Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
Polish
roberta
feature-extraction
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use sdadas/mmlw-roberta-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sdadas/mmlw-roberta-large with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sdadas/mmlw-roberta-large") sentences = [ "zapytanie: Jak dożyć 100 lat?", "Trzeba zdrowo się odżywiać i uprawiać sport.", "Trzeba pić alkohol, imprezować i jeździć szybkimi autami.", "Gdy trwała kampania politycy zapewniali, że rozprawią się z zakazem niedzielnego handlu." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use sdadas/mmlw-roberta-large with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sdadas/mmlw-roberta-large") model = AutoModel.from_pretrained("sdadas/mmlw-roberta-large") - Inference
- Notebooks
- Google Colab
- Kaggle
Problem with load model.
#1
by janchocyk - opened
Hello,
Today I have a problem with load model. Error:
Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 71 column 3
Can I please help you with solve this problem?
It seems to be a bug or a breaking change in the latest version of transformers (4.40.0) and it affects other models too. For now, please use the previous version of the library (4.39.3)
Thanks for fast help. When I used older version library, evrything is ok.