---
license: apache-2.0
tags:
- merge
- mergekit
- BioMistral/BioMistral-7B-DARE
- NousResearch/Nous-Hermes-2-Mistral-7B-DPO
---

# BioMistral-Hermes-Dare

BioMistral-Hermes-Dare is a merge of the following models:
* [BioMistral/BioMistral-7B-DARE](https://huggingface.co/BioMistral/BioMistral-7B-DARE)
* [NousResearch/Nous-Hermes-2-Mistral-7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO)

## Evaluations

| Benchmark | BioMistral-Hermes-Dare | Orca-2-7b | llama-2-7b | meditron-7b | meditron-70b |
| --- | --- | --- | --- | --- | --- |
| MedMCQA |  |  |  |  |  |
| ClosedPubMedQA |  |  |  |  |  |
| PubMedQA |  |  |  |  |  |
| MedQA |  |  |  |  |  |
| MedQA4 |  |  |  |  |  |
| MedicationQA |  |  |  |  |  |
| MMLU Medical |  |  |  |  |  |
| MMLU |  |  |  |  |  |
| TruthfulQA |  |  |  |  |  |
| GSM8K |  |  |  |  |  |
| ARC |  |  |  |  |  |
| HellaSwag |  |  |  |  |  |
| Winogrande |  |  |  |  |  |

More details on the Open LLM Leaderboard evaluation results can be found here.

## 🧩 Configuration

```yaml
models:
  - model: BioMistral/BioMistral-7B-DARE
    parameters:
      weight: 1.0
  - model: NousResearch/Nous-Hermes-2-Mistral-7B-DPO
    parameters:
      weight: 0.6
merge_method: linear
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Technoculture/BioMistral-Hermes-Dare"
messages = [{"role": "user", "content": "I am feeling sleepy these days"}]

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"])
```