Granite Embedding Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912250572308480 |
|---|---|
| author | Awasthy, Parul Trivedi, Aashka Li, Yulong Bornea, Mihaela Cox, David Daniels, Abraham Franz, Martin Goodhart, Gabe Iyer, Bhavani Kumar, Vishwajeet Lastras, Luis McCarley, Scott Murthy, Rudra P, Vignesh Rosenthal, Sara Roukos, Salim Sen, Jaydeep Sharma, Sukriti Sil, Avirup Soule, Kate Sultan, Arafat Florian, Radu |
| author_facet | Awasthy, Parul Trivedi, Aashka Li, Yulong Bornea, Mihaela Cox, David Daniels, Abraham Franz, Martin Goodhart, Gabe Iyer, Bhavani Kumar, Vishwajeet Lastras, Luis McCarley, Scott Murthy, Rudra P, Vignesh Rosenthal, Sara Roukos, Salim Sen, Jaydeep Sharma, Sukriti Sil, Avirup Soule, Kate Sultan, Arafat Florian, Radu |
| contents | We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks, spanning dense-retrieval and sparse retrieval architectures, with both English and Multilingual capabilities. This report provides the technical details of training these highly effective 12 layer embedding models, along with their efficient 6 layer distilled counterparts. Extensive evaluations show that the models, developed with techniques like retrieval oriented pretraining, contrastive finetuning, knowledge distillation, and model merging significantly outperform publicly available models of similar sizes on both internal IBM retrieval and search tasks, and have equivalent performance on widely used information retrieval benchmarks, while being trained on high-quality data suitable for enterprise use. We publicly release all our Granite Embedding models under the Apache 2.0 license, allowing both research and commercial use at https://huggingface.co/collections/ibm-granite. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20204 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Granite Embedding Models Awasthy, Parul Trivedi, Aashka Li, Yulong Bornea, Mihaela Cox, David Daniels, Abraham Franz, Martin Goodhart, Gabe Iyer, Bhavani Kumar, Vishwajeet Lastras, Luis McCarley, Scott Murthy, Rudra P, Vignesh Rosenthal, Sara Roukos, Salim Sen, Jaydeep Sharma, Sukriti Sil, Avirup Soule, Kate Sultan, Arafat Florian, Radu Information Retrieval Computation and Language We introduce the Granite Embedding models, a family of encoder-based embedding models designed for retrieval tasks, spanning dense-retrieval and sparse retrieval architectures, with both English and Multilingual capabilities. This report provides the technical details of training these highly effective 12 layer embedding models, along with their efficient 6 layer distilled counterparts. Extensive evaluations show that the models, developed with techniques like retrieval oriented pretraining, contrastive finetuning, knowledge distillation, and model merging significantly outperform publicly available models of similar sizes on both internal IBM retrieval and search tasks, and have equivalent performance on widely used information retrieval benchmarks, while being trained on high-quality data suitable for enterprise use. We publicly release all our Granite Embedding models under the Apache 2.0 license, allowing both research and commercial use at https://huggingface.co/collections/ibm-granite. |
| title | Granite Embedding Models |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2502.20204 |