Instructions to use google/roberta2roberta_L-24_bbc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/roberta2roberta_L-24_bbc with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="google/roberta2roberta_L-24_bbc")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("google/roberta2roberta_L-24_bbc") model = AutoModelForSeq2SeqLM.from_pretrained("google/roberta2roberta_L-24_bbc") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -39,7 +39,7 @@
|
|
| 39 |
"max_length": 20,
|
| 40 |
"max_position_embeddings": 512,
|
| 41 |
"min_length": 0,
|
| 42 |
-
"model_type": "bert-
|
| 43 |
"no_repeat_ngram_size": 0,
|
| 44 |
"num_attention_heads": 16,
|
| 45 |
"num_beams": 1,
|
|
@@ -101,7 +101,7 @@
|
|
| 101 |
"max_length": 20,
|
| 102 |
"max_position_embeddings": 512,
|
| 103 |
"min_length": 0,
|
| 104 |
-
"model_type": "bert-
|
| 105 |
"no_repeat_ngram_size": 0,
|
| 106 |
"num_attention_heads": 16,
|
| 107 |
"num_beams": 1,
|
|
|
|
| 39 |
"max_length": 20,
|
| 40 |
"max_position_embeddings": 512,
|
| 41 |
"min_length": 0,
|
| 42 |
+
"model_type": "bert-generation",
|
| 43 |
"no_repeat_ngram_size": 0,
|
| 44 |
"num_attention_heads": 16,
|
| 45 |
"num_beams": 1,
|
|
|
|
| 101 |
"max_length": 20,
|
| 102 |
"max_position_embeddings": 512,
|
| 103 |
"min_length": 0,
|
| 104 |
+
"model_type": "bert-generation",
|
| 105 |
"no_repeat_ngram_size": 0,
|
| 106 |
"num_attention_heads": 16,
|
| 107 |
"num_beams": 1,
|