MaartenGr commited on
Commit
e93af37
·
verified ·
1 Parent(s): 3cb659f

Add Technical Report

Browse files
Files changed (1) hide show
  1. README.md +19 -2
README.md CHANGED
@@ -14,7 +14,8 @@ pipeline_tag: any-to-any
14
  <a href="https://huggingface.co/collections/google/gemma-4" target="_blank">Hugging Face</a> |
15
  <a href="https://github.com/google-gemma" target="_blank">GitHub</a> |
16
  <a href="https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemma-4-12B/" target="_blank">Launch Blog</a> |
17
- <a href="https://ai.google.dev/gemma/docs/core" target="_blank">Documentation</a>
 
18
  <br>
19
  <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>
20
  </p>
@@ -570,4 +571,20 @@ The development of vision-language models (VLMs) raises several ethical concerns
570
 
571
  ### **Benefits**
572
 
573
- At the time of release, this family of models provides high-performance open vision-language model implementations designed from the ground up for responsible AI development compared to similarly sized models.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  <a href="https://huggingface.co/collections/google/gemma-4" target="_blank">Hugging Face</a> |
15
  <a href="https://github.com/google-gemma" target="_blank">GitHub</a> |
16
  <a href="https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemma-4-12B/" target="_blank">Launch Blog</a> |
17
+ <a href="https://ai.google.dev/gemma/docs/core" target="_blank">Documentation</a> |
18
+ <a href="https://arxiv.org/abs/2607.02770" target="_blank">Technical Report</a>
19
  <br>
20
  <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>
21
  </p>
 
571
 
572
  ### **Benefits**
573
 
574
+ At the time of release, this family of models provides high-performance open vision-language model implementations designed from the ground up for responsible AI development compared to similarly sized models.
575
+
576
+ ## **Citation**
577
+
578
+ If you find our work helpful, please consider citing it:
579
+
580
+ ```bibtex
581
+ @misc{gemmateam2026gemma4,
582
+ title={Gemma 4 Technical Report},
583
+ author={Gemma Team},
584
+ year={2026},
585
+ eprint={2607.02770},
586
+ archivePrefix={arXiv},
587
+ primaryClass={cs.CL},
588
+ url={https://arxiv.org/abs/2607.02770},
589
+ }
590
+ ```