Instructions to use staka/takomt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use staka/takomt 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="staka/takomt")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("staka/takomt") model = AutoModelForSeq2SeqLM.from_pretrained("staka/takomt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -44,7 +44,7 @@ tako_translator('This is a cat.')
|
|
| 44 |
|
| 45 |
### Eval results
|
| 46 |
|
| 47 |
-
The results of the evaluation using [tatoeba](https://tatoeba.org/ja)(randomly selected 500 sentences) are as follows:
|
| 48 |
|
| 49 |
|source |target |BLEU(*1)|
|
| 50 |
|-------|-------|--------|
|
|
|
|
| 44 |
|
| 45 |
### Eval results
|
| 46 |
|
| 47 |
+
The results of the evaluation using [tatoeba](https://tatoeba.org/ja)(randomly selected 500 sentences) are as follows:
|
| 48 |
|
| 49 |
|source |target |BLEU(*1)|
|
| 50 |
|-------|-------|--------|
|