|
--- |
|
license: apache-2.0 |
|
tags: |
|
- moe |
|
- frankenmoe |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
--- |
|
|
|
# Lumina-5-Instruct |
|
|
|
Lumina-5-Instruct is a Mixture of Experts (MoE) made with [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing). 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): |
|
|
|
1. Parentheses/Brackets |
|
2. Exponents |
|
3. Multiplication and Division (from left to right) |
|
4. Addition and Subtraction (from left to right) |
|
5. The given equation doesn't have any parentheses or exponents, so we can start with multiplication and division: |
|
|
|
25 - 8 = 17 |
|
|
|
Now, perform the addition and subtraction from left to right: |
|
|
|
17 + 3 = 20 |
|
|
|
So, the result is 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: Let's analyze this comparison step by step: |
|
|
|
1. We are given three individuals - Jane, Joe, and Sam. |
|
2. The information provided states that "Jane is faster than Joe" and "Joe is faster than Sam." |
|
3. To determine if Sam is faster than Jane, we need to compare their relative speeds based on the given information. |
|
4. Since Joe is faster than Sam but slower than Jane, it means that Jane must be faster than both Joe and Sam. |
|
5. Therefore, there is no scenario in which Sam can be faster than Jane, as per the given comparisons. |
|
|
|
Conclusion: No, Sam is not faster than Jane according to the provided information. |
|
``` |
|
|
|
## 🏆 Open LLM Leaderboard Evaluation Results |
|
Coming soon. |
|
|
|
## 💻 Usage |
|
|
|
```python |
|
!pip install -qU transformers bitsandbytes accelerate |
|
|
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "Ppoyaa/Lumina-5-Instruct" |
|
|
|
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"]) |
|
``` |
