README.md

---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
- DT12the/Math-Mixtral-7B
base_model:
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
- DT12the/Math-Mixtral-7B
---

# Neuralmaath-12B-MoE

Neuralmaath-12B-MoE is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Kukedlc/NeuralSynthesis-7b-v0.4-slerp](https://huggingface.co./Kukedlc/NeuralSynthesis-7b-v0.4-slerp)
* [DT12the/Math-Mixtral-7B](https://huggingface.co./DT12the/Math-Mixtral-7B)

## 🧩 Configuration

```yaml
base_model: Kukedlc/NeuralSynthesis-7b-v0.4-slerp
experts:
  - source_model: Kukedlc/NeuralSynthesis-7b-v0.4-slerp
    positive_prompts: ["what"]
  - source_model: DT12the/Math-Mixtral-7B
    positive_prompts: ["math"]
```

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "allknowingroger/Neuralmaath-12B-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"])
```