Update README.md
Browse files
README.md
CHANGED
@@ -16,6 +16,13 @@ tags:
|
|
16 |
- ~100 datasets were taken from kaggle https://www.kaggle.com/datasets?search=Tabular+data
|
17 |
- These dataset were used to generate 390 sets of data queries and pandas code answers via llama3-70b https://www.kaggle.com/code/samsonleegh/sampling-data-qns-and-pandas-ans-from-dataset
|
18 |
- Finetuned llama3-8b-4bit with LoRA 16 adapters https://colab.research.google.com/drive/1ZFBZGAK-fNcgt6RYSp0npnDWOeBAXEgf?usp=sharing
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
- **Developed by:** samsonleegh
|
21 |
- **License:** apache-2.0
|
|
|
16 |
- ~100 datasets were taken from kaggle https://www.kaggle.com/datasets?search=Tabular+data
|
17 |
- These dataset were used to generate 390 sets of data queries and pandas code answers via llama3-70b https://www.kaggle.com/code/samsonleegh/sampling-data-qns-and-pandas-ans-from-dataset
|
18 |
- Finetuned llama3-8b-4bit with LoRA 16 adapters https://colab.research.google.com/drive/1ZFBZGAK-fNcgt6RYSp0npnDWOeBAXEgf?usp=sharing
|
19 |
+
## ROUGE Score Comparison
|
20 |
+
| Metric | llama3-8b | llama3-8b finetuned |
|
21 |
+
|------------|----------------|----------------|
|
22 |
+
| ROUGE-1 | 0.4415 | 0.6585 |
|
23 |
+
| ROUGE-2 | 0.2480 | 0.4810 |
|
24 |
+
| ROUGE-L | 0.3155 | 0.5552 |
|
25 |
+
| ROUGE-Lsum | 0.3013 | 0.5570 |
|
26 |
|
27 |
- **Developed by:** samsonleegh
|
28 |
- **License:** apache-2.0
|