---
tags:
- merge
- mergekit
- nvidia/Llama3-ChatQA-1.5-8B
- refuelai/Llama-3-Refueled
base_model:
- nvidia/Llama3-ChatQA-1.5-8B
- refuelai/Llama-3-Refueled
---

# PowerBot-8B
PowerBot-8B is a merge of the following models using [Mergekit](https://github.com/arcee-ai/mergekit):
* [nvidia/Llama3-ChatQA-1.5-8B](https://huggingface.co/nvidia/Llama3-ChatQA-1.5-8B)
* [refuelai/Llama-3-Refueled](https://huggingface.co/refuelai/Llama-3-Refueled)

## 🧩 Configuration

```yamlname: PowerBot-8B
tokenizer_source: union
embed_slerp: true
models:
  - model: nvidia/Llama3-ChatQA-1.5-8B
    parameters:
      density: 0.5
      weight: 0.6
    # No parameters necessary for base model
  - model: refuelai/Llama-3-Refueled
    parameters:
      density: 0.5
      weight: 0.4
merge_method: dare_ties
base_model: nvidia/Llama3-ChatQA-1.5-8B
parameters:
  int8_mask: true
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "saucam/PowerBot-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"])
```