---
tags:
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralFusion-7b-Dare-Ties
- paulml/OmniBeagleSquaredMBX-v3-7B-v2
- macadeliccc/MBX-7B-v3-DPO
- Kukedlc/Fasciculus-Arcuatus-7B-slerp
- liminerity/Neurotic-Jomainotrik-7b-slerp
base_model:
- Kukedlc/NeuralFusion-7b-Dare-Ties
- paulml/OmniBeagleSquaredMBX-v3-7B-v2
- macadeliccc/MBX-7B-v3-DPO
- Kukedlc/Fasciculus-Arcuatus-7B-slerp
- liminerity/Neurotic-Jomainotrik-7b-slerp
---

# Neural-4-Wino-7b

Neural-4-Wino-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralFusion-7b-Dare-Ties](https://huggingface.co/Kukedlc/NeuralFusion-7b-Dare-Ties)
* [paulml/OmniBeagleSquaredMBX-v3-7B-v2](https://huggingface.co/paulml/OmniBeagleSquaredMBX-v3-7B-v2)
* [macadeliccc/MBX-7B-v3-DPO](https://huggingface.co/macadeliccc/MBX-7B-v3-DPO)
* [Kukedlc/Fasciculus-Arcuatus-7B-slerp](https://huggingface.co/Kukedlc/Fasciculus-Arcuatus-7B-slerp)
* [liminerity/Neurotic-Jomainotrik-7b-slerp](https://huggingface.co/liminerity/Neurotic-Jomainotrik-7b-slerp)

## 🧩 Configuration

```yaml
models:
  - model: liminerity/Neurotic-Jomainotrik-7b-slerp
    # No parameters necessary for base model
  - model: Kukedlc/NeuralFusion-7b-Dare-Ties
    parameters:
      density: 0.66
      weight: 0.2
  - model: paulml/OmniBeagleSquaredMBX-v3-7B-v2
    parameters:
      density: 0.55
      weight: 0.2
  - model: macadeliccc/MBX-7B-v3-DPO
    parameters:
      density: 0.55
      weight: 0.2
  - model: Kukedlc/Fasciculus-Arcuatus-7B-slerp
    parameters:
      density: 0.44
      weight: 0.2
  - model: liminerity/Neurotic-Jomainotrik-7b-slerp
    parameters:
      density: 0.66
      weight: 0.2
merge_method: dare_ties
base_model: liminerity/Neurotic-Jomainotrik-7b-slerp
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/Neural-4-Wino-7b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```