Translation
Transformers
PyTorch
Safetensors
m2m_100
text2text-generation
seq2seq
relation-extraction
Instructions to use Babelscape/mrebel-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Babelscape/mrebel-base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" 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("translation", model="Babelscape/mrebel-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Babelscape/mrebel-base") model = AutoModelForSeq2SeqLM.from_pretrained("Babelscape/mrebel-base") - Inference
- Notebooks
- Google Colab
- Kaggle
mrebel-base output interpretation
#2
by Ankush-Chander - opened
Hi team,
Thanks for the work you have put in the model.
Upon running the base model on example text, I get following output:
text: text = 'The Red Hot Chili Peppers were formed in Los Angeles by Kiedis, Flea, guitarist Hillel Slovak and drummer Jack Irons.'
output seq:
__en__ __sv__ Red Hot Chili Peppers __vi__ Los Angeles __tn__ location of formation</s>
__en__ __sv__ Hillel Slovak __uk__ Red Hot Chili Peppers __vi__ part of</s>
__en__ __sv__ Red Hot Chili Peppers __vi__ Los Angeles __tn__ location of formation __sv__ Kiedis __uk__ Red Hot Chili Peppers __vi__ part of</s>
How to interpret the separators like dunder-en , dunder-sv, dunder-vi, dunder-uk etc?
My end goal is to finetune mrebel-base for triplet extraction in English?
Thanks in advance.
Ankush-Chander changed discussion status to closed