---
license: apache-2.0
tags:
- moe
- merge
- mergekit
- lazymergekit
- Felladrin/Minueza-32M-Base
- Felladrin/Minueza-32M-UltraChat
---

# Mixnueza-6x32M-MoE

Mixnueza-6x32M-MoE is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base)
* [Felladrin/Minueza-32M-UltraChat](https://huggingface.co/Felladrin/Minueza-32M-UltraChat)
* [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base)
* [Felladrin/Minueza-32M-UltraChat](https://huggingface.co/Felladrin/Minueza-32M-UltraChat)
* [Felladrin/Minueza-32M-Base](https://huggingface.co/Felladrin/Minueza-32M-Base)
* [Felladrin/Minueza-32M-UltraChat](https://huggingface.co/Felladrin/Minueza-32M-UltraChat)

## 🧩 Configuration

```yamlbase_model: Felladrin/Minueza-32M-UltraChat
experts:
  - source_model: Felladrin/Minueza-32M-Base
    positive_prompts:
    - "reasoning"
    - "logic" 
    - "problem-solving"
    - "critical thinking"
    - "analysis"
    - "synthesis"
    - "evaluation"
    - "decision-making"
    - "judgment"
    - "insight"
    negative_prompts:
    - "programming"
    - "storytelling"
    - "legal"
    - "finance"

  - source_model: Felladrin/Minueza-32M-UltraChat
    positive_prompts:
    - "program"
    - "software"
    - "develop" 
    - "build"
    - "create"
    - "design"
    - "implement"
    - "debug"
    - "test"
    - "code"
    - "python"
    - "programming"
    - "function"
    negative_prompts:
    - "reasoning"
    - "storytelling" 
    - "legal"
    - "finance"

  - source_model: Felladrin/Minueza-32M-Base
    positive_prompts:
    - "storytelling"
    - "narrative"
    - "fiction"
    - "creative writing" 
    - "plot"
    - "characters"
    - "dialogue"
    - "setting"
    - "emotion"
    - "imagination"
    - "scene"
    - "story"
    - "character"
    negative_prompts:
    - "reasoning"
    - "programming"
    - "legal" 
    - "finance"

  - source_model: Felladrin/Minueza-32M-UltraChat
    positive_prompts:  
    - "chat"
    - "conversation"
    - "dialogue"
    - "discuss"
    - "share thoughts"
    - "explore ideas"
    - "personal assistant"
    - "friendly helper"
    negative_prompts:
    - "reasoning"
    - "programming"
    - "storytelling"
    - "legal"
    - "finance"

  - source_model: Felladrin/Minueza-32M-Base
    positive_prompts:
    - "law"
    - "legal"
    - "attorney"
    - "lawyer" 
    - "court"
    - "contract"
    - "criminal"  
    - "evidence"
    - "procedure"
    - "contracts"
    - "mergers & acquisitions"
    - "corporate governance"
    - "intellectual property"
    - "employment law" 
    - "international trade"
    - "competition law"
    - "antitrust"
    - "litigation"
    - "arbitration"
    - "mediation"
    negative_prompts:
    - "reasoning"
    - "programming" 
    - "storytelling"
    - "finance"

  - source_model: Felladrin/Minueza-32M-UltraChat
    positive_prompts:
    - "personal finance"  
    - "budgeting"
    - "investing"
    - "retirement planning"
    - "debt management" 
    - "financial education"
    - "financial"
    - "money"
    - "investment"
    - "banking"
    - "stock" 
    - "bond"
    - "portfolio"
    - "risk"
    - "return"  
    negative_prompts:
    - "reasoning"
    - "programming"
    - "storytelling" 
    - "legal"
```

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "Isotonic/Mixnueza-6x32M-MoE"

tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    model_kwargs={"torch_dtype": torch.float16, "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"])
```