Instructions to use Jose-Ribeir/stt_Huggin_face_tech_new_data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jose-Ribeir/stt_Huggin_face_tech_new_data with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" 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("question-answering", model="Jose-Ribeir/stt_Huggin_face_tech_new_data")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Jose-Ribeir/stt_Huggin_face_tech_new_data") model = AutoModelForQuestionAnswering.from_pretrained("Jose-Ribeir/stt_Huggin_face_tech_new_data", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training complete
Browse files
README.md
CHANGED
|
@@ -38,7 +38,7 @@ The following hyperparameters were used during training:
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
-
- num_epochs:
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
| 44 |
### Training results
|
|
|
|
| 38 |
- seed: 42
|
| 39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 10
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
| 44 |
### Training results
|