Orthrus-12b-v0.8 / README.md
Pyroserenus's picture
Update README.md
97f6855 verified
---
base_model:
- anthracite-org/magnum-12b-v2
- unsloth/Mistral-Nemo-Instruct-2407
- IntervitensInc/Mistral-Nemo-Base-2407-chatml
library_name: transformers
tags:
- mergekit
- merge
license: cc-by-nc-4.0
---
# o8
This model was meant as a component model for a larger merge but is usable as is.
# ChatML prefered, works with Mistral Instruct, kinda works with everything
# Tested using 0.75 temp, 0.10 MinP, 0.30 Smoothing Factor
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [IntervitensInc/Mistral-Nemo-Base-2407-chatml](https://huggingface.co/IntervitensInc/Mistral-Nemo-Base-2407-chatml) as a base.
### Models Merged
The following models were included in the merge:
* [anthracite-org/magnum-12b-v2](https://huggingface.co/anthracite-org/magnum-12b-v2)
* [unsloth/Mistral-Nemo-Instruct-2407](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
- model: unsloth/Mistral-Nemo-Instruct-2407
parameters:
weight: [0.50, 0.20]
density: [0.75, 0.55]
- model: anthracite-org/magnum-12b-v2
parameters:
weight: [0.50, 0.80]
density: [0.75, 0.85]
merge_method: ties
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
parameters:
int8_mask: true
rescale: true
normalize: false
dtype: bfloat16
```