61 lines
1.4 KiB
Markdown
61 lines
1.4 KiB
Markdown
|
|
---
|
||
|
|
base_model:
|
||
|
|
- TheDrummer/UnslopNemo-12B-v4.1
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# vagrant
|
||
|
|
|
||
|
|
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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [TheDrummer/UnslopNemo-12B-v4.1](https://huggingface.co/TheDrummer/UnslopNemo-12B-v4.1) as a base.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* intermediates/storyteller
|
||
|
|
* intermediates/superstar
|
||
|
|
* intermediates/bard
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
base_model: TheDrummer/UnslopNemo-12B-v4.1
|
||
|
|
chat_template: chatml
|
||
|
|
dtype: bfloat16
|
||
|
|
merge_method: dare_ties
|
||
|
|
modules:
|
||
|
|
default:
|
||
|
|
slices:
|
||
|
|
- sources:
|
||
|
|
- layer_range: [0, 40]
|
||
|
|
model: intermediates/storyteller
|
||
|
|
parameters:
|
||
|
|
density: 0.9
|
||
|
|
weight: 1.0
|
||
|
|
- layer_range: [0, 40]
|
||
|
|
model: intermediates/bard
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.7
|
||
|
|
- layer_range: [0, 40]
|
||
|
|
model: intermediates/superstar
|
||
|
|
parameters:
|
||
|
|
density: 0.5
|
||
|
|
weight: 0.7
|
||
|
|
- layer_range: [0, 40]
|
||
|
|
model: TheDrummer/UnslopNemo-12B-v4.1
|
||
|
|
out_dtype: bfloat16
|
||
|
|
parameters:
|
||
|
|
normalize: 1.0
|
||
|
|
tokenizer: {}
|
||
|
|
```
|