Instructions to use ptran74/DSPFirst-Finetuning-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ptran74/DSPFirst-Finetuning-5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="ptran74/DSPFirst-Finetuning-5")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("ptran74/DSPFirst-Finetuning-5") model = AutoModelForQuestionAnswering.from_pretrained("ptran74/DSPFirst-Finetuning-5") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -90,7 +90,7 @@ Also, you should improve the Dataset either by using a **better generated questi
|
|
| 90 |
## Training and evaluation data
|
| 91 |
|
| 92 |
- `batch_size` of 6 results in 14.03 GB VRAM
|
| 93 |
-
- Utilizes `gradient_accumulation_steps` to get total batch size to
|
| 94 |
- 4.52 GB RAM
|
| 95 |
- 30% of the total questions is dedicated for evaluating.
|
| 96 |
|
|
|
|
| 90 |
## Training and evaluation data
|
| 91 |
|
| 92 |
- `batch_size` of 6 results in 14.03 GB VRAM
|
| 93 |
+
- Utilizes `gradient_accumulation_steps` to get total batch size to 516 (total batch size should be at least 256)
|
| 94 |
- 4.52 GB RAM
|
| 95 |
- 30% of the total questions is dedicated for evaluating.
|
| 96 |
|