Update README.md
Browse files
README.md
CHANGED
|
@@ -44,7 +44,7 @@ The small size and on-device focus makes it possible to deploy in environments w
|
|
| 44 |
|
| 45 |
These model weights are designed to be used with [Transformers.js](https://huggingface.co/docs/transformers.js/en/index).
|
| 46 |
|
| 47 |
-
**NOTE**: EmbeddingGemma activations do not support `
|
| 48 |
|
| 49 |
#### Transformers.js in JavaScript
|
| 50 |
|
|
|
|
| 44 |
|
| 45 |
These model weights are designed to be used with [Transformers.js](https://huggingface.co/docs/transformers.js/en/index).
|
| 46 |
|
| 47 |
+
**NOTE**: EmbeddingGemma activations do not support `fp16` or its derivatives. Please use `fp32`, `q8`, or `q4` as appropriate for your hardware.
|
| 48 |
|
| 49 |
#### Transformers.js in JavaScript
|
| 50 |
|