Instructions to use pcuenq/gemma-4-E2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pcuenq/gemma-4-E2B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("pcuenq/gemma-4-E2B-it") model = AutoModelForMultimodalLM.from_pretrained("pcuenq/gemma-4-E2B-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Switch transform to new dict-template format (drops jmespath)
Browse files- tokenizer_config.json +7 -1
tokenizer_config.json
CHANGED
|
@@ -96,7 +96,13 @@
|
|
| 96 |
]
|
| 97 |
]
|
| 98 |
},
|
| 99 |
-
"transform":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
},
|
| 101 |
"content": {
|
| 102 |
"close": [
|
|
|
|
| 96 |
]
|
| 97 |
]
|
| 98 |
},
|
| 99 |
+
"transform": {
|
| 100 |
+
"type": "function",
|
| 101 |
+
"function": {
|
| 102 |
+
"name": "{name}",
|
| 103 |
+
"arguments": "{content}"
|
| 104 |
+
}
|
| 105 |
+
}
|
| 106 |
},
|
| 107 |
"content": {
|
| 108 |
"close": [
|