Commit
•
74a9351
1
Parent(s):
478d995
Update README.md
Browse files
README.md
CHANGED
@@ -1,34 +1,17 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
base_model: t5-small
|
4 |
-
|
5 |
-
-
|
6 |
-
|
7 |
-
-
|
8 |
-
|
9 |
-
- name: t5-small-common-corpus-topic-simple-batch
|
10 |
-
results: []
|
11 |
---
|
12 |
|
13 |
-
|
14 |
-
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
|
17 |
|
18 |
-
|
19 |
|
20 |
-
|
21 |
-
|
22 |
-
Given that Pleias-Topic-Detection is a relatively lightweight model (70 million parameters) it can be used for classification at scale on a large corpus.
|
23 |
-
|
24 |
-
### Training hyperparameters
|
25 |
-
|
26 |
-
The following hyperparameters were used during training:
|
27 |
-
- learning_rate: 2e-05
|
28 |
-
- train_batch_size: 1
|
29 |
-
- eval_batch_size: 1
|
30 |
-
- seed: 42
|
31 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
32 |
-
- lr_scheduler_type: linear
|
33 |
-
- num_epochs: 1
|
34 |
-
- mixed_precision_training: Native AMP
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
base_model: t5-small
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- fr
|
7 |
+
- de
|
8 |
+
- es
|
|
|
|
|
9 |
---
|
10 |
|
11 |
+
**Topical** is a small language model specialized for topic extraction. Given a document Pleias-Topic-Deduction will return a main topic that can be used for further downstream tasks (annotation, embedding indexation)
|
|
|
12 |
|
13 |
+
Like other model from PleIAs Bad Data Toolbox, Topical has been volontarily trained on 70,000 documents extracted from Common Corpus with a various range of digitization artifact.
|
14 |
|
15 |
+
Topical is a lightweight model (70 million parameters) tha can be especially used for classification at scale on a large corpus.
|
16 |
|
17 |
+
## Example
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|