README.md

---
license: cc-by-nc-4.0
tags:
- merge
- mergekit
- lazymergekit
base_model:
- shadowml/WestBeagle-7B
- mlabonne/NeuralBeagle14-7B
- shadowml/BeagSake-7B
- mlabonne/NeuralOmniBeagle-7B-v2
- mlabonne/NeuralOmniBeagle-7B
- mlabonne/OmniBeagle-7B
---

# ArchBeagle-7B

ArchBeagle-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [shadowml/WestBeagle-7B](https://huggingface.co/shadowml/WestBeagle-7B)
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B)
* [shadowml/BeagSake-7B](https://huggingface.co/shadowml/BeagSake-7B)
* [mlabonne/NeuralOmniBeagle-7B-v2](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B-v2)
* [mlabonne/NeuralOmniBeagle-7B](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B)
* [mlabonne/OmniBeagle-7B](https://huggingface.co/mlabonne/OmniBeagle-7B)

## 🧩 Configuration

```yaml
models:
  - model: mistralai/Mistral-7B-v0.1
    # no parameters necessary for base model
  - model: shadowml/WestBeagle-7B
    parameters:
      density: 0.65
      weight: 0.25
  - model: mlabonne/NeuralBeagle14-7B
    parameters:
      density: 0.6
      weight: 0.15
  - model: shadowml/BeagSake-7B
    parameters:
      density: 0.55
      weight: 0.1
  - model: mlabonne/NeuralOmniBeagle-7B-v2
    parameters:
      density: 0.65
      weight: 0.25
  - model: mlabonne/NeuralOmniBeagle-7B
    parameters:
      density: 0.6
      weight: 0.15
  - model: mlabonne/OmniBeagle-7B
    parameters:
      density: 0.55
      weight: 0.1
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/ArchBeagle-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"])
```