Files
Ostblock-12B/README.md

83 lines
2.2 KiB
Markdown
Raw Permalink Normal View History

---
license: apache-2.0
language:
- en
base_model:
- dphn/dolphin-2.9.3-mistral-nemo-12b
- XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2
- WokeAI/Tankie-DPE-12B-SFT-v2
library_name: transformers
tags:
- merge
- mergekit
- roleplay
- creative-writing
---
# OSTBLOCK · 12B
![DARE](https://img.shields.io/badge/Merge-DARE--TIES-8b0000)
![Base](https://img.shields.io/badge/Base-Dolphin%3A12B-1d6fa5)
![Persona](https://img.shields.io/badge/Persona-Helcyon%3A12B-7b2d8b)
![Ideology](https://img.shields.io/badge/Ideology-Tankie%3A12B-c41217)
![Size](https://img.shields.io/badge/Size-12B-555555)
![Status](https://img.shields.io/badge/Status-Unstable-e07b39)
---
![ostblock-12b_small](https://cdn-uploads.huggingface.co/production/uploads/69612b958b0bef761b13d3cf/d8aijax3H42vYPwU56s4T.png)
Don't be fooled by a fancy model card!
> Dolphin with two foreign brain lobes and an open fuse box
---
> “Fuck yes!” She pumps one fist in solidarity. “Thats right, comrade! Age is nothing but a number unless you let them make it feel like a prison.”
> **Ostblock-12B**
---
## Settings
Use Mistral v3-Tekken.
---
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [dphn/dolphin-2.9.3-mistral-nemo-12b](https://huggingface.co/dphn/dolphin-2.9.3-mistral-nemo-12b) as a base.
### Models Merged
The following models were included in the merge:
* [XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2](https://huggingface.co/XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2)
* [WokeAI/Tankie-DPE-12B-SFT-v2](https://huggingface.co/WokeAI/Tankie-DPE-12B-SFT-v2)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: dphn/dolphin-2.9.3-mistral-nemo-12b
parameters:
weight: 1.0
density: 1.0
- model: XeyonAI/Mistral-Helcyon-Mercury-12b-v3.2
parameters:
weight: 0.4
density: 0.6
- model: WokeAI/Tankie-DPE-12B-SFT-v2
parameters:
weight: 0.4
density: 0.55
merge_method: dare_ties
base_model: dphn/dolphin-2.9.3-mistral-nemo-12b
dtype: bfloat16
tokenizer_source: base
```