Summarization
Transformers
Safetensors
English
bart
text2text-generation
fine-tuning
bart-large
xsum
Instructions to use bhargavis/fulltrain-xsum-bart with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bhargavis/fulltrain-xsum-bart 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="bhargavis/fulltrain-xsum-bart")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("bhargavis/fulltrain-xsum-bart") model = AutoModelForSeq2SeqLM.from_pretrained("bhargavis/fulltrain-xsum-bart", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -61,8 +61,9 @@ These metrics were computed using the `rouge_scorer` library for ROUGE scores.
|
|
| 61 |
#### Training Arguments
|
| 62 |
The model was trained using the following Hugging Face Seq2SeqTrainingArguments:
|
| 63 |
|
| 64 |
-
|
|
| 65 |
| ------------- |:-------------:|
|
|
|
|
| 66 |
| Logging Steps | 1000 |
|
| 67 |
| Dataloader Workers | 4 |
|
| 68 |
| Predict with Generate | True |
|
|
|
|
| 61 |
#### Training Arguments
|
| 62 |
The model was trained using the following Hugging Face Seq2SeqTrainingArguments:
|
| 63 |
|
| 64 |
+
| Arguments | Value |
|
| 65 |
| ------------- |:-------------:|
|
| 66 |
+
| Save Strategy | Per Epoch |
|
| 67 |
| Logging Steps | 1000 |
|
| 68 |
| Dataloader Workers | 4 |
|
| 69 |
| Predict with Generate | True |
|