---
base_model:
- Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2
- kromcomp/L3-Direv2-8B
- OEvortex/Emotional-llama-8B
- PJMixers-Archive/ResplendentAI_Theory_of_Mind_Llama3-QLoRA
library_name: transformers
tags:
- mergekit
- merge

---
# grey

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 [kromcomp/L3-Direv2-8B](https://huggingface.co/kromcomp/L3-Direv2-8B) as a base.

### Models Merged

The following models were included in the merge:
* [Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2](https://huggingface.co/Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2)
* [OEvortex/Emotional-llama-8B](https://huggingface.co/OEvortex/Emotional-llama-8B) + [PJMixers-Archive/ResplendentAI_Theory_of_Mind_Llama3-QLoRA](https://huggingface.co/PJMixers-Archive/ResplendentAI_Theory_of_Mind_Llama3-QLoRA)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: kromcomp/L3-Direv2-8B
chat_template: llama3
dtype: float32
merge_method: model_stock
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 32]
        model: OEvortex/Emotional-llama-8B+PJMixers-Archive/ResplendentAI_Theory_of_Mind_Llama3-QLoRA
      - layer_range: [0, 32]
        model: Cas-Warehouse/Llama-3-Mopeyfied-Psychology-v2
      - layer_range: [0, 32]
        model: kromcomp/L3-Direv2-8B
parameters:
  filter_wise: 1.0
tokenizer:
  pad_to_multiple_of: 32
```