294 lines
7.8 KiB
Markdown
294 lines
7.8 KiB
Markdown
|
|
---
|
||
|
|
base_model:
|
||
|
|
- allura-forge/ms32-final-TEXTONLY
|
||
|
|
- ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
|
||
|
|
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||
|
|
- arcee-ai/Arcee-Blitz
|
||
|
|
- ConicCat/Mistral-Small-3.2-AntiRep-24B
|
||
|
|
- CrucibleLab/M3.2-24B-Loki-V2
|
||
|
|
- DarkArtsForge/Morax-24B-v1
|
||
|
|
- Darkhn/M3.2-24B-Animus-V5.1-Pro
|
||
|
|
- Darkhn/M3.2-24B-Animus-V7.1
|
||
|
|
- Delta-Vector/Rei-24B-KTO
|
||
|
|
- dphn/Dolphin-Mistral-24B-Venice-Edition
|
||
|
|
- Doctor-Shotgun/MS3.2-24B-Magnum-Diamond
|
||
|
|
- FlareRebellion/WeirdCompound-v1.7-24b
|
||
|
|
- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||
|
|
- OddTheGreat/Circuitry_24B_V.3
|
||
|
|
- PocketDoc/Dans-DangerousWinds-V1.1.1-24b
|
||
|
|
- ReadyArt/4.2.0-Broken-Tutu-24b
|
||
|
|
- ReadyArt/Broken-Tutu-24B-Transgression-v2.0
|
||
|
|
- ReadyArt/Dark-Nexus-24B-v2.0
|
||
|
|
- ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
||
|
|
- spacewars123/Space-Wars-24B-v1.00a
|
||
|
|
- TheDrummer/Cydonia-24B-v2
|
||
|
|
- TheDrummer/Cydonia-24B-v4.2.0
|
||
|
|
- TheDrummer/Cydonia-24B-v4.3
|
||
|
|
- TheDrummer/Magidonia-24B-v4.2.0
|
||
|
|
- TheDrummer/Magidonia-24B-v4.3
|
||
|
|
- TheDrummer/Precog-24B-v1
|
||
|
|
- trashpanda-org/MS-24B-Instruct-Mullein-v0
|
||
|
|
- trashpanda-org/MS3.2-24B-Mullein-v2
|
||
|
|
- TroyDoesAI/BlackSheep-24B
|
||
|
|
- Undi95/MistralThinker-v1.1
|
||
|
|
- zerofata/MS3.2-PaintedFantasy-v2-24B
|
||
|
|
- zerofata/MS3.2-PaintedFantasy-v3-24B
|
||
|
|
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-v1.3"
|
||
|
|
output:
|
||
|
|
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg
|
||
|
|
---
|
||
|
|
|
||
|
|
# 📜 Goetia 24B v1.3
|
||
|
|
|
||
|
|

|
||
|
|
|
||
|
|
The "Della Edition" meant to test bridging 2501 and 2503 models. See [this post](https://huggingface.co/Naphula/Goetia-24B-v1.3/discussions/1) and [this other post](https://huggingface.co/Naphula/Q0_Bench/discussions/1?not-for-all-audiences=true#6987717c762f0a45f672e250) for more info.
|
||
|
|
|
||
|
|
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--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||
|
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.05
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.05
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
# - model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
||
|
|
# parameters:
|
||
|
|
# density: 0.8
|
||
|
|
# weight: 0.1
|
||
|
|
# epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.1
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.1
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.1
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\Morax-24B-v1
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--FlareRebellion--WeirdCompound-v1.7-24b
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.1
|
||
|
|
epsilon: 0.1
|
||
|
|
# - model: B:\24B\!models--aixonlab--Eurydice-24b-v3.5
|
||
|
|
# parameters:
|
||
|
|
# density: 0.8
|
||
|
|
# weight: 0.08
|
||
|
|
# epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--allura-forge--ms32-final-TEXTONLY
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--Delta-Vector--Rei-24B-KTO
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--Doctor-Shotgun--MS3.2-24B-Magnum-Diamond
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ReadyArt--MS3.2-The-Omega-Directive-24B-Unslop-v2.1
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
# - model: B:\24B\!models--Gryphe--Codex-24B-Small-3.2
|
||
|
|
# parameters:
|
||
|
|
# density: 0.8
|
||
|
|
# weight: 0.1
|
||
|
|
# epsilon: 0.1
|
||
|
|
# - model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V1.3
|
||
|
|
# parameters:
|
||
|
|
# density: 0.8
|
||
|
|
# weight: 0.15
|
||
|
|
# epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--arcee-ai--Arcee-Blitz
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ArliAI--Mistral-Small-24B-ArliAI-RPMax-v1.4
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
# - model: B:\24B\!models--PocketDoc--Dans-PersonalityEngine-V1.3.0-24b
|
||
|
|
# parameters:
|
||
|
|
# density: 0.8
|
||
|
|
# weight: 0.1
|
||
|
|
# epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--ReadyArt--Dark-Nexus-24B-v2.0
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.2
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V5.1-Pro
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.15
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--dphn--Dolphin-Mistral-24B-Venice-Edition
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.01
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TroyDoesAI--BlackSheep-24B
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.01
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v2
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--PocketDoc--Dans-DangerousWinds-V1.1.1-24b
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--trashpanda-org--MS-24B-Instruct-Mullein-v0
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--OddTheGreat--Circuitry_24B_V.3
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.1
|
||
|
|
epsilon: 0.1
|
||
|
|
- model: B:\24B\!models--spacewars123--Space-Wars-24B-v1.00a
|
||
|
|
parameters:
|
||
|
|
density: 0.8
|
||
|
|
weight: 0.02
|
||
|
|
epsilon: 0.1
|
||
|
|
# Total Donors: 33
|
||
|
|
# Total Weights: 3.3
|
||
|
|
# Seed: 420
|
||
|
|
merge_method: della
|
||
|
|
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||
|
|
parameters:
|
||
|
|
lambda: 1.0
|
||
|
|
normalize: true # key variable to test
|
||
|
|
int8_mask: false
|
||
|
|
dtype: float32
|
||
|
|
out_dtype: bfloat16
|
||
|
|
tokenizer:
|
||
|
|
source: base
|
||
|
|
# chat_template: auto
|
||
|
|
name: 📜 Goetia-24B-v1.3
|
||
|
|
```
|