[Models](/models)/[Embeddings](/models?category=embeddings)/lightonai/Reason-ModernColBERT

HFText EmbeddingsCC-BY-NC-4.0

# Reason-ModernColBERT

by lightonai

Late-interaction retriever trained for reasoning-intensive search queries

9.1Kdl/month

150M classparams

[HuggingFace](https://huggingface.co/lightonai/Reason-ModernColBERT)[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

Identifiers

Model ID

`lightonai/Reason-ModernColBERT`

## Deploy Reason-ModernColBERT

Single-tenant

Mixpeek has no managed extractor for this model. On a single-tenant deployment you upload the weights and a custom plugin serves them next to the rest of your pipeline.

[Read the customer-hosted guide](https://mixpeek.com/docs/customer-hosted/overview) [Talk to us about single-tenant](/demo)

## Overview

Reason-ModernColBERT is a PyLate ColBERT model fine-tuned from LightOn's GTE-ModernColBERT-v1 on the ReasonIR dataset. It targets retrieval problems where the query is not a short keyword string but a reasoning-heavy prompt that requires matching evidence across paragraphs.

On Mixpeek, this makes it a useful text retrieval companion for agents. After visual, audio, or document extractors produce text evidence, Reason-ModernColBERT can retrieve passages that match an agent's intermediate reasoning state with token-level MaxSim scoring instead of collapsing each document into one dense vector.

## Architecture

ModernBERT-based late-interaction retriever trained with PyLate. It maps queries and passages to sequences of 128-dimensional token vectors and scores them with MaxSim. The model supports 8,192-token documents and 128-token queries according to the model card.

## Mixpeek SDK Integration

IngestRetrieve

// No extractor parameter takes a Hugging Face model id (checked against
// GET /v1/discovery/extractors, which returns 13), so Reason-ModernColBERT runs
// on your side and the output is upserted through POST
// /v1/namespaces/{namespace\_id}/documents/upsert. On Enterprise the other
// path is to upload the weights instead: POST /v1/namespaces/{id}/models
// accepts the huggingface format and a custom plugin loads them.
const res = await fetch(
  "https://api.mixpeek.com/v1/namespaces/ns\_your\_namespace/documents/upsert",
  {
    method: "POST",
    headers: {
      Authorization: "Bearer API\_KEY",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      collection\_id: "col\_your\_collection",
      documents: \[
        {
          document\_id: "asset-00412",
          // The vector name has to match a vector index on the collection.
          vectors: { "text-embedding": yourVector },
          payload: { source\_key: "archive/2026/asset-00412" },
        },
      \],
    }),
  },
);

// Managed alternative, if this exact model is not the requirement:
// text\_extractor@v1 runs intfloat/multilingual-e5-large-instruct
// (1024-d) over a bucket, with no inference of your own.

## Capabilities

*   Reasoning-intensive retrieval over long passages
*   Late-interaction token matching with MaxSim
*   8K-token document support
*   Useful for agent queries that include context, constraints, and partial findings
*   Fine-tuned on ReasonIR data from GTE-ModernColBERT-v1

## Use Cases on Mixpeek

Retrieve transcript passages after an agent forms a multi-step hypothesis

Search document evidence with long, constraint-heavy queries

Rerank OCR and caption text generated from multimodal pipelines

Build retrieval tools for agents that search while they reason

## Benchmarks

Dataset

Metric

Score

Source

BRIGHT

NDCG@10

Outperforms models up to 7B

LightOn model card

Stack Exchange splits

NDCG@10

+2.5 average over ReasonIR-8B

LightOn model card

## Performance

Input Size8,192-token documents, 128-token queries

Embedding Dim128 per token

GPU LatencyInput dependent

GPU ThroughputBatch dependent

GPU MemoryModel dependent

Late interaction increases index size relative to single-vector dense retrieval

## Common Pipeline Companions

[

lightonai/GTE-ModernColBERT-v1

General-purpose late interaction baseline

](/model/lightonai/GTE-ModernColBERT-v1)[

lightonai/Agent-ModernColBERT

Agent trace retrieval for browser and tool-use workflows

](/model/lightonai/Agent-ModernColBERT)[

cross-encoder/ettin-reranker-1b-v1

Final cross-encoder reranking after candidate retrieval

](/model/cross-encoder/ettin-reranker-1b-v1)

## Explore on Mixpeek

[

More Embeddings models

Compare alternatives in this category

](/models?category=embeddings)[

Best Self-Hosted Embedding Models

Hand-picked tools & platforms compared

](/curated-lists/best-self-hosted-embedding-models)[

Instruction-Tuned Embeddings

Deep-dive technical guide

](/guides/instruction-tuned-embeddings)[

Feature Extractors

See how Mixpeek runs models as extractors

](/extractors)[

Mixpeek Vector Store

Store & search embeddings at scale

](/mvs)[

Pricing

Usage-based pricing for pipelines

](/pricing)[

All Curated Lists

Compare models, APIs & infrastructure

](/curated-lists)

### Specification

FrameworkHF

Organizationlightonai

FeatureText Embeddings

Output1024-dim vector

Modalitiesdocument, audio

RetrieverText Similarity

Parameters150M class

LicenseCC-BY-NC-4.0

Downloads/mo9.1K

[

### Research Paper

Reason-ModernColBERT

arxiv.org](https://huggingface.co/lightonai/Reason-ModernColBERT)

### Build a pipeline with Reason-ModernColBERT

Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

[Run it on your own data, free](https://studio.mixpeek.com/namespaces/create?mode=managed&utm_source=homepage&utm_medium=model_page&utm_campaign=mvs_onramp)

### Alternative Models

[

BAAI/bge-large-en-v1.5

Text Embeddings

](/model/BAAI/bge-large-en-v1.5)[

sentence-transformers/all-MiniLM-L6-v2

Text Embeddings

](/model/sentence-transformers/all-MiniLM-L6-v2)[

Qwen/Qwen3-Embedding-0.6B

Text Embeddings

](/model/Qwen/Qwen3-Embedding-0.6B)[

nomic-ai/nomic-embed-text-v2-moe

Text Embeddings

](/model/nomic-ai/nomic-embed-text-v2-moe)

### Related in Embeddings

[

openai/clip-vit-large-patch14

Visual Embeddings

](/model/openai/clip-vit-large-patch14)[

google/siglip-base-patch16-224

Visual Embeddings

](/model/google/siglip-base-patch16-224)[

google/siglip2-giant-opt-patch16-384

Visual Embeddings

](/model/google/siglip2-giant-opt-patch16-384)[

facebook/dinov2-large

Visual Embeddings

](/model/facebook/dinov2-large)