File size: 2,324 Bytes
791a242
 
 
 
 
 
 
 
 
 
 
 
b0c433f
0c32c26
b33eded
791a242
2656a79
 
 
 
 
 
 
 
 
 
 
 
 
 
0c32c26
 
 
 
 
 
 
 
 
 
 
791a242
 
 
 
 
 
 
 
 
4e834f0
791a242
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
---
license: apache-2.0
tags:
- moe
- frankenmoe
- merge
- mergekit
- lazymergekit
---

# Lumina-RP

Lumina-4 is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing).
This model has improved roleplaying and storytelling from [Lumina-3.5](https://huggingface.co/Ppoyaa/Lumina-3.5) while still retaining its strength. A slight improvement on the Open LLM leaderboard.
It uses a context window of up to 32k.

# Response Examples
``` Math
Input: 25 - 4 * 2 + 3 = ?
------------------------------------
Output: The given mathematical expression is 25 - 4 * 2 + 3. To solve it, we should follow the order of operations (PEMDAS):

1. Parentheses: There are none in this equation.
2. Exponents: None present.
3. Multiplication and Division: We perform multiplications before divisions from left to right. In this case, 4 * 2 = 8. Now our equation becomes 25 - 8 + 3.
4. Addition and Subtraction: We perform additions before subtractions from left to right. Here, we have a subtraction then an addition: 25 - 8 = 17, then 17 + 3 = 20.

So the result of the expression 25 - 4 * 2 + 3 is 20.
```

# 🏆 Open LLM Leaderboard Evaluation Results 
|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |75.59|
|AI2 Reasoning Challenge (25-Shot)|72.61|
|HellaSwag (10-Shot)              |88.45|
|MMLU (5-Shot)                    |64.73|
|TruthfulQA (0-shot)              |74.24|
|Winogrande (5-shot)              |83.90|
|GSM8k (5-shot)                   |69.60|

## 💻 Usage

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

from transformers import AutoTokenizer
import transformers
import torch

model = "Ppoyaa/Lumina-4"

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"])
```