Update README.md
Browse files
README.md
CHANGED
|
@@ -35,7 +35,7 @@ To load the model:
|
|
| 35 |
|
| 36 |
```py
|
| 37 |
from transformers import BertForSequenceClassification, AutoTokenizer
|
| 38 |
-
model_path =
|
| 39 |
model = BertForSequenceClassification.from_pretrained(model_path)
|
| 40 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 41 |
```
|
|
@@ -46,22 +46,21 @@ To create embeddings and for classification:
|
|
| 46 |
# sample abstract & title text
|
| 47 |
title = "Why Brain Criticality Is Clinically Relevant: A Scoping Review."
|
| 48 |
abstract = "The past 25 years have seen a strong increase in the number of publications related to criticality in different areas of neuroscience..."
|
| 49 |
-
|
| 50 |
text = title + tokenizer.sep_token + abstract
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
#
|
| 60 |
with torch.no_grad():
|
| 61 |
output = model.bert(**tokens)
|
| 62 |
embedding = output.last_hidden_state[:, 0, :]
|
| 63 |
|
| 64 |
-
#
|
| 65 |
output = model(**tokens)
|
| 66 |
class = output.logits
|
| 67 |
```
|
|
|
|
| 35 |
|
| 36 |
```py
|
| 37 |
from transformers import BertForSequenceClassification, AutoTokenizer
|
| 38 |
+
model_path = "biodatlab/MIReAD-Neuro"
|
| 39 |
model = BertForSequenceClassification.from_pretrained(model_path)
|
| 40 |
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
| 41 |
```
|
|
|
|
| 46 |
# sample abstract & title text
|
| 47 |
title = "Why Brain Criticality Is Clinically Relevant: A Scoping Review."
|
| 48 |
abstract = "The past 25 years have seen a strong increase in the number of publications related to criticality in different areas of neuroscience..."
|
|
|
|
| 49 |
text = title + tokenizer.sep_token + abstract
|
| 50 |
+
tokens = tokenizer(
|
| 51 |
+
text,
|
| 52 |
+
max_length=512,
|
| 53 |
+
padding=True,
|
| 54 |
+
truncation=True,
|
| 55 |
+
return_tensors="pt"
|
| 56 |
+
)
|
| 57 |
+
|
| 58 |
+
# to generate an embedding from a given title and abstract
|
| 59 |
with torch.no_grad():
|
| 60 |
output = model.bert(**tokens)
|
| 61 |
embedding = output.last_hidden_state[:, 0, :]
|
| 62 |
|
| 63 |
+
# to classify (200 journals) a given title and abstract
|
| 64 |
output = model(**tokens)
|
| 65 |
class = output.logits
|
| 66 |
```
|