Update README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,3 @@
|
|
| 1 |
-
### Model description
|
| 2 |
-
|
| 3 |
-
We fine-tuned the bass with LoRA using ORKG/SciQA benchmark for question answering over sholarly knowledge graphs.
|
| 4 |
-
|
| 5 |
-
We tried several training epochs: 3,5,7,10,15,20.
|
| 6 |
-
The best performance was obtained on 15 epochs, so we pubished this model with 15 epochs.
|
| 7 |
-
|
| 8 |
-
For more details on the evaluation, please check this GitHub repo[FIRESPARQL](https://github.com/sherry-pan/FIRESPARQL)
|
| 9 |
-
|
| 10 |
-
|
| 11 |
---
|
| 12 |
license: mit
|
| 13 |
datasets:
|
|
@@ -21,4 +11,13 @@ metrics:
|
|
| 21 |
base_model:
|
| 22 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 23 |
pipeline_tag: question-answering
|
| 24 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
datasets:
|
|
|
|
| 11 |
base_model:
|
| 12 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
| 13 |
pipeline_tag: question-answering
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
### Model description
|
| 17 |
+
|
| 18 |
+
We fine-tuned the bass with LoRA using ORKG/SciQA benchmark for question answering over sholarly knowledge graphs.
|
| 19 |
+
|
| 20 |
+
We tried several training epochs: 3,5,7,10,15,20.
|
| 21 |
+
The best performance was obtained on 15 epochs, so we pubished this model with 15 epochs.
|
| 22 |
+
|
| 23 |
+
For more details on the evaluation, please check this GitHub repo[FIRESPARQL](https://github.com/sherry-pan/FIRESPARQL)
|