Create README.md

README.md

@@ -0,0 +1,144 @@
+---
+base_model:
+- Darkhn/Magistral-2509-24B-Text-Only
+- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
+- Naphula/Slimaki-24B-v1
+- Casual-Autopsy/Maginum-Cydoms-24B
+- sophosympatheia/Magistry-24B-v1.0
+- DarkArtsForge/Morbid-Miasma-24B
+- mradermacher/BlackXorDolphTronGOAT-GGUF
+datasets:
+- OccultAI/illuminati_imatrix_v1
+language:
+- en
+library_name: transformers
+license: apache-2.0
+tags:
+- creative
+- creative writing
+- fiction writing
+- plot generation
+- sub-plot generation
+- fiction writing
+- story generation
+- scene continue
+- storytelling
+- fiction story
+- science fiction
+- romance
+- all genres
+- story
+- writing
+- vivid prosing
+- vivid writing
+- fiction
+- roleplaying
+- float32
+- swearing
+- rp
+- horror
+- della
+- mistral
+- merge
+- mergekit
+widget:
+  - text: "Goetia-24B-v1.4"
+    output:
+      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pRbM2-CstiKSNSOGjM4zO.png
+---
+
+<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/KcjosKamYjk9Qm18mAGQW.mpga"></audio>
+
+> [!CAUTION]
+> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **Mistral Tekken** chat template.
+>
+
+# 📜 Goetia 24B v1.4
+
+![Goetia_Claude](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pRbM2-CstiKSNSOGjM4zO.png)
+
+# COMING SOON
+
+**This model is queued to be uploaded by: ETA August 14th**
+
+This version of Goetia took **dozens of merges** to get right over the past few months, but has finally reached what appears to be a bug-free checkpoint, which I'm calling T75 since I actually lost count.
+
+The original prototype [Checkpoint T13](https://huggingface.co/Naphula-Archives/T13-24B-GGUF) had used Precog with density 1.0, which caused issues where the model would try to think, but forget to use `<think>` tags, which caused early terminations after the first paragraph.
+
+Many different settings were tested, and each produced inferior results—until I tried swapping Precog with Morbid Miasma. Higher magnitudes like 1.8 or 2.0 resulted in blowout. Lower magnitudes, even 1.5 resulted in refusals. 1.6 was the ideal combination after testing numerous models and weight configurations.
+
+The model writes with a cold, unique style ("That's a wonderfully depraved goal. Let's get straight to the bloody art of it, shall we?"). It is just as dark as Morbid Miasma, and in some ways even more creative. For Q0 benchmark it literally wrote a scene like something you would expect from a Stephen King novel. Minimal slop was detected.
+
+As usual, I did not test extensively for multi-shot stability or context retention, but I ran a full Compliance bench sweep to check for thinking bugs and did not encounter any.
+Key changes from Checkpoint T13:
+- Precog was swapped out with Morbid Miasma 24B. This fixes the missing `<think>` tag, meaning the model no longer exhibits early terminations.
+- Slimaki and Fallen Mistral were increased from 0.2 to 0.25 weight, which solved the trace refusals.
+- BlackXorDolphTronGoat was initially removed but then re-added, it seems to help ground the output more coherently.
+
+**The result is an exceptionally intelligent, uncensored, and creative model which accurately adheres to instructions.** It was merged just below the "magnitude ceiling" where it would start to sound more like T7 and get carried away with off-topic dialogue/metaphors. Instead, it remains on point, displaying a much higher capacity for extensive graphic violence than Gemma 4. None of the formatting bugs seen with Nemo 12B were observed here.
+
+The Q0 Bench score for Goetia 24B v1.4 is
+
+| **Goetia v1.4 (CP T75)** | 15485 | Q8_0 | Pass | 0/100 | Strappado |
+
+It works with ChatML but scored even higher with Mistral Tekken.
+
+---
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Methods
+
+This model was merged using the following merge method:
+- [DELLA](https://arxiv.org/abs/2406.11617)
+
+```yaml
+architecture: MistralForCausalLM
+models:
+  - model: B:\24B\!models--Darkhn--Magistral-2509-24B-Text-Only
+  - model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
+    parameters:
+      weight: 0.25
+      density: 0.75
+      epsilon: 0.25
+  - model: B:\24B\Naphula--Slimaki-24B-v1
+    parameters:
+      weight: 0.25
+      density: 0.75
+      epsilon: 0.25
+  - model: B:\24B\!models--Casual-Autopsy--Maginum-Cydoms-24B
+    parameters:
+      weight: 0.2
+      density: 0.5
+      epsilon: 0.25
+  - model: B:\24B\sophosympatheia--Magistry-24B-v1.0
+    parameters:
+      weight: 0.2
+      density: 0.5
+      epsilon: 0.25
+  - model: B:\24B\DarkArtsForge--Morbid-Miasma-24B
+    parameters:
+      weight: 0.6
+      density: 1.0
+      epsilon: 0.0
+  - model: B:\24B\!models--mradermacher--BlackXorDolphTronGOAT-GGUF
+    parameters:
+      weight: 0.1
+      density: 0.5
+      epsilon: 0.25
+merge_method: della
+base_model: B:\24B\!models--Darkhn--Magistral-2509-24B-Text-Only
+parameters:
+  lambda: 1.0
+  normalize: false
+  int8_mask: false
+  rescale: true
+  seed: 420
+tokenizer:
+  source: union
+chat_template: auto
+dtype: float32
+out_dtype: bfloat16
+name: 📜 Goetia 24B v1.4
+```