README.md

---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- lazymergekit
- Qwen/Qwen1.5-0.5B
---

# TinyQwex-4x620M-MoE

TinyQwex-4x620M-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)
* [Qwen/Qwen1.5-0.5B](https://huggingface.co/Qwen/Qwen1.5-0.5B)

🌟 Buying me coffee is a direct way to show support for this project. 
<a href="https://www.buymeacoffee.com/isotonic"><img src="https://www.buymeacoffee.com/assets/img/guidelines/download-assets-sm-1.svg" alt=""></a>

## 💻 Usage

```python
!pip install -qU transformers bitsandbytes accelerate eniops

from transformers import AutoTokenizer
import transformers
import torch

model = "Isotonic/TinyQwex-4x620M-MoE"

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen1.5-0.5B")
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.bfloat16, "load_in_4bit": True},
)

messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
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"])
```

## 🧩 Configuration

```yamlbase_model: Qwen/Qwen1.5-0.5B
experts:
  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "reasoning"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "program"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "storytelling"

  - source_model: Qwen/Qwen1.5-0.5B
    positive_prompts:
    - "Instruction following assistant"
```