Update README.md
Browse filesOutput:
"fantastic", "great", "terrible", "fabulous", "perfect"
README.md
CHANGED
@@ -1,48 +1,54 @@
|
|
1 |
---
|
2 |
-
|
|
|
3 |
tags:
|
4 |
-
-
|
5 |
-
|
6 |
-
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
-
probably proofread and complete it, then remove this comment. -->
|
12 |
-
|
13 |
# distilbert-base-uncased-finetuned-imdb
|
14 |
|
15 |
-
This model
|
16 |
-
It
|
17 |
-
|
18 |
-
|
19 |
-
## Model description
|
20 |
-
|
21 |
-
More information needed
|
22 |
|
23 |
-
|
24 |
-
|
25 |
-
More information needed
|
26 |
|
27 |
-
##
|
28 |
|
29 |
-
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
-
|
32 |
|
33 |
-
|
34 |
|
35 |
-
|
36 |
-
-
|
37 |
-
-
|
|
|
38 |
|
39 |
-
|
40 |
|
|
|
41 |
|
|
|
|
|
42 |
|
43 |
-
|
|
|
|
|
|
|
|
|
44 |
|
45 |
-
|
46 |
-
- TensorFlow 2.18.0
|
47 |
-
- Datasets 3.6.0
|
48 |
-
- Tokenizers 0.21.1
|
|
|
1 |
---
|
2 |
+
language: en
|
3 |
+
license: apache-2.0
|
4 |
tags:
|
5 |
+
- masked-language-modeling
|
6 |
+
- imdb
|
7 |
+
- distilbert
|
8 |
+
- domain-adaptation
|
9 |
+
- tensorflow
|
10 |
+
- movie-reviews
|
11 |
+
pipeline_tag: fill-mask
|
12 |
+
widget:
|
13 |
+
- text: "This movie was absolutely [MASK]."
|
14 |
---
|
15 |
|
|
|
|
|
|
|
16 |
# distilbert-base-uncased-finetuned-imdb
|
17 |
|
18 |
+
This is a **DistilBERT** model fine-tuned using **Masked Language Modeling (MLM)** on the **IMDB movie reviews dataset**.
|
19 |
+
It is domain-adapted specifically for understanding and completing movie-related text.
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
+
---
|
|
|
|
|
22 |
|
23 |
+
## Model Details
|
24 |
|
25 |
+
- **Base model**: [`distilbert-base-uncased`](https://huggingface.co/distilbert-base-uncased)
|
26 |
+
- **Training objective**: Masked Language Modeling
|
27 |
+
- **Domain**: English movie reviews (IMDB)
|
28 |
+
- **Framework**: TensorFlow / Keras
|
29 |
+
- **Training time**: ~3 hours on Google Colab
|
30 |
+
- **Chunk size**: 128 tokens
|
31 |
|
32 |
+
---
|
33 |
|
34 |
+
## Use Case
|
35 |
|
36 |
+
This model is ideal for:
|
37 |
+
- Autocompletion of masked tokens in movie reviews
|
38 |
+
- Domain-aware masked language modeling
|
39 |
+
- Sentence generation or augmentation in film-related contexts
|
40 |
|
41 |
+
---
|
42 |
|
43 |
+
## Example Usage
|
44 |
|
45 |
+
```python
|
46 |
+
from transformers import pipeline
|
47 |
|
48 |
+
fill_mask = pipeline(
|
49 |
+
"fill-mask",
|
50 |
+
model="Prathamesh2403/distilbert-base-uncased-finetuned-imdb",
|
51 |
+
tokenizer="Prathamesh2403/distilbert-base-uncased-finetuned-imdb"
|
52 |
+
)
|
53 |
|
54 |
+
fill_mask("This movie was absolutely [MASK].")
|
|
|
|
|
|