Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

RamsesDIIP
/
me5-large-construction-v2

Sentence Similarity
sentence-transformers
Safetensors
multilingual
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:1765
loss:TripletLoss
Eval Results (legacy)
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use RamsesDIIP/me5-large-construction-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use RamsesDIIP/me5-large-construction-v2 with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("RamsesDIIP/me5-large-construction-v2")
    
    sentences = [
        "Pavimento de piedra calcárea nacional serrada y sin pulir, precio alto, de 40 mm de espesor con arista viva en los cuatro bordes 1251 a 2500 cm2, colocada a pique de maceta con mortero cemento 1:6",
        "Bordillo de hormigón recto con canaleta, de una sola capa, dimensiones 40x35 cm, instalado sobre una base de hormigón no estructural de 25 a 30 cm de altura y sellado con mortero.",
        "Pavimento de piedra caliza nacional, sin pulir y con un grosor de 40 mm, con bordes afilados, en un rango de 1251 a 2500 cm2, instalado en macetas utilizando mortero de cemento en una proporción de 1:6, a un precio elevado.",
        "Pavimento de cerámica esmaltada de importación, precio bajo, de 10 mm de espesor con bordes redondeados en los cuatro lados 500 a 1000 cm2, instalada en superficie plana con adhesivo flexible."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Notebooks
  • Google Colab
  • Kaggle
me5-large-construction-v2
2.26 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
RamsesDIIP's picture
RamsesDIIP
Add new SentenceTransformer model
1518227 verified over 1 year ago
  • 1_Pooling
    Add new SentenceTransformer model over 1 year ago
  • .gitattributes
    1.57 kB
    Add new SentenceTransformer model over 1 year ago
  • README.md
    41 kB
    Add new SentenceTransformer model over 1 year ago
  • config.json
    716 Bytes
    Add new SentenceTransformer model over 1 year ago
  • config_sentence_transformers.json
    201 Bytes
    Add new SentenceTransformer model over 1 year ago
  • model.safetensors
    2.24 GB
    xet
    Add new SentenceTransformer model over 1 year ago
  • modules.json
    349 Bytes
    Add new SentenceTransformer model over 1 year ago
  • sentence_bert_config.json
    53 Bytes
    Add new SentenceTransformer model over 1 year ago
  • sentencepiece.bpe.model
    5.07 MB
    xet
    Add new SentenceTransformer model over 1 year ago
  • special_tokens_map.json
    964 Bytes
    Add new SentenceTransformer model over 1 year ago
  • tokenizer.json
    17.1 MB
    xet
    Add new SentenceTransformer model over 1 year ago
  • tokenizer_config.json
    1.15 kB
    Add new SentenceTransformer model over 1 year ago