MarcGrumpyOlejak's picture
Update README.md
4bbd25f verified
|
raw
history blame
No virus
3.42 kB
---
base_model:
- hiig-piai/simba-01d-ftb
- DRXD1000/Phoenix
- OpenPipe/mistral-ft-optimized-1227
- mistralai/Mistral-7B-v0.1
- VAGOsolutions/SauerkrautLM-7b-LaserChat
library_name: transformers
tags:
- mergekit
- merge
---
# VerwaltungsAnthologie_clear_simbad_7B
This model is used as an intermediate model for future merges.
This is a merge of 4 pre-trained language models based upon Mistral-7B-v0.1 created using [mergekit](https://github.com/cg123/mergekit).
In combination with [DiscoLM_German_7b_v1](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1) this 'clear'-model is the 'base' model to build the successor of my first 'VA_Disco_7B': [VerwaltungsAnthologie_Disco_7B](https://huggingface.co/MarcGrumpyOlejak/VerwaltungsAnthologie_Disco_7B)
## Merge Details
### Merge Method
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [hiig-piai/simba-01d-ftb](https://huggingface.co/hiig-piai/simba-01d-ftb)
* [DRXD1000/Phoenix](https://huggingface.co/DRXD1000/Phoenix)
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227)
* [VAGOsolutions/SauerkrautLM-7b-LaserChat](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-LaserChat)
### Explanations of used models
* Main focus of this "clear" model is the [hiig-piai/simba-01d](https://huggingface.co/hiig-piai/simba-01d-ftb) (strangley without a 'v') by the Humboldt Institute for Internet and Society has built this model for "simplified language" (Leichte Sprache in german).
* The [DRXD1000/Phoenix](https://huggingface.co/DRXD1000/Phoenix) got finetuned with many german texts of law – it can even "hallucinate" almost perfect URL of the official archive of german laws: [Gesetze im Internet]](https://www.gesetze-im-internet.de/)
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) performed best using mixed languages in combination with [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as base model.
* [VAGOsolutions/SauerkrautLM-7b-LaserChat](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-LaserChat) has a wider range of colloquial german language.
* [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) is the base model – funny but true – only using [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227) as base model is not as good as combining both.
### Configuration
The following YAML configuration was used to produce this model:
```yaml
# works but never stops
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: VAGOsolutions/SauerkrautLM-7b-LaserChat
parameters:
density: 0.53
weight: 0.15
- model: hiig-piai/simba-01d-ftb
parameters:
density: 0.53
weight: 0.55
- model: DRXD1000/Phoenix
parameters:
density: 0.53
weight: 0.15
- model: OpenPipe/mistral-ft-optimized-1227
parameters:
density: 0.53
weight: 0.15
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
name: VerwaltungsAnthologie_clear_simbad_7B
```