Update README.md
Browse files
README.md
CHANGED
|
@@ -447,7 +447,7 @@ Risks identified and mitigations:
|
|
| 447 |
encouraged to adhere to privacy regulations with privacy-preserving
|
| 448 |
techniques.
|
| 449 |
|
| 450 |
-
### Benefits
|
| 451 |
|
| 452 |
At the time of release, this family of models provides high-performance open
|
| 453 |
vision-language model implementations designed from the ground up for
|
|
@@ -455,7 +455,7 @@ responsible AI development compared to similarly sized models.
|
|
| 455 |
|
| 456 |
Using the benchmark evaluation metrics described in this document, these models
|
| 457 |
have shown to provide superior performance to other, comparably-sized open model
|
| 458 |
-
alternatives
|
| 459 |
|
| 460 |
[g3-tech-report]: https://goo.gle/Gemma3Report
|
| 461 |
[rai-toolkit]: https://ai.google.dev/responsible
|
|
|
|
| 447 |
encouraged to adhere to privacy regulations with privacy-preserving
|
| 448 |
techniques.
|
| 449 |
|
| 450 |
+
### Benefits:
|
| 451 |
|
| 452 |
At the time of release, this family of models provides high-performance open
|
| 453 |
vision-language model implementations designed from the ground up for
|
|
|
|
| 455 |
|
| 456 |
Using the benchmark evaluation metrics described in this document, these models
|
| 457 |
have shown to provide superior performance to other, comparably-sized open model
|
| 458 |
+
alternatives or options
|
| 459 |
|
| 460 |
[g3-tech-report]: https://goo.gle/Gemma3Report
|
| 461 |
[rai-toolkit]: https://ai.google.dev/responsible
|