---
tags:
- merge
- mergekit
- lazymergekit
- DiscoResearch/DiscoLM_German_7b_v1
- DRXD1000/Phoenix
- LeoLM/leo-mistral-hessianai-7b-chat
- openaccess-ai-collective/DPOpenHermes-7B-v2
- fblgit/una-cybertron-7b-v2-bf16
- mlabonne/NeuralHermes-2.5-Mistral-7B
base_model:
- DiscoResearch/DiscoLM_German_7b_v1
- DRXD1000/Phoenix
- LeoLM/leo-mistral-hessianai-7b-chat
- openaccess-ai-collective/DPOpenHermes-7B-v2
- fblgit/una-cybertron-7b-v2-bf16
- mlabonne/NeuralHermes-2.5-Mistral-7B
---

# GermanDare-7B

GermanDare-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [DiscoResearch/DiscoLM_German_7b_v1](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1)
* [DRXD1000/Phoenix](https://huggingface.co/DRXD1000/Phoenix)
* [LeoLM/leo-mistral-hessianai-7b-chat](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b-chat)
* [openaccess-ai-collective/DPOpenHermes-7B-v2](https://huggingface.co/openaccess-ai-collective/DPOpenHermes-7B-v2)
* [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co/fblgit/una-cybertron-7b-v2-bf16)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)

## 🧩 Configuration

```yaml
models:
  - model: mistralai/Mistral-7B-v0.1
    # No parameters necessary for base model
  - model: DiscoResearch/DiscoLM_German_7b_v1
    parameters:
      density: 0.6
      weight: 0.2
  - model: DRXD1000/Phoenix
    parameters:
      density: 0.6
      weight: 0.2
  - model: LeoLM/leo-mistral-hessianai-7b-chat
    parameters:
      density: 0.6
      weight: 0.1
  - model: openaccess-ai-collective/DPOpenHermes-7B-v2
    parameters:
      density: 0.6
      weight: 0.2
  - model: fblgit/una-cybertron-7b-v2-bf16
    parameters:
      density: 0.6
      weight: 0.2
  - model: mlabonne/NeuralHermes-2.5-Mistral-7B
    parameters:
      density: 0.6
      weight: 0.1
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mayflowergmbh/GermanDare-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"])
```