ockerman0's picture
Update README.md
dee7de8 verified
---
base_model:
- nothingiisreal/MN-12B-Starcannon-v3
library_name: transformers
tags:
- mergekit
- merge
---
# Unofficial continuation of [aetherwiing's](https://huggingface.co/aetherwiing) "Starcannon" series
By request, I made this merge of v3 and v5. It doesn't seem majorly dissimilar from v5, but it does seem to act slightly differently.
static quants at: https://huggingface.co/mradermacher/MN-12B-Starcannon-v5.5-unofficial-GGUF
imatrix quants at: https://huggingface.co/mradermacher/MN-12B-Starcannon-v5.5-unofficial-i1-GGUF
# mergedmodel
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 [nothingiisreal/MN-12B-Starcannon-v3](https://huggingface.co/nothingiisreal/MN-12B-Starcannon-v3) as a base.
### Models Merged
The following models were included in the merge:
* /home/ciaran/Documents/Quantisingmodels/testmerges/MN-12B-Starcannon-v5-unofficial/
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: /home/ciaran/Documents/Quantisingmodels/testmerges/MN-12B-Starcannon-v5-unofficial/
parameters:
density: 0.25
weight: 0.4
- model: nothingiisreal/MN-12B-Starcannon-v3
parameters:
density: 0.75
weight: 0.6
merge_method: ties
base_model: nothingiisreal/MN-12B-Starcannon-v3
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
```