Summarization
Transformers
PyTorch
mt5
text2text-generation
arabic
ar
Abstractive Summarization
Generated from Trainer
Instructions to use eslamxm/mt5-base-arabic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use eslamxm/mt5-base-arabic 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="eslamxm/mt5-base-arabic")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("eslamxm/mt5-base-arabic") model = AutoModelForSeq2SeqLM.from_pretrained("eslamxm/mt5-base-arabic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Librarian Bot: Add base_model information to model
#2
by librarian-bot - opened
README.md
CHANGED
|
@@ -9,6 +9,7 @@ tags:
|
|
| 9 |
- generated_from_trainer
|
| 10 |
datasets:
|
| 11 |
- xlsum
|
|
|
|
| 12 |
model-index:
|
| 13 |
- name: mt5-base-arabic
|
| 14 |
results: []
|
|
|
|
| 9 |
- generated_from_trainer
|
| 10 |
datasets:
|
| 11 |
- xlsum
|
| 12 |
+
base_model: google/mt5-base
|
| 13 |
model-index:
|
| 14 |
- name: mt5-base-arabic
|
| 15 |
results: []
|