Instructions to use klue/roberta-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use klue/roberta-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="klue/roberta-base")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("klue/roberta-base") model = AutoModelForMaskedLM.from_pretrained("klue/roberta-base") - Inference
- Notebooks
- Google Colab
- Kaggle
james.ryu commited on
Commit ·
41b3d9b
1
Parent(s): 436ec9c
fix: model_max_length to 514
Browse files- config.json +1 -1
- tokenizer_config.json +1 -1
config.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 3072,
|
| 12 |
"layer_norm_eps": 1e-05,
|
| 13 |
-
"max_position_embeddings":
|
| 14 |
"model_type": "roberta",
|
| 15 |
"num_attention_heads": 12,
|
| 16 |
"num_hidden_layers": 12,
|
|
|
|
| 10 |
"initializer_range": 0.02,
|
| 11 |
"intermediate_size": 3072,
|
| 12 |
"layer_norm_eps": 1e-05,
|
| 13 |
+
"max_position_embeddings": 514,
|
| 14 |
"model_type": "roberta",
|
| 15 |
"num_attention_heads": 12,
|
| 16 |
"num_hidden_layers": 12,
|
tokenizer_config.json
CHANGED
|
@@ -11,5 +11,5 @@
|
|
| 11 |
"eos_token": "[SEP]",
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
"strip_accents": null,
|
| 14 |
-
"model_max_length":
|
| 15 |
}
|
|
|
|
| 11 |
"eos_token": "[SEP]",
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
"strip_accents": null,
|
| 14 |
+
"model_max_length": 514
|
| 15 |
}
|