Instructions to use mrm8488/bert2bert_shared-turkish-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mrm8488/bert2bert_shared-turkish-summarization 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="mrm8488/bert2bert_shared-turkish-summarization")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mrm8488/bert2bert_shared-turkish-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("mrm8488/bert2bert_shared-turkish-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,26 @@ widget:
|
|
| 10 |
---
|
| 11 |
|
| 12 |
|
| 13 |
-
# Turkish BERT2BERT fine-tuned on MLSUM TR for summarization
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
|
| 16 |
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
|
| 13 |
+
# Turkish BERT2BERT (shared) fine-tuned on MLSUM TR for summarization
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
## Model
|
| 17 |
+
[dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) (BERT Checkpoint)
|
| 18 |
+
|
| 19 |
+
## Dataset
|
| 20 |
+
[MLSUM tu/tr](https://huggingface.co/datasets/viewer/?dataset=mlsum)
|
| 21 |
+
|
| 22 |
+
## Results
|
| 23 |
+
|
| 24 |
+
|Set|Metric| Value|
|
| 25 |
+
|----|------|------|
|
| 26 |
+
| Test |Rouge2 - mid -precision | 32.41|
|
| 27 |
+
| Test | Rouge2 - mid - recall | 28.65|
|
| 28 |
+
| Test | Rouge2 - mid - fmeasure | 29.48|
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
|
| 34 |
|
| 35 |
|