embedding

harrier-oss-v1-0.6b

Open multilingual text embedding model from Microsoft for retrieval and semantic similarity; a 270M version is also released.

Microsoft AIUSA

Levelmodel

Classembedding

Parameters596.05M

Contextnot in the notes

Released30 Mar 2026

Opennessopen weights permissive

Runs onnot in the notes

Statusactive

R&D Topics

Retrieval-augmented generation (RAG)used by Text embeddings for semantic searchproduced by

Identity

Developer: Microsoft AI
Family: not in the notes
Released: 30 Mar 2026 sourcesregistry date
Weights published: –
Record checked: 12 Oct 2026

Where this comes from

Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture: dense transformer
Total parameters: 596.05M sources
Active parameters: –
Checkpoint parameters: –
Note: Parameter count from the safetensors index on Hugging Face.
Context length: not in the notes
Input: text
Output: text

Where this comes from

Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness: open weights permissive
Licence: MIT License sources
Access routes: open weights download

Where this comes from

The licence file governs over registry tags and aggregator labels.

Deployment

Runs on: not in the notes
Footprint: not in the notes
Runtimes: not in the notes

Where this comes from

Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support: listed by developer
Regional languages: Javanese, Khmer, Lao, Malay, Burmese, Sundanese, Thai, Tagalog, Vietnamese
Jakarta hosting: unknown
Languages: Model card lists 94 languages, including Indonesian

Where this comes from

Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Links

Developer

Microsoft AIbig tech, USA

Model

harrier-oss-v1-0.6bMicrosoft AI, embedding

R&D TopicsRetrieval-Augmented Generation (RAG)Text Embeddings for Semantic Search

Use CasesEmbeddings and Retrieval for SEA LanguagesPublic SectorUse cases of models in the same R&D topic; none is recorded for this model itself.

Who Runs Itnone recordedDeployments of these use cases; none names this model.

Graph

Organisations 1

Microsoft AIbig tech, USADeveloper

R&D topics 2

Retrieval-Augmented Generation (RAG)Grounding generation in retrieved documents.used by Text Embeddings for Semantic SearchTraining encoders that turn text in many languages into vectors so that search, clusterin…produced by

Sources

huggingface.co/microsoft/harrier-oss-v1-0.6b https://huggingface.co/microsoft/harrier-oss-v1-0.6b
ai.azure.com/catalog/models?task=embeddings https://ai.azure.com/catalog/models?task=embeddings
keras.io/keras_hub/presets https://keras.io/keras_hub/presets/

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Harrier-Oss-v1-0.6b", https://aurion.semai.id/models/microsoft-harrier-oss-v1-0-6b/, records of October 2026.