Instructions to use lighteternal/SSE-TUC-mt-en-el-lowercase with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lighteternal/SSE-TUC-mt-en-el-lowercase with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="lighteternal/SSE-TUC-mt-en-el-lowercase")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("lighteternal/SSE-TUC-mt-en-el-lowercase") model = AutoModelForSeq2SeqLM.from_pretrained("lighteternal/SSE-TUC-mt-en-el-lowercase") - Notebooks
- Google Colab
- Kaggle
Commit ·
0fe3604
1
Parent(s): 0e0c191
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,8 @@ metrics:
|
|
| 25 |
|
| 26 |
### Model description
|
| 27 |
|
| 28 |
-
Trained using the Fairseq framework, transformer_iwslt_de_en architecture.\
|
| 29 |
-
BPE segmentation (10k codes).\
|
| 30 |
Lower-case model.
|
| 31 |
|
| 32 |
### How to use
|
|
@@ -75,4 +75,10 @@ Results on XNLI parallel (EN-EL):
|
|
| 75 |
| 66.1 | 0.606 |
|
| 76 |
|
| 77 |
### BibTeX entry and citation info
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
### Model description
|
| 27 |
|
| 28 |
+
Trained using the Fairseq framework, transformer_iwslt_de_en architecture.\\
|
| 29 |
+
BPE segmentation (10k codes).\\
|
| 30 |
Lower-case model.
|
| 31 |
|
| 32 |
### How to use
|
|
|
|
| 75 |
| 66.1 | 0.606 |
|
| 76 |
|
| 77 |
### BibTeX entry and citation info
|
| 78 |
+
|
| 79 |
+
Dimitris Papadopoulos, et al. "PENELOPIE: Enabling Open Information Extraction for the Greek Language through Machine Translation." (2021). Accepted at EACL 2021 SRW
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Acknowledgement
|
| 83 |
+
|
| 84 |
+
The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship grant (Fellowship Number:50, 2nd call)
|