---
tags:
- merge
- mergekit
- cognitivecomputations/dolphin-2.9-llama3-8b
- NousResearch/Hermes-2-Pro-Llama-3-8B
- abacusai/Llama-3-Smaug-8B
base_model:
- cognitivecomputations/dolphin-2.9-llama3-8b
- NousResearch/Hermes-2-Pro-Llama-3-8B
- abacusai/Llama-3-Smaug-8B
---

# aqua-smaug-hermes-8B
aqua-smaug-hermes-8B is a merge of the following models using [Mergekit](https://github.com/arcee-ai/mergekit):
* [cognitivecomputations/dolphin-2.9-llama3-8b](https://huggingface.co/cognitivecomputations/dolphin-2.9-llama3-8b)
* [NousResearch/Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B)
* [abacusai/Llama-3-Smaug-8B](https://huggingface.co/abacusai/Llama-3-Smaug-8B)

## 🧩 Configuration

```yamlname: aqua-smaug-hermes-8B
tokenizer_source: union
base_model:
  model:
   path: NousResearch/Hermes-2-Pro-Llama-3-8B
dtype: float16
merge_method: dare_linear
parameters:
  normalize: 1.0
slices:
  - sources:
    - model: cognitivecomputations/dolphin-2.9-llama3-8b
      layer_range: [0, 32]
      parameters:
        weight: 0.3
    - model: NousResearch/Hermes-2-Pro-Llama-3-8B
      layer_range: [0, 32]
      parameters:
        weight: 0.4
    - model: abacusai/Llama-3-Smaug-8B
      layer_range: [0, 32]
      parameters:
        weight: 0.3```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "saucam/aqua-smaug-hermes-8B"
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"])
```