ibm-granite/granite-embedding-97m-multilingual-r2
feature-extraction model by ibm-granite
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Model Summary: Granite-Embedding-97M-Multilingual-R2 is a 97M parameter dense embedding model from the Granite Embeddings collection for high-quality multilingual text embeddings at minimal compute cost. It produces 384-dimensional vectors with a context length of up to 32,768 tokens. The model supports 200+ languages (based on the multilingual pretraining corpus of the underlying encoder), with enhanced support for 52 languages and programming code that receive explicit retrieval-pair and cross-lingual training. All training data uses permissive, enterprise-friendly licenses, plus IBM-collected and IBM-generated datasets. The model uses a bi-encoder architecture to generate high-quality embeddings from text inputs such as queries, passages, code, and documents, enabling seamless comparison through cosine similarity. Built using contrastive fine-tuning, knowledge distillation, model pruning, and vocabulary selection, granite-embedding-97m-multilingual-r2 is optimized to ensure strong alignment between query and passage embeddings across many languages while maintaining a compact model size. The Granite Embedding Multilingual R2 release consists of two multilingual embedding models,…
Read the full model card ↗ · Preview checked 2026-10-05T06:45:49.823Z
Inside the original model card — Document outline
- Granite-Embedding-97M-Multilingual-R2
- What's New in R2
- Model Details
- Supported Languages
- When to Use This Model
- Usage
- Optimized Inference and Deployment
- Evaluation Results
- Multilingual Retrieval Performance
- Model Architecture and Key Features
- Training and Optimization
- Data Collection
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
ibm-granite/granite-embedding-97m-multilingual-r2 is a feature-extraction model repository published by ibm-granite on Hugging Face. The source reports the sentence-transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- feature-extraction
- Library
- sentence-transformers
- Recent downloads (30 days)
- 98,059
- Cumulative likes
- 145
- Hugging Face trending score
- 3
- Reported safetensors parameters
- 97,441,152
- Architecture
- ModernBertModel
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-04-20T15:15:55.000Z
- Last modified
- 2026-05-18T20:17:17.000Z
Compatibility and lineage
Reported languages: ar, az, bg, bn, ca, cs, da, de, el, en, es, et, fa, fi, fr, he, hi, hr, hu, id, is, it, ja, ka, kk, km, ko, lt, lv, mr, ms, nl, no, pl, pt, ro, ru, sk, sl, sq
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-05T06:40:55.443Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.