bebechien commited on
Commit
2671115
·
verified ·
1 Parent(s): 21ad7b3

Add Technical Report

Browse files
Files changed (1) hide show
  1. README.md +17 -1
README.md CHANGED
@@ -27,7 +27,7 @@ library_name: transformers
27
  <a href="https://huggingface.co/google/embeddinggemma-2" target="_blank">Hugging Face</a> |
28
  <a href="https://github.com/google-gemma" target="_blank">GitHub</a> |
29
  <a href="https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2" target="_blank">Launch Blog</a> |
30
- <a href="https://ai.google.dev/gemma/docs/embeddinggemma" target="_blank">Documentation</a> |
31
  <br>
32
  <b>License</b>: <a href="https://ai.google.dev/gemma/docs/gemma_4_license" target="_blank">Apache 2.0</a> | <b>Authors</b>: <a href="https://deepmind.google/models/gemma/" target="_blank">Google DeepMind</a>
33
  </p>
@@ -333,3 +333,19 @@ In creating an open embedding model, we have carefully considered the following:
333
  EmbeddingGemma 2 is among the strongest multimodal embedding models under 1B parameters. We’re excited to see how developers will use and adapt this model for on-device or edge AI applications.&nbsp;
334
 
335
  The model is designed from the ground up for responsible AI development, like other Gemma-family models.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  <a href="https://huggingface.co/google/embeddinggemma-2" target="_blank">Hugging Face</a> |
28
  <a href="https://github.com/google-gemma" target="_blank">GitHub</a> |
29
  <a href="https://blog.google/innovation-and-ai/technology/developers-tools/embeddinggemma-2" target="_blank">Launch Blog</a> |
30
+ <a href="https://ai.google.dev/gemma/docs/embeddinggemma" target="_blank">Documentation</a> | <a href="https://arxiv.org/abs/2610.37364" target="_blank">Technical Report</a>
31
  <br>
32
  <b>License</b>: <a href="https://ai.google.dev/gemma/docs/gemma_4_license" target="_blank">Apache 2.0</a> | <b>Authors</b>: <a href="https://deepmind.google/models/gemma/" target="_blank">Google DeepMind</a>
33
  </p>
 
333
  EmbeddingGemma 2 is among the strongest multimodal embedding models under 1B parameters. We’re excited to see how developers will use and adapt this model for on-device or edge AI applications.&nbsp;
334
 
335
  The model is designed from the ground up for responsible AI development, like other Gemma-family models.
336
+
337
+ ## **Citation**
338
+
339
+ If you find our work helpful, please consider citing it:
340
+
341
+ ```bibtex
342
+ @misc{embeddinggemma2_2026,
343
+ title={EmbeddingGemma 2: Unified and Efficient Multimodal Representations},
344
+ author={Schechter Vera, Henrique and Dua, Sahil and Team, EmbeddingGemma},
345
+ year={2026},
346
+ eprint={2610.37364},
347
+ archivePrefix={arXiv},
348
+ primaryClass={cs.LG},
349
+ url={https://arxiv.org/abs/2610.37364}
350
+ }
351
+ ```