Commit
•
f980787
1
Parent(s):
3e53bc8
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Info
|
| 2 |
-
This is a V2 of the Gemini Nano V2 weights. The reason this is a V2 is the original conversion code was heavily bugged and
|
| 3 |
|
| 4 |
# Known issues
|
| 5 |
The layer norms have an extra 2 dimensions. This will be fixed ASAP!
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- wave-on-discord/gemini-nano
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- conversational
|
| 7 |
+
---
|
| 8 |
# Info
|
| 9 |
+
This is a V2 of the Gemini Nano V2 weights. The reason this is a V2 is the original conversion code was heavily bugged and extremely slow. So Claude 3.5 Sonnet and o1-preview went in and fixed it! Now you'll notice the model has a lot more 2 dimension tensors and should, as a result, be easier to get working as a Gemma2 model!
|
| 10 |
|
| 11 |
# Known issues
|
| 12 |
The layer norms have an extra 2 dimensions. This will be fixed ASAP!
|