Instructions to use AndrewChar/model-QA-5-epoch-RU with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AndrewChar/model-QA-5-epoch-RU with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="AndrewChar/model-QA-5-epoch-RU")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("AndrewChar/model-QA-5-epoch-RU") model = AutoModelForQuestionAnswering.from_pretrained("AndrewChar/model-QA-5-epoch-RU", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
8481faf
1
Parent(s): 53fa717
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# model-QA-5-epoch-RU
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [AndrewChar/diplom-prod-epoch-4-datast-sber-QA](https://huggingface.co/AndrewChar/diplom-prod-epoch-4-datast-sber-QA) on
|
|
|
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Train Loss: 1.1991
|
| 20 |
- Validation Loss: 0.0
|
|
|
|
| 14 |
|
| 15 |
# model-QA-5-epoch-RU
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [AndrewChar/diplom-prod-epoch-4-datast-sber-QA](https://huggingface.co/AndrewChar/diplom-prod-epoch-4-datast-sber-QA) on sberquad
|
| 18 |
+
dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Train Loss: 1.1991
|
| 21 |
- Validation Loss: 0.0
|