44 lines
789 B
Markdown
44 lines
789 B
Markdown
|
---
|
||
|
|
base_model: []
|
||
|
|
library_name: transformers
|
||
|
|
tags:
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
|
||
|
|
---
|
||
|
|
# Merged_gpt2_0.4
|
||
|
|
|
||
|
|
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 [Linear](https://arxiv.org/abs/2203.05482) merge method.
|
||
|
|
|
||
|
|
### Models Merged
|
||
|
|
|
||
|
|
The following models were included in the merge:
|
||
|
|
* /kaggle/working/debias_gpt2
|
||
|
|
* /kaggle/working/gpt2
|
||
|
|
|
||
|
|
### Configuration
|
||
|
|
|
||
|
|
The following YAML configuration was used to produce this model:
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
dtype: float32
|
||
|
|
merge_method: linear
|
||
|
|
models:
|
||
|
|
- model: /kaggle/working/gpt2
|
||
|
|
parameters:
|
||
|
|
weight: 0.6
|
||
|
|
- model: /kaggle/working/debias_gpt2
|
||
|
|
parameters:
|
||
|
|
weight: 0.4
|
||
|
|
parameters:
|
||
|
|
normalize: true
|
||
|
|
tokenizer:
|
||
|
|
source: ComCom/gpt2-small
|
||
|
|
|
||
|
|
```
|