Instructions to use google/gemma-4-E2B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-E2B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-E2B-it") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-E2B-it", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
Add response_template to tokenizer_config.json
Browse filesAdds a `response_template` key to `tokenizer_config.json`.
- tokenizer_config.json +46 -0
tokenizer_config.json
CHANGED
|
@@ -63,6 +63,52 @@
|
|
| 63 |
},
|
| 64 |
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
|
| 65 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
"soc_token": "<|channel>",
|
| 67 |
"sot_token": "<|turn>",
|
| 68 |
"stc_token": "<|tool_call>",
|
|
|
|
| 63 |
},
|
| 64 |
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
|
| 65 |
},
|
| 66 |
+
"response_template": {
|
| 67 |
+
"defaults": {
|
| 68 |
+
"role": "assistant"
|
| 69 |
+
},
|
| 70 |
+
"fields": {
|
| 71 |
+
"content": {
|
| 72 |
+
"close": [
|
| 73 |
+
"<turn|>",
|
| 74 |
+
"<|tool_response>",
|
| 75 |
+
"<eos>"
|
| 76 |
+
],
|
| 77 |
+
"content": "text"
|
| 78 |
+
},
|
| 79 |
+
"thinking": {
|
| 80 |
+
"close": "<channel|>",
|
| 81 |
+
"content": "text",
|
| 82 |
+
"open": "<|channel>thought\n"
|
| 83 |
+
},
|
| 84 |
+
"tool_calls": {
|
| 85 |
+
"close": "<tool_call|>",
|
| 86 |
+
"content": "json",
|
| 87 |
+
"content_args": {
|
| 88 |
+
"string_delims": [
|
| 89 |
+
[
|
| 90 |
+
"<|\"|>",
|
| 91 |
+
"<|\"|>"
|
| 92 |
+
]
|
| 93 |
+
],
|
| 94 |
+
"unquoted_keys": true
|
| 95 |
+
},
|
| 96 |
+
"open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
|
| 97 |
+
"repeats": true,
|
| 98 |
+
"transform": {
|
| 99 |
+
"function": {
|
| 100 |
+
"arguments": "{content}",
|
| 101 |
+
"name": "{name}"
|
| 102 |
+
},
|
| 103 |
+
"type": "function"
|
| 104 |
+
}
|
| 105 |
+
}
|
| 106 |
+
},
|
| 107 |
+
"start_anchor": [
|
| 108 |
+
"<|turn>model\n",
|
| 109 |
+
"<tool_response|>"
|
| 110 |
+
]
|
| 111 |
+
},
|
| 112 |
"soc_token": "<|channel>",
|
| 113 |
"sot_token": "<|turn>",
|
| 114 |
"stc_token": "<|tool_call>",
|