Instructions to use google/bert2bert_L-24_wmt_de_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/bert2bert_L-24_wmt_de_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="google/bert2bert_L-24_wmt_de_en")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/bert2bert_L-24_wmt_de_en") model = AutoModelForSeq2SeqLM.from_pretrained("google/bert2bert_L-24_wmt_de_en", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -129,7 +129,7 @@
|
|
| 129 |
"eos_token_id": 1,
|
| 130 |
"is_encoder_decoder": true,
|
| 131 |
"max_length": 128,
|
| 132 |
-
"model_type": "
|
| 133 |
"num_beams": 4,
|
| 134 |
"pad_token_id": 0,
|
| 135 |
"tokenizer_class": "BertTokenizer"
|
|
|
|
| 129 |
"eos_token_id": 1,
|
| 130 |
"is_encoder_decoder": true,
|
| 131 |
"max_length": 128,
|
| 132 |
+
"model_type": "encoder-decoder",
|
| 133 |
"num_beams": 4,
|
| 134 |
"pad_token_id": 0,
|
| 135 |
"tokenizer_class": "BertTokenizer"
|