Instructions to use raphaelmerx/ko-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use raphaelmerx/ko-en 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="raphaelmerx/ko-en")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("raphaelmerx/ko-en") model = AutoModelForSeq2SeqLM.from_pretrained("raphaelmerx/ko-en") - Notebooks
- Google Colab
- Kaggle
Commit ·
be7d85f
1
Parent(s): f049402
README: mention fork
Browse files
README.md
CHANGED
|
@@ -13,6 +13,8 @@ library_name: transformers
|
|
| 13 |
---
|
| 14 |
# Model info
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Distilled model from a Tatoeba-MT Teacher: [Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28.zip), which has been trained on the [Tatoeba](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/data) dataset.
|
| 17 |
|
| 18 |
We used the [OpusDistillery](https://github.com/Helsinki-NLP/OpusDistillery) to train new a new student with the tiny architecture, with a regular transformer decoder.
|
|
@@ -33,4 +35,4 @@ The configuration file fed into OpusDistillery can be found [here](https://githu
|
|
| 33 |
|
| 34 |
| testset | BLEU | chr-F |
|
| 35 |
|-----------------------|-------|-------|
|
| 36 |
-
| flores200 | 20.3 | 50.3 |
|
|
|
|
| 13 |
---
|
| 14 |
# Model info
|
| 15 |
|
| 16 |
+
Forked from [odegiber/ko-en](https://huggingface.co/odegiber/ko-en), with a `.tflite` version of the model weights added.
|
| 17 |
+
|
| 18 |
Distilled model from a Tatoeba-MT Teacher: [Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28](https://object.pouta.csc.fi/Tatoeba-MT-models/kor-eng/opusTCv20210807-sepvoc_transformer-big_2022-07-28.zip), which has been trained on the [Tatoeba](https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/data) dataset.
|
| 19 |
|
| 20 |
We used the [OpusDistillery](https://github.com/Helsinki-NLP/OpusDistillery) to train new a new student with the tiny architecture, with a regular transformer decoder.
|
|
|
|
| 35 |
|
| 36 |
| testset | BLEU | chr-F |
|
| 37 |
|-----------------------|-------|-------|
|
| 38 |
+
| flores200 | 20.3 | 50.3 |
|