ReMatch-3B

by FireRedTeam

Multimodal retriever trained with generative matching for stronger query-item alignment

35dl/month

3Bparams

HuggingFace Use in Pipeline

Identifiers

Model ID

FireRedTeam/ReMatch-3B

Feature URI

mixpeek://image_extractor@v1/fireredteam_rematch_3b_v1

Overview

ReMatch turns a multimodal LLM into a retrieval model by adding a chat-style generative matching objective. Instead of relying only on contrastive pairs, it teaches the model to reason about whether a query and candidate match, then distills that signal into retrieval embeddings.

On Mixpeek, ReMatch is relevant for agent retrieval when queries are specific, compositional, or visual-textual, such as finding a frame where a person is doing one action while an object appears in a certain place.

Architecture

3B multimodal retriever with learnable representation tokens and a generative matching training objective. The model supports English and Chinese according to the model card.

Mixpeek SDK Integration

import { Mixpeek } from "mixpeek";

const mx = new Mixpeek({ apiKey: "API_KEY" });

await mx.collections.ingest({
  collection_id: "evidence-library",
  source: { url: "https://example.com/camera-stills/" },
  feature_extractors: [{
    feature: "multimodal_embedding",
    model: "FireRedTeam/ReMatch-3B"
  }]
});

Capabilities

Multimodal retrieval from image and text inputs
Generative matching objective for hard query-candidate pairs
Single-vector retrieval path with richer alignment than plain contrastive training
Apache 2.0 license