LFM2.5-ColBERT

src="https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/2b08LKpev0DNEk6DlnWkY.png" alt="Liquid AI" style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;" />

LFM2.5-ColBERT-350M

We release two new best-in-class multilingual retrieval models:

• LFM2.5-Embedding-350M — A dense bi-encoder, one vector per document. Smallest, fastest index.
• LFM2.5-ColBERT-350M — A late-interaction model. One vector per token, matched via MaxSim. Higher accuracy and better generalization at the cost of index size.

Both models are 350M params and the first bidirectional members of the LFM family, built on LFM2.5-350M-Base. They can be used as a drop-in replacement for your current RAG pipeline and target fast, cheap, and reliable multilingual / cross-lingual search across 11 languages.

Find more details about the bidirectional architecture and training recipe in our blog post.

[!NOTE] 💻 Demo: https://huggingface.co/spaces/LiquidAI/colbert-tool-selection

📄 Model details

Document length: 512 tokens   

Query length: 32 tokens

Supported languages: English, Spanish, German, French, Italian, Portuguese, Arabic, Swedish, Norwegian, Japanese, Korean.

Architecture:

ColBERT(
  (0): Transformer({'max_seq_length': 511, 'do_lower_case': False}) with Transformer model: Lfm2BidirectionalModel
  (1): Dense({'in_features': 1024, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
)

We recommend LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M for short-context retrieval use cases, such as:

• E-commerce: find products across many languages with semantic search at scale.
• FAQ and support knowledge bases: retrieve the right answer reliably across customer-facing surfaces.
• On-device semantic search: search files, emails, and notes locally on consumer hardware.
• Enterprise knowledge assistants: retrieve internal legal, financial, and technical documents across languages.

🏃 How to run

Using Sentence Transformers

This model can be used as a multi-vector (ColBERT-style late interaction) retriever directly with Sentence Transformers via the MultiVectorEncoder.

pip install "sentence-transformers>=6.0.0"

from sentence_transformers import MultiVectorEncoder

model = MultiVectorEncoder("LiquidAI/LFM2.5-ColBERT-350M", trust_remote_code=True)

query = "Which planet is known as the Red Planet?"
documents = [
    "Venus is often called Earth's twin because of its similar size and proximity.",
    "Mars, known for its reddish appearance, is often referred to as the Red Planet.",
    "Jupiter, the largest planet in our solar system, has a prominent red spot.",
    "Saturn, famous for its rings, is sometimes mistaken for the Red Planet.",
]

query_embeddings = model.encode_query([query])
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (32, 128) (17, 128)

# MaxSim late-interaction scoring (the Mars document ranks highest)
scores = model.similarity(query_embeddings, document_embeddings)
print(scores)
# tensor([[27.1621, 28.2578, 27.7266, 28.1992]])

Using PyLate

Use this model with PyLate to index and retrieve documents. The index uses FastPLAID for efficient similarity search. First, install PyLate and transformers:

pip install -U pylate

Indexing documents

Load LFM2.5-ColBERT-350M and initialize the PLAID index, then encode and index your documents:

from pylate import indexes, models, retrieve

# Step 1: Load the ColBERT model (trust_remote_code applies the bidirectional patches)
model = models.ColBERT(
    model_name_or_path="LiquidAI/LFM2.5-ColBERT-350M",
    trust_remote_code=True,
)
model.tokenizer.pad_token = model.tokenizer.eos_token

# Step 2: Initialize the PLAID index
index = indexes.PLAID(
    index_folder="pylate-index",
    index_name="index",
    override=True,  # This overwrites the existing index if any
)

# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]

documents_embeddings = model.encode(
    documents,
    batch_size=32,
    is_query=False,  # Ensure that it is set to False to indicate that these are documents, not queries
    show_progress_bar=Tru