mdbr leaf mt

from sentence_transformers import SentenceTransformer  
  
# Load the model  
model = SentenceTransformer("MongoDB/mdbr-leaf-mt")  
  
# Example queries and documents  
queries = [
    "What is machine learning?",  
    "How does neural network training work?"  
]  
  
documents = [  
    "Machine learning is a subset of artificial intelligence that focuses on algorithms that can learn from data.",  
    "Neural networks are trained through backpropagation, adjusting weights to minimize prediction errors."  
]  
  
# Encode queries and documents  
query_embeddings = model.encode(queries, prompt_name="query")  
document_embeddings = model.encode(documents)  
  
# Compute similarity scores  
scores = model.similarity(query_embeddings, document_embeddings)  

# Print results
for i, query in enumerate(queries):
    print(f"Query: {query}")
    for j, doc in enumerate(documents):
        print(f" Similarity: {scores[i, j]:.4f} | Document {j}: {doc[:80]}...")

npm i @huggingface/transformers

import { AutoModel, AutoTokenizer, matmul } from "@huggingface/transformers";

// Download from the 🤗 Hub
const model_id = "MongoDB/mdbr-leaf-mt";
const tokenizer = await AutoTokenizer.from_pretrained(model_id);
const model = await AutoModel.from_pretrained(model_id, {
    dtype: "fp32", // Options: "fp32" | "fp16" | "q8" | "q4" | "q4f16"
});

// Prepare queries and documents
const queries = [
    "What is machine learning?",
    "How does neural network training work?",
];
const documents = [  
    "Machine learning is a subset of artificial intelligence that focuses on algorithms that can learn from data.",
    "Neural networks are trained through backpropagation, adjusting weights to minimize prediction errors.",
];
const inputs = await tokenizer([
    ...queries.map((x) => "Represent this sentence for searching relevant passages: " + x),
    ...documents,
], { padding: true });

// Generate embeddings
const { sentence_embedding } = await model(inputs);
const normalized_sentence_embedding = sentence_embedding.normalize();

// Compute similarities
const scores = await matmul(
    normalized_sentence_embedding.slice([0, queries.length]),
    normalized_sentence_embedding.slice([queries.length, null]).transpose(1, 0),
);
const scores_list = scores.tolist();

for (let i = 0; i < queries.length; ++i) {
    console.log(`Query: ${queries[i]}`);
    for (let j = 0; j < documents.length; ++j) {
        console.log(` Similarity: ${scores_list[i][j].toFixed(4)} | Document ${j}: ${documents[j]}`);
    }
    console.log();
}

# Use mdbr-leaf-mt for query encoding (real-time, low latency)  
query_model = SentenceTransformer("MongoDB/mdbr-leaf-mt")  
query_embeddings = query_model.encode(queries, prompt_name="query")  

# Use a larger model for document encoding (one-time, at index time)  
doc_model = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")  
document_embeddings = doc_model.encode(documents)  
  
# Compute similarities  
scores = query_model.similarity(query_embeddings, document_embeddings)  

query_embeds = model.encode(queries, prompt_name="query", truncate_dim=256)
doc_embeds = model.encode(documents, truncate_dim=256)

similarities = model.similarity(query_embeds, doc_embeds)

print('After MRL:')
print(f"* Embeddings dimension: {query_embeds.shape[1]}")
print(f"* Similarities: \n\t{similarities}")

from sentence_transformers.quantization import quantize_embeddings
import torch

query_embeds = model.encode(queries, prompt_name="query")
doc_embeds = model.encode(documents)

# Quantize embeddings to int8 using -1.0 and +1.0
ranges = torch.tensor([[-1.0], [+1.0]]).expand(2, query_embeds.shape[1]).cpu().numpy()
query_embeds = quantize_embeddings(query_embeds, "int8", ranges=ranges)
doc_embeds = quantize_embeddings(doc_embeds, "int8", ranges=ranges)

# Calculate similarities; cast to int64 to avoid under/overflow
similarities = query_embeds.astype(int) @ doc_embeds.astype(int).T

print('After quantization:')
print(f"* Embeddings type: {query_embeds.dtype}")
print(f"* Similarities: \n{similarities}")

@misc{mdbr_leaf,
      title={LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations}, 
      author={Robin Vujanic and Thomas Rueckstiess},
      year={2025},
      eprint={2509.12539},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2509.12539}, 
}