Commit
•
1caf087
1
Parent(s):
a946bcb
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,13 @@
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- BI55/MedText
|
|
|
|
| 4 |
metrics:
|
| 5 |
- bleu
|
| 6 |
- perplexity
|
| 7 |
pipeline_tag: text-generation
|
| 8 |
---
|
| 9 |
-
A further fine-tuned version of Locutusque/gpt2-large-conversational on MedText
|
| 10 |
|
| 11 |
# Evaluation
|
| 12 |
-
This model was evaluated using GPT-3.5, and it was asked medical questions. It achieved an average accuracy of 75.8%.
|
|
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- BI55/MedText
|
| 4 |
+
- pubmed_qa
|
| 5 |
metrics:
|
| 6 |
- bleu
|
| 7 |
- perplexity
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
+
A further fine-tuned version of Locutusque/gpt2-large-conversational on MedText and the pqa_labeled subset of pubmed_qa
|
| 11 |
|
| 12 |
# Evaluation
|
| 13 |
+
This model was evaluated using GPT-3.5, and it was asked medical questions. It achieved an average accuracy of 75.8%.
|