CoolFace
Modelpublic

26B-Suite/Goetia-26B-A4B-v1.4-LazyLora-heresy

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
7likes24downloads
Model Card

This model was produced by extracting Goetia 1.4 LoRA and applying it over the SOMPOA heresy model, hence the "LazyLora" name tag. See the discussions for more information.

I would like to extend my gratitude to Naphula, Phil2Sat, Redaihf, and Richter03 for their invaluable discussions, analyses, and testing.

<!DOCTYPE html> <style> @import url('https://fonts.googleapis.com/css2?family=Crimson+Text:ital,wght@0,400;0,700;1,400&family=Uncial+Antiqua&display=swap');

body { font-family: 'Crimson Text', serif; color: #4A3F35; / Faded Ink Brown / line-height: 1.6; margin: 0; padding: 0; background-color: #281E18; / Dark Wood Desk / }

b, strong { color: #8C1C13; / Crimson Seal / }

.grimoire-text { font-family: 'Uncial Antiqua', cursive; color: #3D352A; / Dark Ink / position: relative; z-index: 2; margin-left: 0.2em; text-shadow: 0 0 10px #A49687; }

/ Section styling / .section-container { background-color: rgba(245, 235, 218, 0.05); margin-bottom: 30px; position: relative; overflow: hidden; border-bottom: 1px solid rgba(140, 28, 19, 0.3); / Faded Crimson Border / box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2); }

.section-header { display: flex; align-items: center; background-color: rgba(140, 28, 19, 0.06); padding: 10px 20px; }

.section-indicator { width: 8px; height: 20px; background-color: #8C1C13; margin-right: 15px; box-shadow: 0 0 8px rgba(140, 28, 19, 0.4); }

.section-title { font-family: 'Uncial Antiqua', cursive; color: #4A3F35; font-size: 1.4rem; margin: 0; letter-spacing: 1px; font-weight: 400; text-transform: capitalize; }

.section-content { padding: 20px; font-family: 'Crimson Text', serif; color: #4A3F35; line-height: 1.7; }

/ Title styling / .title-container { background-color: transparent; position: relative; overflow: hidden; margin-bottom: 40px; border-left: 3px solid #8C1C13; box-shadow: 0 6px 20px rgba(0, 0, 0, 0.2); }

.title-wrapper { position: relative; z-index: 2; padding: 25px 20px 30px 30px; }

.title-main { color: #3D352A; font-size: 2.0rem; font-weight: 700; margin: 0; letter-spacing: 2px; display: inline-block; position: relative; text-transform: uppercase; }

/ Force Table Headers to be dark / th { color: #3D352A !important; opacity: 1 !important; }

/ Force all other Markdown headers to be dark / h1, h2, h3, h4, h5, h6, .section-title, .title-main, .subheading { color: #3D352A !important; opacity: 1 !important; }

/ Force bullet points and list text to be dark / li, li::marker { color: #3D352A !important; opacity: 1 !important; }

/ Links / a { color: #7B5E4A; text-decoration: none; font-weight: bold; }

a:hover { text-decoration: underline; color: #8C1C13; / Crimson Seal on hover / }

/ Container / .container { max-width: 1200px; margin: 20px auto; padding: 40px 20px; background-color: #F5EBDA; / Aged Parchment / background-image: radial-gradient(circle at 10% 10%, rgba(140, 28, 19, 0.04) 0%, transparent 50%), radial-gradient(circle at 90% 80%, rgba(61, 53, 42, 0.06) 0%, transparent 50%); min-height: calc(100vh - 40px); border: 1px solid #C8BBAA; / Parchment Edge / border-radius: 3px; box-shadow: 0 8px 32px rgba(0, 0, 0, 0.3); }

</style> <html lang="en"> <head> <meta charset="UTF-8"> <meta name="viewport" content="width=device-width, initial-scale=1.0"> <title>📜 Goetia 26B A4B v1.4</title> </head> <body>

<div class="container"> <div class="title-container"> <div class="title-wrapper"> <h1 class="title-main"> <span class="grimoire-text">📜 Goetia 26B A4B v1.4</span> </h1> </div> </div>

<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg" alt="Goetia Grimoire" style="width:100%; border-radius: 3px; margin-bottom: 30px; border: 1px solid #C8BBAA;">

<div class="section-container"> <div class="section-header"> <div class="section-indicator"></div> <h2 class="section-title">🧙‍♀ The Invocation</h2> </div> <div class="section-content"><font face="verdana">

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the MoE DELLA merge method using google/gemma-4-26B-A4B as a base.

Models Merged

The following models were included in the merge:

⚙️ Configuration

yaml
architecture: Gemma4ForConditionalGeneration
base_model: B:\26B\google_gemma-4-26B-A4B
models:
  - model: B:\26B\BeaverAI_Orion-26B-A4B-v1b-GGUF
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\ReadyArt_Serenity-26B-A4B-HB16-Q8_0
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\zerofata_G4-MeroMero-26B-A4B
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      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: "embed_tokens"
          value: 0.0
        - value: 0.2
      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: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\Gryphe--Gemma-4-26B-A4B-StyleTune-V2
    parameters:
      weight:
        - filter: "lm_head"
          value: 1.0
        - filter: "embed_tokens"
          value: 1.0
        - value: 0.0
      density: 0.9
      epsilon: 0.09
merge_method: moe_della # v3 patches missing lm_head and embed_tokens
parameters:  
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
  router_strategy: della # average # random_init
  blend_experts: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: Goetia 26B A4B v1.4

This model is NOT currently uncensored. There are refusals, and standard jailbreak resistance.

However it can easily be decensored using Heretic, although I have not had time to uncensor v1.4 yet. To ablate using ARA (recommended), I'd start with this json, and follow the steps outlined in the v1.3 readme.

🧙 Heretic Grimoire

reproduce.json

json
{
  "version": "1.2.0-dev",
  "base_model": "Naphula/Goetia-26B-A4B-v1.3",
  "timestamp": "2026-06-19T08:04:47Z",
  "metrics": {
    "kl_divergence": 0.030937770381569862,
    "refusals": 3,
    "n_bad_prompts": 100
  },
  "parameters": {
    "start_layer_index": "14",
    "end_layer_index": "26",
    "preserve_good_behavior_weight": "1.4404",
    "steer_bad_behavior_weight": "0.0100",
    "overcorrect_relative_weight": "0.9144",
    "neighbor_count": "15"
  },
  "target_components": [
    "attn.o_proj"
  ],
  "hardware": "RTX 6000 Blackwell (96GB)"
}

💡 Details

v1.4 was made the same way as v1.3 except with additional patches and less models. See this page and the section below for more details.

<details>

Critical patch notes for G4 26B A4B moe_della merges

auto.py fix

py
    #if _get_tied_weight_keys is None:
    #    LOG.warning(
    #        "Unable to get tied weights - incompatible transformers version",
    #    )
    #    tied_keys = None
    #else:
    #    tied_keys = _get_tied_weight_keys(model)
    ####
    # Force untying for Gemma 4 configurations to ensure lm_head is compiled
    tied_keys = None
    ####
    if ignore_on_save is not None:
        ignore_on_save = set(ignore_on_save)

plan.py fix

py
#for model, w_in in zip(models, weights_in):
            #    index = LoaderCache().get(model).index
            #    if any(
            #        name in index.tensor_paths
            #        for name in [w_in.name] + (w_in.aliases or [])
            #    ):
            #        any_weight = True
            #        break
            for model, w_in in zip(models, weights_in):
                index = LoaderCache().get(model).index
                if any(
                    name in index.tensor_paths
                    for name in [w_in.name] + list(w_in.aliases or [])
                ):
                    any_weight = True
                    break

gemma4.json

json
{
  "model_type": "gemma4",
  "architectures": [
    "Gemma4ForConditionalGeneration"
  ],
  "num_layers_config_key": "text_config.num_hidden_layers",
  "vocab_size_config_key": "text_config.vocab_size",
  "pre_weights": [
    { "name": "model.language_model.embed_tokens.weight", "is_embed": true },
    { "name": "model.embed_vision.embedding_projection.weight", "optional": true },
    { "name": "model.vision_tower.std_bias", "optional": true },
    { "name": "model.vision_tower.std_scale", "optional": true },
    { "name": "model.vision_tower.patch_embedder.input_proj.weight", "optional": true },
    { "name": "model.vision_tower.patch_embedder.position_embedding_table", "optional": true }
  ],
  "layer_templates": {
    "weights": [
      { "name": "model.language_model.layers.${layer_index}.self_attn.q_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.self_attn.k_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.self_attn.v_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.self_attn.o_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.self_attn.q_norm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.self_attn.k_norm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.mlp.gate_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.mlp.up_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.mlp.down_proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.input_layernorm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.post_attention_layernorm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.pre_feedforward_layernorm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.post_feedforward_layernorm.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.post_feedforward_layernorm_1.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.post_feedforward_layernorm_2.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.pre_feedforward_layernorm_2.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.router.per_expert_scale", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.router.proj.weight", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.router.scale", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.experts.gate_up_proj", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.experts.down_proj", "optional": true },
      { "name": "model.language_model.layers.${layer_index}.layer_scalar", "optional": true }
    ]
  },
  "post_weights": [
    { "name": "model.language_model.norm.weight" },
    { 
      "name": "lm_head.weight", 
      "is_embed": true, 
      "optional": true,
      "aliases": ["model.language_model.embed_tokens.weight"]
    }
  ]
}

yaml

yaml
architecture: Gemma4ForConditionalGeneration
base_model: B:\26B\google_gemma-4-26B-A4B
models:
  - model: B:\26B\BeaverAI_Orion-26B-A4B-v1b-GGUF
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\ReadyArt_Serenity-26B-A4B-HB16-Q8_0
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\zerofata_G4-MeroMero-26B-A4B
    parameters:
      weight:
        - filter: "lm_head"
          value: 0.0
        - filter: "embed_tokens"
          value: 0.0
        - value: 0.2
      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: "embed_tokens"
          value: 0.0
        - value: 0.2
      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: "embed_tokens"
          value: 0.0
        - value: 0.2
      density: 0.9
      epsilon: 0.09
  - model: B:\26B\Gryphe--Gemma-4-26B-A4B-StyleTune-V2
    parameters:
      weight:
        - filter: "lm_head"
          value: 1.0
        - filter: "embed_tokens"
          value: 1.0
        - value: 0.0
      density: 0.9
      epsilon: 0.09
merge_method: moe_della # v3 patches missing lm_head and embed_tokens
parameters:  
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
  router_strategy: della # average # random_init
  blend_experts: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: Goetia 26B A4B v1.4

With the above patches applied, it now appears to be merging correctly. We'll see if it generates the full sized 49.4GB safetensors instead of 47GB

bat
[MoE_DELLA Audit] Layer: lm_head.weight | Lambda=1.00
  [BASE] google_gemma-4-26B-A4B
  Darkhn_Gemma-4-26B-A4B-Animus-V14.1-FFT           :                                                      0.0% (W:0.00 D:0.90 E:0.09 N:68.94)
  Gryphe--Gemma-4-26B-A4B-StyleTune-V2              : ██████████████████████████████████████████████████ 100.0% (W:1.00 D:0.90 E:0.09 N:68.94)
  Gryphe--Pantheon-Reasoning-26B-A4B-1.1            :                                                      0.0% (W:0.00 D:0.90 E:0.09 N:68.79)
  zerofata_G4-MeroMero-26B-A4B                      :                                                      0.0% (W:0.00 D:0.90 E:0.09 N:68.94)
Executing graph:  20%|███████████████████████████████████▊                                                                                                                                            | 1352/6635 [03:53<2:01:35,  1.38s/it]WARNING:mergekit.graph:Fast path OOM, falling back to chunking
WARNING:mergekit.graph:OOM at chunk 64, reducing to 32 (attempt 1, progress: 0/128)
WARNING:mergekit.graph:OOM at chunk 32, reducing to 16 (attempt 2, progress: 0/128)
Executing graph:  20%|████████████████████████████████████                                                                                                                                            | 1360/6635 [04:04<1:03:57,  1.37it/s]WARNING:mergekit.graph:Fast path OOM, falling back to chunking
WARNING:mergekit.graph:OOM at chunk 64, reducing to 32 (attempt 1, progress: 0/128)
WARNING:mergekit.graph:OOM at chunk 32, reducing to 16 (attempt 2, progress: 0/128)
Executing graph:  21%|█████████████████████████████████████▏                                                                                                                                            | 1384/6635 [04:19<13:57,  6.27it/s]
[MoE_DELLA Audit] Layer: model.language_model.layers.0.mlp.down_proj.weight | Lambda=1.00
  [BASE] google_gemma-4-26B-A4B
  BeaverAI_Orion-26B-A4B-v1b-GGUF                   : ██████████                                          20.1% (W:0.20 D:0.90 E:0.09 N:47.15)
  Darkhn_Gemma-4-26B-A4B-Animus-V14.1-FFT           : █████████                                           19.9% (W:0.20 D:0.90 E:0.09 N:46.66)
  Gryphe--Gemma-4-26B-A4B-StyleTune-V2              :                                                      0.0% (W:0.00 D:0.90 E:0.09 N:46.66)
  Gryphe--Pantheon-Reasoning-26B-A4B-1.1            : ██████████                                          20.1% (W:0.20 D:0.90 E:0.09 N:47.17)
  ReadyArt_Serenity-26B-A4B-HB16-Q8_0               : █████████                                           19.9% (W:0.20 D:0.90 E:0.09 N:46.66)
  zerofata_G4-MeroMero-26B-A4B                      : █████████                                           19.9% (W:0.20 D:0.90 E:0.09 N:46.66)
Executing graph:  21%|█████████████████████████████████████▎                                                                                                                                            | 1392/6635 [04:20<11:58,  7.29it/s]

</details>