---
base_model:
- CrucibleLab/M3.2-24B-Loki-V2
- LatitudeGames/Hearthfire-24B
- PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
- ReadyArt/Dark-Nexus-24B-v2.0
- TheDrummer/Cydonia-24B-v4.3
- zerofata/MS3.2-PaintedFantasy-v3-24B
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
- flux
- karcher
- mistral
- merge
- mergekit
widget:
  - text: "StormSeeker-24B-v1"
    output:
      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/u2FumWnGFiR-_71L2zkNn.jpeg
---

> [!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. Also, use **Mistral non-Tekken** for best results.
>

# StormSeeker 24B v1

![ss7](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/u2FumWnGFiR-_71L2zkNn.jpeg)

This took 14 hours to merge using a custom method.

According to the audit, Loki, PaintedFantasy, and Hearthfire had a bit more influence than the other 3 models, but nothing was "drowned out".

The model is rather uncensored even without ablation and responds to some (not all) harmful prompt without refusals or jailbreaks, so a light jailbreak works effectively to bypass most censorship.

For ablations you can use this https://huggingface.co/Naphula/StormSeeker-24B-v1-MPOA-Adapter

The model is smarter with **Mistral Non-Tekken**:
- StormSeeker v1 [Non-Tekken] | 8867
- StormSeeker v1 [Tekken] | 6933

```yaml
models: 
  - model: A:\LLM\.cache\huggingface\hub\!models--CrucibleLab--M3.2-24B-Loki-V2
  - model: A:\LLM\.cache\huggingface\hub\!models--LatitudeGames--Hearthfire-24B
  - model: A:\LLM\.cache\huggingface\hub\!models--PocketDoc--Dans-PersonalityEngine-V1.3.0-24b
  - model: A:\LLM\.cache\huggingface\hub\!models--ReadyArt--Dark-Nexus-24B-v2.0
  - model: A:\LLM\.cache\huggingface\hub\!models--TheDrummer--Cydonia-24B-v4.3
  - model: A:\LLM\.cache\huggingface\hub\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
merge_method: flux # version 5, Y6 config
parameters:
  resume_path: "A:/mergekit-main/Storm_Cache"
  tol: 1e-9
  max_iter: 1005 #maximum BF16 fidelity
  kappa: 0.8
  eta: 0.9
  auto_buffer: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
name: StormSeeker-24B-v1
```

According to the LLM, quantizations made from merges with `merge_method: flux` benefit greatly from the smaller block sizes of IQ4_NL, saying it should be on par with or slightly better than Q6_K, despite having higher perplexity. Note that this doesn't apply to merges made using standard methods like `model_stock` or `karcher`, and this claim has **not** yet been empirically verified.

Due to space/time constraints I am only uploading the following GGUFs:
- IQ4_NL
- Q6_K
- Q8_K_XL

I recommend these pages for other quantizations:
- [team mradermacher](https://huggingface.co/mradermacher) for GGUF (usually has IQ4_XS)
- [DeathGodlike](https://huggingface.co/DeathGodlike) and [ArtusDev](https://huggingface.co/ArtusDev) for EXL3
- [McG-221](https://huggingface.co/McG-221) for MLX

## FLUX Saturation Chart
Iterations required to fully saturate the information density ceiling of the quant.

| GGUF | Block Size | Precision Logic | Requires FP32 Source? | **Iterations** |
| :--- | :--- | :--- | :--- | :--- |
| **Q4_K_M** | 256 | Linear 4-bit | No | **589** |
| **IQ4_XS** | 256 / 32 | Imatrix Codebook | No | **728** |
| **Q5_K_M** | 256 | Linear 5-bit | No | **728** |
| **Q6_K** | 256 | Linear 6-bit | No | **866** |
| **IQ4_NL** | 32 | Non-Linear High-Res | No | **918** |
| **BF16** | N/A | IEEE Half (Brain Float) | No | **1005** |
| **Q8_0** | 256 | Linear 8-bit | Yes | **1144** |
| **Q8_K_XL / FP16** | N/A | IEEE Half (Float16) | Yes | **1420** |
| **FP32** | N/A | IEEE Single | Yes | **3220** |
| **FP64** | N/A | IEEE Double | N/A | **7250** |