Commit
•
cc2c908
1
Parent(s):
b585e46
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
datasets:
|
| 3 |
- imdb
|
| 4 |
- cornell_movie_dialogue
|
|
|
|
|
|
|
| 5 |
|
| 6 |
language:
|
| 7 |
- English
|
|
@@ -19,6 +21,8 @@ license: cc-by-4.0
|
|
| 19 |
---
|
| 20 |
# roberta-base for MLM
|
| 21 |
|
|
|
|
|
|
|
| 22 |
```
|
| 23 |
model_name = "thatdramebaazguy/movie-roberta-base"
|
| 24 |
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="Fill-Mask")
|
| 2 |
datasets:
|
| 3 |
- imdb
|
| 4 |
- cornell_movie_dialogue
|
| 5 |
+
- polarity_movie_data
|
| 6 |
+
- 25mlens_movie_data
|
| 7 |
|
| 8 |
language:
|
| 9 |
- English
|
| 21 |
---
|
| 22 |
# roberta-base for MLM
|
| 23 |
|
| 24 |
+
Objective: To make a Roberta Base for the Movie Domain by using various Movie Datasets as simple text for Masked Language Modeling.
|
| 25 |
+
This is the Movie Roberta to be used in Movie Domain applications.
|
| 26 |
```
|
| 27 |
model_name = "thatdramebaazguy/movie-roberta-base"
|
| 28 |
pipeline(model=model_name, tokenizer=model_name, revision="v1.0", task="Fill-Mask")
|