Magnolia-v3b-12B / README.md
grimjim's picture
Update README.md
4fd3462 verified
---
base_model:
- grimjim/mistralai-Mistral-Nemo-Instruct-2407
- TheDrummer/Rocinante-12B-v1.1
- anthracite-org/magnum-v4-12b
- grimjim/magnum-twilight-12b
- anthracite-org/magnum-v2.5-12b-kto
- nbeerbower/Mistral-Nemo-Prism-12B
- grimjim/mistralai-Mistral-Nemo-Base-2407
- Delta-Vector/Rei-V2-12B
library_name: transformers
pipeline_tag: text-generation
tags:
- mergekit
- merge
license: apache-2.0
---
# Magnolia-v3b-12B
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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [grimjim/mistralai-Mistral-Nemo-Base-2407](https://huggingface.co/grimjim/mistralai-Mistral-Nemo-Base-2407) as a base.
### Models Merged
The following models were included in the merge:
* [grimjim/mistralai-Mistral-Nemo-Instruct-2407](https://huggingface.co/grimjim/mistralai-Mistral-Nemo-Instruct-2407)
* [TheDrummer/Rocinante-12B-v1.1](https://huggingface.co/TheDrummer/Rocinante-12B-v1.1)
* [anthracite-org/magnum-v4-12b](https://huggingface.co/anthracite-org/magnum-v4-12b)
* [grimjim/magnum-twilight-12b](https://huggingface.co/grimjim/magnum-twilight-12b)
* [anthracite-org/magnum-v2.5-12b-kto](https://huggingface.co/anthracite-org/magnum-v2.5-12b-kto)
* [nbeerbower/Mistral-Nemo-Prism-12B](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B)
* [Delta-Vector/Rei-V2-12B](https://huggingface.co/Delta-Vector/Rei-V2-12B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: grimjim/mistralai-Mistral-Nemo-Base-2407
dtype: bfloat16
merge_method: task_arithmetic
parameters:
normalize: true
models:
- model: grimjim/mistralai-Mistral-Nemo-Base-2407
- model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
parameters:
weight: 0.9
- model: anthracite-org/magnum-v2.5-12b-kto
parameters:
weight: 0.05
- model: anthracite-org/magnum-v4-12b
parameters:
weight: 0.05
- model: nbeerbower/Mistral-Nemo-Prism-12B
parameters:
weight: 0.05
- model: grimjim/magnum-twilight-12b
parameters:
weight: 0.001
- model: TheDrummer/Rocinante-12B-v1.1
parameters:
weight: 0.001
- model: Delta-Vector/Rei-V2-12B
parameters:
weight: 0.001
```