---
base_model:
- jeiku/Orthocopter_8B
- nothingiisreal/L3.1-8B-Celeste-V1.5
- Sao10K/L3-8B-Chara-v1-Alpha
- nothingiisreal/L3-8B-Celeste-v1
library_name: transformers
tags:
- mergekit
- merge

---
# humanity.b

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 [nothingiisreal/L3.1-8B-Celeste-V1.5](https://huggingface.co/nothingiisreal/L3.1-8B-Celeste-V1.5) as a base.

### Models Merged

The following models were included in the merge:
* [jeiku/Orthocopter_8B](https://huggingface.co/jeiku/Orthocopter_8B)
* [Sao10K/L3-8B-Chara-v1-Alpha](https://huggingface.co/Sao10K/L3-8B-Chara-v1-Alpha)
* [nothingiisreal/L3-8B-Celeste-v1](https://huggingface.co/nothingiisreal/L3-8B-Celeste-v1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: nothingiisreal/L3.1-8B-Celeste-V1.5
dtype: float32
merge_method: model_stock
out_dtype: bfloat16
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 32]
    model: nothingiisreal/L3-8B-Celeste-v1
  - layer_range: [0, 32]
    model: Sao10K/L3-8B-Chara-v1-Alpha
  - layer_range: [0, 32]
    model: jeiku/Orthocopter_8B
  - layer_range: [0, 32]
    model: nothingiisreal/L3.1-8B-Celeste-V1.5
tokenizer_source: base
```