---
base_model:
- tinycompany/shawty-CoT-Hindi-English
- tinycompany/Shawty-1.4B-SFT-Stage-1
library_name: transformers
tags:
- mergekit
- merge

---
# MergedShawty-v0.4

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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [tinycompany/shawty-CoT-Hindi-English](https://huggingface.co/tinycompany/shawty-CoT-Hindi-English)
* [tinycompany/Shawty-1.4B-SFT-Stage-1](https://huggingface.co/tinycompany/Shawty-1.4B-SFT-Stage-1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: tinycompany/Shawty-1.4B-SFT-Stage-1
merge_method: slerp
tokenizer_source: base
dtype: bfloat16
parameters:
  t:
    - filter: self_attn
      value: [0.2, 0.6, 0.4, 0.8, 1.0]
    - filter: mlp
      value: [1.0, 0.6, 0.8, 0.4, 0.2]
    - value: 0.3 
slices:
  - sources:
      - model: tinycompany/Shawty-1.4B-SFT-Stage-1
        layer_range: [0, 28]
      - model: tinycompany/shawty-CoT-Hindi-English
        layer_range: [0, 28]

```