Commit
•
750be3e
1
Parent(s):
810ccaa
Update README.md
Browse files
README.md
CHANGED
|
@@ -69,9 +69,7 @@ The model was finetuned for 3 epochs using 32 H100s on dataset of size 2400. We
|
|
| 69 |
|
| 70 |
### Training Data
|
| 71 |
|
| 72 |
-
We train on 2400 samples consisting of CovidQA, PubmedQA, DROP and RAGTruth samples. For datasets that do not contain hallucinated samples, we generate perturbations to introduce hallucinations in the data. For more details about the data generation process, refer to the paper.
|
| 73 |
-
|
| 74 |
-
The training data can be found here: [PatronusAI/drop-RAGTruth-covidqa-pubmed](https://huggingface.co/datasets/PatronusAI/drop-RAGTruth-covidqa-pubmed)
|
| 75 |
|
| 76 |
## Evaluation
|
| 77 |
|
|
|
|
| 69 |
|
| 70 |
### Training Data
|
| 71 |
|
| 72 |
+
We train on 2400 samples consisting of CovidQA, PubmedQA, DROP and RAGTruth samples. For datasets that do not contain hallucinated samples, we generate perturbations to introduce hallucinations in the data. For more details about the data generation process, refer to the paper.
|
|
|
|
|
|
|
| 73 |
|
| 74 |
## Evaluation
|
| 75 |
|