embeddinggemma-pms-32768

This model is a 58.2% smaller version of google/embeddinggemma-300m optimized for Piedmontese language via vocabulary trimming mined on Lumberjackk/fineweb-2-trimming.

Model Statistics

• Original vocabulary size: 262,144 tokens
• Trimmed vocabulary size: 32,768 tokens
• Vocabulary reduction: 87.5%
• Original model size: 302,863,104 parameters
• Trimmed model size: 126,702,336 parameters
• Size reduction: 58.2%

Usage

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("embeddinggemma-pms-32768")

# Run inference with queries and documents
query = "My query"
documents = [
    "Chunk 1",
    "Chunk 2",
    "Chunk 3",
]
query_embeddings = model.encode_query(query)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)

# Compute similarities to determine a ranking
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)