Model reference · open weights

GTE-ModernColBERT

GTE-ModernColBERT is an open-weight embedding model from lightonai, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings lightonai 1 variants 361k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What GTE-ModernColBERT is

GTE-ModernColBERT-v1 Multi-vector embedding model based on Alibaba-NLP/gte-modernbert-base This is a multi-vector (ColBERT-style late interaction) embedding model trained on the ms-marco-en-bge-gemma dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. Model Details Model Description - Model Type: Multi-vector embedding model - Base model: Alibaba-NLP/gte-modernbert-base <!-- at revision bc02f0a92d1b6dd82108036f6cb4b7b423fb7434 -- - Document Length: 300 tokens - Query Length: 32 tokens - Output Dimensionality: 128 dimensions - Similarity Function: MaxSim - Training Dataset: - ms-marco-en-bge-gemma - Language: English - License: Apache 2.0 Document length GTE-ModernColBERT has been trained with knowledge distillation on MS MARCO with a document length of 300 tokens, explaining its default value for documents length. However, as illustrated in the ModernBERT paper, ColBERT models can generalize to documents lengths way beyond their training length and GTE-ModernColBERT actually yields results way above SOTA in long-context embedding benchmarks, see LongEmbed results. Simply change adapt the document length parameter to your needs when loading the model: ModernBERT itself has only been trained on 8K context length, but it seems that GTE-ModernColBERT can generalize to even bigger context sizes, though it is not guaranteed so please perform your own benches! Model Sources - Documentation: PyLate Documentation - Repository: PyLate on GitHub - Hugging Face: PyLate models on Hugging Face Full Model Architecture Usage Sentence Transformers This model can be used with Sentence Transformers as a multi-vector (ColBERT-style late interaction) retriever via the MultiVectorEncoder: PyLate First install the PyLate library: Retrieval PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval. Indexing documents First, load the ColBERT model and initialize the Voyager index, then encode and index your documents: Note that you do

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerlightonai
TypeEmbedding models
Parameters (lead)149M
Context8k tokens
Variants1
Runs withPyLate
Based onAlibaba-NLP/gte-modernbert-base
Released2025-04-30
Popularity361k downloads / month
Likes176
LicenceOpen weights

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
GTE-ModernColBERT-v1149MBF16~0.3 GBWeights ↗

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@10.36
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@30.62
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@50.78
Py Late Information RetrievalNanoClimateFEVERMaxsim Accuracy@100.86
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@10.36
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@30.233
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@50.208
Py Late Information RetrievalNanoClimateFEVERMaxsim Precision@100.128
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@10.183
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@30.289
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@50.416
Py Late Information RetrievalNanoClimateFEVERMaxsim Recall@100.496
Py Late Information RetrievalNanoClimateFEVERMaxsim Ndcg@100.415
Py Late Information RetrievalNanoClimateFEVERMaxsim Mrr@100.527
Py Late Information RetrievalNanoClimateFEVERMaxsim Map@1000.335
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@10.88
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@30.94
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@50.96
Py Late Information RetrievalNanoDBPediaMaxsim Accuracy@100.98
Py Late Information RetrievalNanoDBPediaMaxsim Precision@10.88
Py Late Information RetrievalNanoDBPediaMaxsim Precision@30.713
Py Late Information RetrievalNanoDBPediaMaxsim Precision@50.656
Py Late Information RetrievalNanoDBPediaMaxsim Precision@100.572
Py Late Information RetrievalNanoDBPediaMaxsim Recall@10.118

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys gte-moderncolbert for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gte-moderncolbert below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gte-moderncolbert","input":"text to embed"}'

Details

Languages, data & research

Tags

PyLate onnx safetensors modernbert ColBERT multi-vector sentence-transformers sentence-similarity feature-extraction generated_from_trainer dataset_size:640000 loss:Distillation model-index text-embeddings-inference

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want GTE-ModernColBERT on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms