charlieoneill
commited on
Merge branch 'main' of https://huggingface.co/charlieoneill/distilbert-base-uncased-gradient-clinic
Browse files
README.md
CHANGED
@@ -35,7 +35,16 @@ This model is a PyTorch `torch.nn.Module` sub-class.
|
|
35 |
|
36 |
## Intended uses & limitations
|
37 |
|
38 |
-
Note that because of the fine-tuning, the model will not perform as well on general question answering tasks.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
## Training and evaluation data
|
41 |
|
|
|
35 |
|
36 |
## Intended uses & limitations
|
37 |
|
38 |
+
Note that because of the fine-tuning, the model will not perform as well on general question answering tasks. However, this is because we have trained the model specifically to answer two types of questions:
|
39 |
+
* What is the drug used on the left/right eye?
|
40 |
+
* What is the visual acuity of this patient?
|
41 |
+
|
42 |
+
For instance, using the standard `distilbert-base-cased-distilled-squad` on the following question and context gives the answer `Eylea` with 96% confidence:
|
43 |
+
```python
|
44 |
+
context = "4/52 rev + l) eylea hn $95"
|
45 |
+
question = "What drug was used on the left eye?"
|
46 |
+
```
|
47 |
+
However, with our new, fine-tuned model we get 98% confidence.
|
48 |
|
49 |
## Training and evaluation data
|
50 |
|