Summarization
Transformers
PyTorch
Safetensors
Russian
English
mbart
text2text-generation
dialogue-summarization
mbart-50
Instructions to use d0rj/ru-mbart-large-summ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d0rj/ru-mbart-large-summ 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="d0rj/ru-mbart-large-summ")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("d0rj/ru-mbart-large-summ") model = AutoModelForSeq2SeqLM.from_pretrained("d0rj/ru-mbart-large-summ") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -46,7 +46,7 @@ Train subset = 155678 rows.
|
|
| 46 |
|
| 47 |
Evaluation on 10% of concatenated 'validation' subsets = 1458 rows.
|
| 48 |
|
| 49 |
-
See [WandB logs](https://wandb.ai/d0rj/
|
| 50 |
|
| 51 |
See report at **REPORT WIP**.
|
| 52 |
|
|
|
|
| 46 |
|
| 47 |
Evaluation on 10% of concatenated 'validation' subsets = 1458 rows.
|
| 48 |
|
| 49 |
+
See [WandB logs](https://wandb.ai/d0rj/summarization/runs/q8w8frta).
|
| 50 |
|
| 51 |
See report at **REPORT WIP**.
|
| 52 |
|