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

Gswrtz
/
finetuned-neg-rag-embedder

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:117937
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files Files and versions
xet
Community

Instructions to use Gswrtz/finetuned-neg-rag-embedder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • sentence-transformers

    How to use Gswrtz/finetuned-neg-rag-embedder with sentence-transformers:

    from sentence_transformers import SentenceTransformer
    
    model = SentenceTransformer("Gswrtz/finetuned-neg-rag-embedder")
    
    sentences = [
        "In a certain population, there are 6 times as many people aged twenty-one or under as there are people over twenty-one. The ratio of those twenty-one or under to the total population is A. 1 to 2. B. 1 to 3. C. 2 to 3. D. 6 to 7.",
        "Population size is the number of individuals in a population.",
        "Reactivity is the ability of matter to combine chemically with other substances. For example, iron is highly reactive with oxygen. When it combines with oxygen, it forms the reddish powder called rust (see Figure below ). Rust is not iron but an entirely different substance that consists of both iron and oxygen.",
        "The age-sex structure of a population is the number of individuals of each sex and age in the population. Age-sex structure influences population growth. It is represented by a population pyramid. The number of survivors at each age is plotted on a survivorship curve."
    ]
    embeddings = model.encode(sentences)
    
    similarities = model.similarity(embeddings, embeddings)
    print(similarities.shape)
    # [4, 4]
  • Notebooks
  • Google Colab
  • Kaggle
finetuned-neg-rag-embedder
91.8 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Gswrtz's picture
Gswrtz
Upload fine-tuned RAG embedding model
531dbff verified 12 months ago
  • 1_Pooling
    Upload fine-tuned RAG embedding model 12 months ago
  • .gitattributes
    1.52 kB
    initial commit 12 months ago
  • README.md
    29.9 kB
    Upload fine-tuned RAG embedding model 12 months ago
  • config.json
    617 Bytes
    Upload fine-tuned RAG embedding model 12 months ago
  • config_sentence_transformers.json
    199 Bytes
    Upload fine-tuned RAG embedding model 12 months ago
  • model.safetensors
    90.9 MB
    xet
    Upload fine-tuned RAG embedding model 12 months ago
  • modules.json
    349 Bytes
    Upload fine-tuned RAG embedding model 12 months ago
  • sentence_bert_config.json
    53 Bytes
    Upload fine-tuned RAG embedding model 12 months ago
  • special_tokens_map.json
    695 Bytes
    Upload fine-tuned RAG embedding model 12 months ago
  • tokenizer.json
    712 kB
    Upload fine-tuned RAG embedding model 12 months ago
  • tokenizer_config.json
    1.46 kB
    Upload fine-tuned RAG embedding model 12 months ago
  • vocab.txt
    232 kB
    Upload fine-tuned RAG embedding model 12 months ago