README.md

---
tags:
- merge
- mergekit
- lazymergekit
- viethq188/LeoScorpius-7B-Chat-DPO
- GreenNode/GreenNode-mini-7B-multilingual-v1olet
base_model:
- viethq188/LeoScorpius-7B-Chat-DPO
- GreenNode/GreenNode-mini-7B-multilingual-v1olet
---

# GreenScorpius2-xb

GreenScorpius2-xb is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [viethq188/LeoScorpius-7B-Chat-DPO](https://huggingface.co/viethq188/LeoScorpius-7B-Chat-DPO)
* [GreenNode/GreenNode-mini-7B-multilingual-v1olet](https://huggingface.co/GreenNode/GreenNode-mini-7B-multilingual-v1olet)

## 🧩 Configuration

```yaml
slices:
  - sources:
    - model: viethq188/LeoScorpius-7B-Chat-DPO
      layer_range: [0, 26]
  - sources:
    - model: GreenNode/GreenNode-mini-7B-multilingual-v1olet
      layer_range: [8, 32]
merge_method: passthrough
tokenizer_source: union
dtype: float16
    ```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "powermove72/GreenScorpius2-xb"
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"])
```