data-agent-2b-normal-best / tokenizer_config.json
AdithyaSK's picture
AdithyaSK HF Staff
v0: inference weights
d530c39 verified
Raw
History Blame Contribute Delete
2.25 kB
{
"add_prefix_space": false,
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"image_token": "<|image_pad|>",
"is_local": false,
"local_files_only": false,
"model_max_length": 262144,
"model_specific_special_tokens": {
"audio_bos_token": "<|audio_start|>",
"audio_eos_token": "<|audio_end|>",
"audio_token": "<|audio_pad|>",
"image_token": "<|image_pad|>",
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>"
},
"pad_token": "<|endoftext|>",
"padding_side": "left",
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
"processor_class": "Qwen3VLProcessor",
"response_template": {
"defaults": {
"role": "assistant"
},
"fields": {
"content": {
"close_pattern": "<\\|im_end\\|>\\s*",
"content": "text"
},
"reasoning_content": {
"close_pattern": "</think>\\s*",
"content": "text",
"open": "<think>"
},
"tool_calls": {
"close_pattern": "</tool_call>\\s*",
"content": "xml-inline",
"content_args": {
"tag_pattern": "<parameter=(?P<key>[^>\\n]+)>\\s*(?P<value>.*?)\\s*</parameter>",
"value_parser": {
"args": {
"allow_non_json": true
},
"name": "json"
}
},
"open_pattern": "<tool_call>\\s*<function=(?P<name>[^\\n>]+)>",
"repeats": true,
"transform": {
"function": {
"arguments": "{content}",
"name": "{name}"
},
"type": "function"
}
}
},
"start_anchor": "<|im_start|>assistant\n"
},
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"truncation_side": "left",
"unk_token": null,
"video_token": "<|video_pad|>",
"vision_bos_token": "<|vision_start|>",
"vision_eos_token": "<|vision_end|>"
}