bruphin-eta / README.md
nbeerbower's picture
update readme
419bf26
|
raw
history blame
1.05 kB
---
license: apache-2.0
base_model:
- nbeerbower/bruphin-epsilon
- jondurbin/bagel-dpo-7b-v0.4
library_name: transformers
tags:
- mergekit
- merge
---
# bruphin-eta
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 SLERP merge method.
### Models Merged
The following models were included in the merge:
* [nbeerbower/bruphin-epsilon](https://huggingface.co/nbeerbower/bruphin-epsilon)
* [jondurbin/bagel-dpo-7b-v0.4](https://huggingface.co/jondurbin/bagel-dpo-7b-v0.4)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: nbeerbower/bruphin-epsilon
layer_range: [0, 32]
- model: jondurbin/bagel-dpo-7b-v0.4
layer_range: [0, 32]
merge_method: slerp
base_model: jondurbin/bagel-dpo-7b-v0.4
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16
```