---
base_model:
- Khetterman/Llama-3.2-Kapusta-3B-v8
- AELLM/Llama-3.2-Chibi-3B
- AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE
library_name: transformers
tags:
- mergekit
- merge
- bfloat16
- safetensors
- llama
- llama-3
- llama-3.2
- 3b
- chat
- creative
- conversational
- not-for-all-audiences
language:
- en
- ru

---
# Llama-3.2-Kapusta-JapanChibi-3B-v1

>やめてください、私は小さくて役に立ちます
>>I love this model, but I don't understand Japanese, although it is also good in other languages.

![Kapusta-JapanChibi-Logo256.png](https://cdn-uploads.huggingface.co/production/uploads/673125091920e70ac26c8a2e/bD3Zv39dUVMQBEn1G8DTM.png)

This is an interesting merge of **3 cool models**, created using [mergekit](https://github.com/arcee-ai/mergekit).
Enjoy exploring :)

## Merge Details
### Method

This model was merged using the model_stock method.

### Models

The following models were included in the merge:

* [Khetterman/Llama-3.2-Kapusta-3B-v8](https://huggingface.co/Khetterman/Llama-3.2-Kapusta-3B-v8)
* [AELLM/Llama-3.2-Chibi-3B](https://huggingface.co/AELLM/Llama-3.2-Chibi-3B)
* [AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE](https://huggingface.co/AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE)

### Configuration

The following YAML configurations was used to produce this model:

```yaml
# Llama-3.2-Kapusta-JapanChibi-3B-v1
models:
  - model: AELLM/Llama-3.2-Chibi-3B
  - model: AXCXEPT/EZO-Llama-3.2-3B-Instruct-dpoE
merge_method: model_stock
base_model: Khetterman/Llama-3.2-Kapusta-3B-v8
dtype: bfloat16
```

>My thanks to the authors of the original models, your work is incredible. Have a good time 🖤