Update README.md
Browse files
README.md
CHANGED
@@ -18,9 +18,11 @@ To force the target language id as the first generated token, pass the `forced_b
|
|
18 |
*Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
|
19 |
|
20 |
To install `sentencepiece` run `pip install sentencepiece`
|
|
|
21 |
Note: Since the model was trained with domain tags, you should append them to the input as well.
|
22 |
-
"wmtdata newsdomain": Use for sentences in the news domain
|
23 |
-
"wmtdata otherdomain": Use for sentences in all other domain
|
|
|
24 |
```python
|
25 |
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
26 |
|
|
|
18 |
*Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
|
19 |
|
20 |
To install `sentencepiece` run `pip install sentencepiece`
|
21 |
+
|
22 |
Note: Since the model was trained with domain tags, you should append them to the input as well.
|
23 |
+
* "wmtdata newsdomain": Use for sentences in the news domain
|
24 |
+
* "wmtdata otherdomain": Use for sentences in all other domain
|
25 |
+
|
26 |
```python
|
27 |
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
28 |
|