Mainak Manna
commited on
Commit
·
ffd5552
1
Parent(s):
d1d16a1
First version of the model
Browse files
README.md
CHANGED
@@ -6,7 +6,7 @@ tags:
|
|
6 |
datasets:
|
7 |
- dcep europarl jrc-acquis
|
8 |
widget:
|
9 |
-
- text: "
|
10 |
|
11 |
---
|
12 |
|
@@ -38,7 +38,7 @@ tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/l
|
|
38 |
device=0
|
39 |
)
|
40 |
|
41 |
-
de_text = "
|
42 |
|
43 |
pipeline([de_text], max_length=512)
|
44 |
```
|
@@ -49,12 +49,12 @@ The legal_t5_small_trans_de_en model was trained on [JRC-ACQUIS](https://wt-publ
|
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
-
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
|
53 |
-
|
54 |
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
|
55 |
|
56 |
### Preprocessing
|
57 |
|
|
|
|
|
58 |
### Pretraining
|
59 |
|
60 |
|
|
|
6 |
datasets:
|
7 |
- dcep europarl jrc-acquis
|
8 |
widget:
|
9 |
+
- text: "Eisenbahnunternehmen müssen Fahrkarten über mindestens einen der folgenden Vertriebswege anbieten: an Fahrkartenschaltern oder Fahrkartenautomaten, per Telefon, Internet oder jede andere in weitem Umfang verfügbare Informationstechnik oder in den Zügen."
|
10 |
|
11 |
---
|
12 |
|
|
|
38 |
device=0
|
39 |
)
|
40 |
|
41 |
+
de_text = "Eisenbahnunternehmen müssen Fahrkarten über mindestens einen der folgenden Vertriebswege anbieten: an Fahrkartenschaltern oder Fahrkartenautomaten, per Telefon, Internet oder jede andere in weitem Umfang verfügbare Informationstechnik oder in den Zügen."
|
42 |
|
43 |
pipeline([de_text], max_length=512)
|
44 |
```
|
|
|
49 |
|
50 |
## Training procedure
|
51 |
|
|
|
|
|
52 |
The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
|
53 |
|
54 |
### Preprocessing
|
55 |
|
56 |
+
An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
|
57 |
+
|
58 |
### Pretraining
|
59 |
|
60 |
|