Commit
·
7e0106b
1
Parent(s):
fd20764
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ widget:
|
|
| 9 |
---
|
| 10 |
|
| 11 |
|
| 12 |
-
# Finetuned
|
| 13 |
|
| 14 |
This distilbert model was fine-tuned on 50.000 stock news articles using the HuggingFace adapter from Kern AI refinery. The articles consisted of the headlines plus abstract of the article.
|
| 15 |
For the finetuning, a single NVidia K80 was used for about four hours.
|
|
@@ -38,8 +38,8 @@ Then you can load the model and the tokenizer from the HuggingFace Hub:
|
|
| 38 |
```python
|
| 39 |
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 40 |
|
| 41 |
-
model = AutoModelForSequenceClassification.from_pretrained("KernAI/stock-news-
|
| 42 |
-
tokenizer = AutoTokenizer.from_pretrained("KernAI/stock-news-
|
| 43 |
```
|
| 44 |
To classify a single sentence or a sentence pair, you can use the HuggingFace Pipeline API:
|
| 45 |
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
|
| 12 |
+
# Finetuned distilBERT model for stock news classification
|
| 13 |
|
| 14 |
This distilbert model was fine-tuned on 50.000 stock news articles using the HuggingFace adapter from Kern AI refinery. The articles consisted of the headlines plus abstract of the article.
|
| 15 |
For the finetuning, a single NVidia K80 was used for about four hours.
|
|
|
|
| 38 |
```python
|
| 39 |
from transformers import AutoModelForSequenceClassification, AutoTokenizer
|
| 40 |
|
| 41 |
+
model = AutoModelForSequenceClassification.from_pretrained("KernAI/stock-news-distilbert")
|
| 42 |
+
tokenizer = AutoTokenizer.from_pretrained("KernAI/stock-news-distilbert")
|
| 43 |
```
|
| 44 |
To classify a single sentence or a sentence pair, you can use the HuggingFace Pipeline API:
|
| 45 |
|