Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +74 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_token": "<|audio|>",
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"boa_token": "<|audio>",
|
| 5 |
+
"boi_token": "<|image>",
|
| 6 |
+
"bos_token": "<bos>",
|
| 7 |
+
"eoa_token": "<audio|>",
|
| 8 |
+
"eoc_token": "<channel|>",
|
| 9 |
+
"eoi_token": "<image|>",
|
| 10 |
+
"eos_token": "<eos>",
|
| 11 |
+
"eot_token": "<turn|>",
|
| 12 |
+
"escape_token": "<|\"|>",
|
| 13 |
+
"etc_token": "<tool_call|>",
|
| 14 |
+
"etd_token": "<tool|>",
|
| 15 |
+
"etr_token": "<tool_response|>",
|
| 16 |
+
"extra_special_tokens": [
|
| 17 |
+
"<|video|>"
|
| 18 |
+
],
|
| 19 |
+
"image_token": "<|image|>",
|
| 20 |
+
"mask_token": "<mask>",
|
| 21 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": "<pad>",
|
| 23 |
+
"padding_side": "left",
|
| 24 |
+
"processor_class": "Gemma4Processor",
|
| 25 |
+
"response_schema": {
|
| 26 |
+
"type": "object",
|
| 27 |
+
"properties": {
|
| 28 |
+
"role": {
|
| 29 |
+
"const": "assistant"
|
| 30 |
+
},
|
| 31 |
+
"thinking": {
|
| 32 |
+
"type": "string"
|
| 33 |
+
},
|
| 34 |
+
"content": {
|
| 35 |
+
"type": "string"
|
| 36 |
+
},
|
| 37 |
+
"tool_calls": {
|
| 38 |
+
"x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
|
| 39 |
+
"type": "array",
|
| 40 |
+
"items": {
|
| 41 |
+
"type": "object",
|
| 42 |
+
"properties": {
|
| 43 |
+
"type": {
|
| 44 |
+
"const": "function"
|
| 45 |
+
},
|
| 46 |
+
"function": {
|
| 47 |
+
"type": "object",
|
| 48 |
+
"x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
|
| 49 |
+
"properties": {
|
| 50 |
+
"name": {
|
| 51 |
+
"type": "string"
|
| 52 |
+
},
|
| 53 |
+
"arguments": {
|
| 54 |
+
"type": "object",
|
| 55 |
+
"x-parser": "gemma4-tool-call",
|
| 56 |
+
"additionalProperties": {}
|
| 57 |
+
}
|
| 58 |
+
}
|
| 59 |
+
}
|
| 60 |
+
}
|
| 61 |
+
}
|
| 62 |
+
}
|
| 63 |
+
},
|
| 64 |
+
"x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<content>(?:(?!\\<\\|tool_call\\>)(?!\\<turn\\|\\>).)+)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?:\\<turn\\|\\>)?"
|
| 65 |
+
},
|
| 66 |
+
"soc_token": "<|channel>",
|
| 67 |
+
"sot_token": "<|turn>",
|
| 68 |
+
"stc_token": "<|tool_call>",
|
| 69 |
+
"std_token": "<|tool>",
|
| 70 |
+
"str_token": "<|tool_response>",
|
| 71 |
+
"think_token": "<|think|>",
|
| 72 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 73 |
+
"unk_token": "<unk>"
|
| 74 |
+
}
|