Summarization
Transformers
Safetensors
Finnish
mbart
text2text-generation
mbart50
low-resource
research
rahvusarhiiv
Eval Results (legacy)
Instructions to use Rahvusarhiiv/fi_summariser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Rahvusarhiiv/fi_summariser 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="Rahvusarhiiv/fi_summariser")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Rahvusarhiiv/fi_summariser") model = AutoModelForSeq2SeqLM.from_pretrained("Rahvusarhiiv/fi_summariser", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| dataset,eu_legalese_template_flag,examples,hit_max_new_tokens,kind,label,prediction_source_content_token_precision,prediction_words,reference_content_token_coverage,repeated_4gram_rate,rouge1_f,rouge2_f,rougeL_f | |
| news_supported_fi,0.0,253,0.0,automatic,News-supported v2 automatic,0.8563214009522284,26.09090909090909,0.25135526321861434,0.0,0.24742374710032744,0.14037243917776332,0.22090510168567307 | |
| wiki4_fi,0.0,100,0.0,automatic,Wiki4 final automatic,0.8823272809018744,53.93,0.39366923596637643,0.0,0.4065308522110746,0.2878370008587213,0.36632625050723816 | |
| gdelt_fi,0.0,100,0.0,automatic,GDELT final automatic,0.8308603512930368,23.39,0.12319378225476148,0.0,0.1346809917233249,0.044391688391582314,0.11569887351597742 | |