LeoCordoba/CC-NEWS-ES-titles
Viewer • Updated • 402k • 299 • 3
How to use LeoCordoba/beto2beto-cc-news-es-titles 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="LeoCordoba/beto2beto-cc-news-es-titles") # Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("LeoCordoba/beto2beto-cc-news-es-titles")
model = AutoModelForSeq2SeqLM.from_pretrained("LeoCordoba/beto2beto-cc-news-es-titles", device_map="auto"){
"num_train_epochs": 3,
"seed": 7,
"summary_column": "output_text",
"text_column": "text",
"encoder_max_length" : 512,
"decoder_max_length" :36,
"batch_size" : 256
}
| key | value |
|---|---|
| eval loss | 4.539857387542725 |
| eval_rouge1 | 23.7478 |
| eval_rouge2 | 7.3616 |
| eval_rougeL | 20.6615 |
| eval_rougeLsum | 20.7371 |
| eval_gen_len | 16.1806 |
| test loss | 4.515065670013428 |
| test_rouge1 | 23.7415 |
| test_rouge2 | 7.3548 |
| test_rougeL | 20.746 |
| test_rougeLsum | 20.8149 |
| test_gen_len | 16.1926 |