---
base_model:
- NousResearch/Meta-Llama-3-8B
- inflatebot/helide-beta-r1
- inflatebot/helide-beta-r0
- inflatebot/helide-beta-r4
library_name: transformers
tags:
- mergekit
- merge

---
# helium-3-r2

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details

Helium3, but the base model is Llama-3. Ended up being too dry, but if He3's too horny for you, try this one.

[GGUFs by mradermacher](https://huggingface.co/mradermacher/L3-8B-Helium3-baseLlama-GGUF)

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) as a base.

### Models Merged

The following models were included in the merge:
* [inflatebot/helide-beta-r1](https://huggingface.co/inflatebot/helide-beta-r1)
* [inflatebot/helide-beta-r0](https://huggingface.co/inflatebot/helide-beta-r0)
* [inflatebot/helide-beta-r4](https://huggingface.co/inflatebot/helide-beta-r4)

### 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: NousResearch/Meta-Llama-3-8B
dtype: bfloat16

```