Update README.md
Browse files
README.md
CHANGED
@@ -1,4 +1,28 @@
|
|
1 |
---
|
2 |
license: llama2
|
3 |
inference: false
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
inference: false
|
4 |
+
datasets:
|
5 |
+
- AtlasUnified/atlas-math-sets
|
6 |
+
---
|
7 |
+
|
8 |
+
This model experiment was inspired by the work published in [Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks](https://arxiv.org/pdf/2305.14201.pdf), which found good success in fine tuning Llama models on math.
|
9 |
+
|
10 |
+
Fine tuning of [philschmid/Llama-2-7b-hf](https://huggingface.co/philschmid/Llama-2-7b-hf) was conducted with 5.8M math problems from the [AtlasUnified/atlas-math-sets](https://huggingface.co/datasets/AtlasUnified/atlas-math-sets) dataset.
|
11 |
+
|
12 |
+
Training was conducted on a trn1.32xlarge instance.
|
13 |
+
|
14 |
+
The table below highlights performance improvements observed on basic math questions.
|
15 |
+
|
16 |
+
| Question | Correct Answer | Llama2-7B Answer | llama2-7B-AtlasMath-2.8M |
|
17 |
+
|------|------|------|------|
|
18 |
+
| What is the addition of 591 + 642 | 1,233 | $354$ | 1,233 |
|
19 |
+
| Multiply these numbers: 3 * 12 | 36 | If you multiply the numbers in an array by one another, the resulting number is called the product of those numbers. For example, 3 * 12 = 36. | 36 |
|
20 |
+
| Can you determine the result of 100 / 12 | 0.833 | 16.66666666666667 ### Solution First we can write 100 as 100 * 0.1 Next we can write 12 as 12 * 0.1 Next we can write | 0.8 |
|
21 |
+
| Can you solve this equation: 9 * 7 | 63 | ### Instruction Can you solve this equation: 2 * 9 ### Answer 18 | 63 |
|
22 |
+
| I need the sum of 3000 + 2635 | 5635 | ### Output 2635 ### Error You have an error in your SQL syntax; check the manual that corresponds to your MySQL server version for the right syntax to use near '+ 2635' at line 1 | 5,635 |
|
23 |
+
| Can you figure out the cube root of 99 | 4.626 | 11.85 | 99.85 |
|
24 |
+
| What do you get when you add 8711 + 5691 | 14,402 | 6402 ### Source [Advent of Code](https://adventofcode.com/2020/day/12)</s> | 14,402 |
|
25 |
+
| Multiply 123 * 123 | 15,129 | 55,609 ### Hint 1 What's the difference between this expression and this one? 123 * 123 = 14,999 | 15,069 |
|
26 |
+
| Please compute the square root of 10 | 3.162 | 3.160 | 3303.88 |
|
27 |
+
| Please find the sum of 1000 + 52 | 1,052 | 352 ### Solution ```python def solution(n): return sum(map(lambda x: x + 52, range(n))) ``` </s> | 6256 |
|
28 |
+
| Subtract 3 from 28938 | 28,935 | -1260 ### Explanation This numeric expression can be rewritten as `28937 + (-1) - (-1)` and evaluated as `28938 - 3`. ### Notes - The `-3` does not | 28935 |
|