Instructions to use Hyper-AI/gemma-4-E4B-it-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hyper-AI/gemma-4-E4B-it-fp8 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Hyper-AI/gemma-4-E4B-it-fp8") model = AutoModelForMultimodalLM.from_pretrained("Hyper-AI/gemma-4-E4B-it-fp8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ tags:
|
|
| 9 |
- lightvl
|
| 10 |
---
|
| 11 |
|
| 12 |
-
## gemma-4-E4B-it-fp8
|
| 13 |
|
| 14 |
**weight: fp8 channel, activation: fp8 dynamic**
|
| 15 |
|
|
|
|
| 9 |
- lightvl
|
| 10 |
---
|
| 11 |
|
| 12 |
+
## gemma-4-E4B-it-fp8
|
| 13 |
|
| 14 |
**weight: fp8 channel, activation: fp8 dynamic**
|
| 15 |
|