Instructions to use SZTAKI-HLT/mT5-base-HunSum-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SZTAKI-HLT/mT5-base-HunSum-2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" 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("summarization", model="SZTAKI-HLT/mT5-base-HunSum-2")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("SZTAKI-HLT/mT5-base-HunSum-2") model = AutoModelForMultimodalLM.from_pretrained("SZTAKI-HLT/mT5-base-HunSum-2") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,8 @@ inference:
|
|
| 14 |
max_length: 128
|
| 15 |
encoder_no_repeat_ngram_size: 4
|
| 16 |
no_repeat_ngram_size: 3
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# Model Card for mT5-base-HunSum-2
|
|
@@ -46,4 +48,4 @@ The model is based on [google/mt5-base](https://huggingface.co/google/mt5-base).
|
|
| 46 |
| :------------ | :------------------------------------------ |
|
| 47 |
| ROUGE-1 | 40.06 |
|
| 48 |
| ROUGE-2 | 12.67 |
|
| 49 |
-
| ROUGE-L | 25.93 |
|
|
|
|
| 14 |
max_length: 128
|
| 15 |
encoder_no_repeat_ngram_size: 4
|
| 16 |
no_repeat_ngram_size: 3
|
| 17 |
+
base_model:
|
| 18 |
+
- google/mt5-base
|
| 19 |
---
|
| 20 |
|
| 21 |
# Model Card for mT5-base-HunSum-2
|
|
|
|
| 48 |
| :------------ | :------------------------------------------ |
|
| 49 |
| ROUGE-1 | 40.06 |
|
| 50 |
| ROUGE-2 | 12.67 |
|
| 51 |
+
| ROUGE-L | 25.93 |
|