README.md

---
base_model:
- grimjim/mistralai-Mistral-Nemo-Base-2407
- grimjim/mistralai-Mistral-Nemo-Instruct-2407
- grimjim/magnum-consolidatum-v1-12b
library_name: transformers
pipeline_tag: text-generation
tags:
- mergekit
- merge
license: apache-2.0
---
# Magnolia-v2-12B

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

This model essentially a rebuild of v1, using task arithmetic instead of SLERP.
Of note, Mistral Nemo Base was used as the base model for task arithmetic, rather than Instruct or another fine-tune.
Furthermore, max_position_embeddings was reduced to 131072, down from 1000000, as the model was only trained on up to 131072.
Tested with temperature 1.0 and minP 0.01; temperature can be reduced (briefly tested at 0.45) if the model is too aggressively creative/hallucinatory.

## 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)
* [grimjim/magnum-consolidatum-v1-12b](https://huggingface.co/grimjim/magnum-consolidatum-v1-12b)

### 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: false
slices:
- sources:
  - layer_range: [0, 40]
    model: grimjim/mistralai-Mistral-Nemo-Base-2407
  - layer_range: [0, 40]
    model: grimjim/mistralai-Mistral-Nemo-Instruct-2407
    parameters:
      weight: 0.9
  - layer_range: [0, 40]
    model: grimjim/magnum-consolidatum-v1-12b
    parameters:
      weight: 0.1

```