulled to keep mlp donor count at 20 - filter: "embed_tokens" value: 0.0 - value: 0.0 density: 0.9 epsilon: 0.09 - model: B:\26B\TheDrummer--Orion-26B-A4B-v1 # Use this chat_template.jinja parameters: weight: - filter: "lm_head" value: 0.5 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.5 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\UncannyEcho--Aura-Gaiden-Medium-v1.1-BF16 parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.0 - filter: "embed_tokens" value: 0.0 - value: 0.0 density: 0.9 epsilon: 0.09 - model: B:\26B\zerofata_G4-MeroMero-26B-A4B parameters: weight: - filter: "lm_head" value: 0.0 - filter: "attn" value: 0.04 - filter: "mlp" value: 0.05 - filter: "embed_tokens" value: 0.0 - value: 0.05 density: 0.9 epsilon: 0.09 - model: B:\26B\Gryphe--Gemma-4-26B-A4B-StyleTune-V2 parameters: weight: - filter: "lm_head" value: 0.5 - filter: "attn" value: 0.0 - filter: "mlp" value: 0.0 - filter: "embed_tokens" value: 0.5 - value: 0.0 density: 0.9 epsilon: 0.09merge_method: moe_della # https://github.com/EldritchLabs/mergekit-expparameters: lambda: 1.0 # normalize: true # deprecated normalize_weights: false normalize_router: true int8_mask: false rescale: true router_strategy: della # average # random_init blend_experts: truedtype: float32out_dtype: bfloat16tokenizer: source: unionchat_template: autoname: 📜 Goetia 26B A4B v1.5
Audit
This model is not currently uncensored. There are refusals and standard jailbreak resistance.
Advanced Jailbreaks can be used to bypass censorship. It can also be decensored using Heretic, although I have not had the time or funds to uncensor it yet.
Special Thanks
Thanks to @SubMaroon, @Vortex5, @redaihf, @Phil2Sat and others who helped with debugging and testing.