update readme
Browse files
README.md
CHANGED
|
@@ -133,6 +133,8 @@ language:
|
|
| 133 |
|
| 134 |
`flores101_mm100_175M` is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation. It was introduced in this [paper](https://aclanthology.org/2022.tacl-1.30) and released in [this](https://github.com/facebookresearch/fairseq/tree/main/examples/flores101) repository.
|
| 135 |
|
|
|
|
|
|
|
| 136 |
```python
|
| 137 |
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
|
| 138 |
|
|
|
|
| 133 |
|
| 134 |
`flores101_mm100_175M` is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation. It was introduced in this [paper](https://aclanthology.org/2022.tacl-1.30) and released in [this](https://github.com/facebookresearch/fairseq/tree/main/examples/flores101) repository.
|
| 135 |
|
| 136 |
+
The model architecture and config are the same as [M2M100](https://huggingface.co/facebook/m2m100_418M) implementation, but the **tokenizer should be modified** to adjust language codes.
|
| 137 |
+
|
| 138 |
```python
|
| 139 |
from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
|
| 140 |
|