50 lines
1.4 KiB
Markdown
50 lines
1.4 KiB
Markdown
---
|
|
base_model:
|
|
- inflatebot/helide-beta-r0
|
|
- inflatebot/helide-beta-r4
|
|
- Sao10K/L3-8B-Stheno-v3.2
|
|
- inflatebot/helide-beta-r1
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# helium-3-r5
|
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
## Merge Details
|
|
|
|
Helium3, but the base is Stheno. A bit stupid. If Helium3-baseLlama is too dry and regular Helium3 is too horny, this *might* be a good middle ground.
|
|
Emphasis on "might."
|
|
|
|
[GGUFs by mradermacher](https://huggingface.co/mradermacher/L3-8B-Helium3-baseStheno-GGUF)
|
|
|
|
### Merge Method
|
|
|
|
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) as a base.
|
|
|
|
### Models Merged
|
|
|
|
The following models were included in the merge:
|
|
* [inflatebot/helide-beta-r0](https://huggingface.co/inflatebot/helide-beta-r0)
|
|
* [inflatebot/helide-beta-r4](https://huggingface.co/inflatebot/helide-beta-r4)
|
|
* [inflatebot/helide-beta-r1](https://huggingface.co/inflatebot/helide-beta-r1)
|
|
|
|
### Configuration
|
|
|
|
The following YAML configuration was used to produce this model:
|
|
|
|
```yaml
|
|
models:
|
|
- model: inflatebot/helide-beta-r4
|
|
- model: inflatebot/helide-beta-r1
|
|
- model: inflatebot/helide-beta-r0
|
|
|
|
merge_method: model_stock
|
|
base_model: Sao10K/L3-8B-Stheno-v3.2
|
|
dtype: bfloat16
|
|
|
|
```
|