|
|
--- |
|
|
base_model: |
|
|
- IlyaGusev/gemma-2-2b-it-abliterated |
|
|
- monsterapi/gemma-2-2b-norobots |
|
|
- benjamin/Gemma2-2B-Distilled-Math |
|
|
- SaisExperiments/GemmOwO-2B |
|
|
- kweinmeister/gemma-2-2b-it-dolly-15k |
|
|
- Arnic/Gemma-2-2b-it-chat-medicare |
|
|
- bunnycore/Gemma-2-2b-TitanFusion |
|
|
- zli12321/prometheus2-2B |
|
|
- lmassaron/gemma-2-2b-it-grpo-gsm8k |
|
|
library_name: transformers |
|
|
tags: |
|
|
- mergekit |
|
|
- merge |
|
|
|
|
|
--- |
|
|
# merge |
|
|
|
|
|
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [IlyaGusev/gemma-2-2b-it-abliterated](https://huggingface.co/IlyaGusev/gemma-2-2b-it-abliterated) + [monsterapi/gemma-2-2b-norobots](https://huggingface.co/monsterapi/gemma-2-2b-norobots) as a base. |
|
|
|
|
|
### Models Merged |
|
|
|
|
|
The following models were included in the merge: |
|
|
* [benjamin/Gemma2-2B-Distilled-Math](https://huggingface.co/benjamin/Gemma2-2B-Distilled-Math) |
|
|
* [SaisExperiments/GemmOwO-2B](https://huggingface.co/SaisExperiments/GemmOwO-2B) + [kweinmeister/gemma-2-2b-it-dolly-15k](https://huggingface.co/kweinmeister/gemma-2-2b-it-dolly-15k) |
|
|
* [Arnic/Gemma-2-2b-it-chat-medicare](https://huggingface.co/Arnic/Gemma-2-2b-it-chat-medicare) |
|
|
* [bunnycore/Gemma-2-2b-TitanFusion](https://huggingface.co/bunnycore/Gemma-2-2b-TitanFusion) |
|
|
* [zli12321/prometheus2-2B](https://huggingface.co/zli12321/prometheus2-2B) |
|
|
* [lmassaron/gemma-2-2b-it-grpo-gsm8k](https://huggingface.co/lmassaron/gemma-2-2b-it-grpo-gsm8k) |
|
|
|
|
|
### Configuration |
|
|
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
|
|
```yaml |
|
|
models: |
|
|
- model: bunnycore/Gemma-2-2b-TitanFusion |
|
|
- model: SaisExperiments/GemmOwO-2B+kweinmeister/gemma-2-2b-it-dolly-15k |
|
|
- model: lmassaron/gemma-2-2b-it-grpo-gsm8k |
|
|
- model: benjamin/Gemma2-2B-Distilled-Math |
|
|
- model: zli12321/prometheus2-2B |
|
|
- model: Arnic/Gemma-2-2b-it-chat-medicare |
|
|
merge_method: model_stock |
|
|
base_model: IlyaGusev/gemma-2-2b-it-abliterated+monsterapi/gemma-2-2b-norobots |
|
|
normalize: false |
|
|
filter_wise: true |
|
|
int8_mask: true |
|
|
dtype: bfloat16 |
|
|
|
|
|
``` |
|
|
|
