README.md

---
tags:
- merge
- mergekit
- lazymergekit
- Nitral-AI/Kunocchini-7b-128k-test
- SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
- Endevor/InfinityRP-v1-7B
base_model:
- Nitral-AI/Kunocchini-7b-128k-test
- SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
- Endevor/InfinityRP-v1-7B
---

# InfinToppyKuno-DARE-7bv2

InfinToppyKuno-DARE-7bv2 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Nitral-AI/Kunocchini-7b-128k-test](https://huggingface.co/Nitral-AI/Kunocchini-7b-128k-test)
* [SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE](https://huggingface.co/SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE)
* [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/63b79573ca2f378e71027268/-ZGuDjXvjTHC4F-sG-3bY.png)

## 🧩 Configuration

```yaml
models:
  - model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
    # No parameters necessary for base model
  - model: Nitral-AI/Kunocchini-7b-128k-test
    parameters:
      density: 0.53
      weight: 0.4
  - model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
    parameters:
      density: 0.53
      weight: 0.3
  - model: Endevor/InfinityRP-v1-7B
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Smuggling1710/InfinToppyKuno-DARE-7bv2"
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"])
```