Instructions to use a5u7/roberta_t3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use a5u7/roberta_t3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="a5u7/roberta_t3")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("a5u7/roberta_t3") model = AutoModel.from_pretrained("a5u7/roberta_t3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
3d1d74b
1
Parent(s): ad17411
Rename roberta_t3_config.json to config.json
Browse files
roberta_t3_config.json → config.json
RENAMED
|
@@ -15,8 +15,8 @@
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 514,
|
| 17 |
"model_type": "roberta",
|
| 18 |
-
"num_attention_heads":
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
"transformers_version": "4.27.4",
|
|
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 514,
|
| 17 |
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 18,
|
| 19 |
+
"num_hidden_layers": 9,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
"transformers_version": "4.27.4",
|