Summarization
Transformers
PyTorch
Enawené-Nawé
mt5
text2text-generation
Trained with AutoTrain
Eval Results (legacy)
Instructions to use ell-hol/mT5-OrangeSum with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ell-hol/mT5-OrangeSum 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="ell-hol/mT5-OrangeSum")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("ell-hol/mT5-OrangeSum") model = AutoModelForMultimodalLM.from_pretrained("ell-hol/mT5-OrangeSum") - Notebooks
- Google Colab
- Kaggle
Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 2638979565
- CO2 Emissions (in grams): 675.7790
Validation Metrics
- Loss: 1.631
- Rouge1: 33.348
- Rouge2: 14.481
- RougeL: 24.210
- RougeLsum: 25.514
- Gen Len: 48.497
Usage
You can use cURL to access this model:
$ curl -X POST -H "Authorization: Bearer YOUR_HUGGINGFACE_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/ell-hol/autotrain-test-orangesum-2638979565
- Downloads last month
- 4
Evaluation results
- ROUGE-1 on orange_sumvalidation set verified33.377
- ROUGE-2 on orange_sumvalidation set verified14.447
- ROUGE-L on orange_sumvalidation set verified24.190
- ROUGE-LSUM on orange_sumvalidation set verified25.528
- loss on orange_sumvalidation set verified1.635
- gen_len on orange_sumvalidation set verified48.497