Lambent's picture
Update README.md
93ba186 verified
---
base_model:
- Lambent/CosmoAlpacaLight-1b
- HuggingFaceTB/cosmo-1b
- Lambent/CosmoAlpacaLisa-1b
- Lambent/CosmoAlpacaLisa-0.2-1b
tags:
- mergekit
- merge
---
Figured the model must have learned the data a somewhat different way for all three training methods.
Decided to test if merging them would give generalization benefits. I think it didn't hurt at least!
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|-------------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[CosmoAlpacaLisa-0.3-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-0.3-1b)| 23.79| 51.61| 40.25| 29.97| 36.41|
| Model |AGIEval|GPT4All|TruthfulQA|Bigbench|Average|
|-------------------------------------------------------------------------|------:|------:|---------:|-------:|------:|
|[CosmoAlpacaLight-1b](https://huggingface.co/Lambent/CosmoAlpacaLight-1b)| 24.28| 51.31| 40.33| 29.47| 36.35|
# lisacosmo
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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [HuggingFaceTB/cosmo-1b](https://huggingface.co/HuggingFaceTB/cosmo-1b) as a base.
### Models Merged
The following models were included in the merge:
* [Lambent/CosmoAlpacaLight-1b](https://huggingface.co/Lambent/CosmoAlpacaLight-1b)
* [Lambent/CosmoAlpacaLisa-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-1b)
* [Lambent/CosmoAlpacaLisa-0.2-1b](https://huggingface.co/Lambent/CosmoAlpacaLisa-0.2-1b)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Lambent/CosmoAlpacaLisa-1b
parameters:
density: 1.0
weight: 1.0
- model: Lambent/CosmoAlpacaLisa-0.2-1b
parameters:
density: 1.0
weight: 1.0
- model: Lambent/CosmoAlpacaLight-1b
parameters:
density: 1.0
weight: 1.0
merge_method: dare_ties
base_model: HuggingFaceTB/cosmo-1b
parameters:
normalize: true
int8_mask: false
dtype: float16
```