Summarization
Transformers
PyTorch
Safetensors
Russian
t5
text2text-generation
russian
text-generation-inference
Instructions to use cointegrated/rut5-base-absum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cointegrated/rut5-base-absum 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="cointegrated/rut5-base-absum")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("cointegrated/rut5-base-absum") model = AutoModelForSeq2SeqLM.from_pretrained("cointegrated/rut5-base-absum", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
#1
by Den4ikAI - opened
README.md
CHANGED
|
@@ -17,6 +17,7 @@ This is a model for abstractive Russian summarization, based on [cointegrated/ru
|
|
| 17 |
It can be used as follows:
|
| 18 |
|
| 19 |
```python
|
|
|
|
| 20 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
| 21 |
MODEL_NAME = 'cointegrated/rut5-base-absum'
|
| 22 |
model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME)
|
|
|
|
| 17 |
It can be used as follows:
|
| 18 |
|
| 19 |
```python
|
| 20 |
+
import torch
|
| 21 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
| 22 |
MODEL_NAME = 'cointegrated/rut5-base-absum'
|
| 23 |
model = T5ForConditionalGeneration.from_pretrained(MODEL_NAME)
|