Summarization
Transformers
PyTorch
Safetensors
French
mt5
text2text-generation
Trained with AutoTrain
Instructions to use Faradaylab/aria-synthesia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Faradaylab/aria-synthesia 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="Faradaylab/aria-synthesia")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Faradaylab/aria-synthesia") model = AutoModelForSeq2SeqLM.from_pretrained("Faradaylab/aria-synthesia") - Notebooks
- Google Colab
- Kaggle
Model Trained Using AutoTrain
- Problem type: Summarization
- Model ID: 83325142252
- CO2 Emissions (in grams): 79.3397
Validation Metrics
- Loss: 2.130
- Rouge1: 19.332
- Rouge2: 6.434
- RougeL: 15.385
- RougeLsum: 15.933
- Gen Len: 18.951
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/Faradaylab/autotrain-ariatestia-83325142252
- Downloads last month
- -