README.md

---
base_model:
- unsloth/Qwen2.5-1.5B-Instruct
- unsloth/Qwen2.5-Coder-1.5B-Instruct
- unsloth/Qwen2.5-Math-1.5B-Instruct
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- unsloth/Qwen2.5-1.5B-Instruct
- unsloth/Qwen2.5-Coder-1.5B-Instruct
- unsloth/Qwen2.5-Math-1.5B-Instruct
---

> Note: This model is experimental and has not been tested for quality.

# Qwen2.5-Sci

Qwen2.5-Sci is a `mergekit` merge of the following models:
* [unsloth/Qwen2.5-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-1.5B-Instruct)
* [unsloth/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct)
* [unsloth/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Math-1.5B-Instruct)

## 🧩 Configuration

```yaml
models:
  - model: unsloth/Qwen2.5-1.5B-Instruct
    parameters:
      weight: 0.5
  - model: unsloth/Qwen2.5-Coder-1.5B-Instruct
    parameters:
      weight: 0.3
  - model: unsloth/Qwen2.5-Math-1.5B-Instruct
    parameters:
      weight: 0.2
merge_method: task_arithmetic
base_model: unsloth/Qwen2.5-1.5B-Instruct
parameters:
  normalize: true
dtype: float16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "halbihn/Qwen2.5-Sci"
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"])
```