Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,10 @@ license: llama3.3
|
|
| 3 |
base_model:
|
| 4 |
- meta-llama/Llama-3.2-90B-Vision-Instruct
|
| 5 |
- meta-llama/Llama-3.3-70B-Vision-Instruct
|
| 6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
base_model:
|
| 4 |
- meta-llama/Llama-3.2-90B-Vision-Instruct
|
| 5 |
- meta-llama/Llama-3.3-70B-Vision-Instruct
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# gghfez/Llama-3.3-90B-Vision-merged
|
| 9 |
+
|
| 10 |
+
Since Meta have finished up with Llama3 and likely won't be releasing a version 3.3 for their vision model, I've swapped out all the text layers from Llama-3.2-90B-Vision-Instruct (which are identical to Llama-3.1-70B-instruct) with those from Llama-3.3-70b-instruct) so we can get the benefits of Llama3.3-70b-Instruct when doing vision tasks.
|
| 11 |
+
|
| 12 |
+
I've switched to this model now and it's working as expected. If anyone has a comprehensive vision benchmark let me know. I'd be curious to see if there's a measurable performance improvement.
|