README.md

---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
---

# Lumina-3.5

Lumina-3.5 is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). Improved reasoning than [Lumina-3](https://huggingface.co/Ppoyaa/Lumina-3). This model uses a context window of up to 32k.

# Response Examples
``` Math
Input: 25 - 4 * 2 + 3 = ?
------------------------------------
Output: To solve this equation, follow the order of operations (PEMDAS/BODMAS): Parentheses, Exponents, Multiplication and Division (from left to right), and Addition and Subtraction (from left to right).

25 - 4 * 2 + 3

First, perform the multiplication:

25 - 8 + 3

Next, do the subtraction from left to right:

17 + 3

Finally, complete the addition:

20
```

``` Reasoning
Input: Jane is faster than Joe. Joe is faster than Sam. Is Sam faster than Jane? Explain your reasoning step by step.
------------------------------------
Output: To answer this question, let's analyze the given information step by step:

We are provided with a comparison between three individuals - Jane, Joe, and Sam - in terms of their relative speeds. The statements tell us the following about their ranks:
Jane > Joe (Jane is faster than Joe)
Joe > Sam (Joe is faster than Sam)
Now we need to determine if the opposite relationship holds true: whether Sam is faster than Jane or not. Based on the given comparisons, we know that both Jane and Joe have faster speeds compared to Sam. There isn't any piece of information suggesting otherwise.

Since the original premise established an ordered ranking among these individuals (Jane > Joe > Sam), and the direct opposite of the relationship between Sam and the other two is not present, we cannot conclude that Sam is faster than Jane.

Thus, based on the provided information, our reasoning confirms that Sam is not faster than Jane.
```

## 🏆 Open LLM Leaderboard Evaluation Results 
|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |75.41|
|AI2 Reasoning Challenge (25-Shot)|71.59|
|HellaSwag (10-Shot)              |88.82|
|MMLU (5-Shot)                    |64.48|
|TruthfulQA (0-shot)              |75.66|
|Winogrande (5-shot)              |83.98|
|GSM8k (5-shot)                   |67.93|

# Quants

Special thanks to GGUFs made by [mradermacher](https://huggingface.co/mradermacher)
* [mradermacher/Lumina-3.5-GGUF](https://huggingface.co/mradermacher/Lumina-3.5-GGUF)

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/Lumina-3.5"

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"])
```