test1 / tokenizer_config.json
Kingaimaster's picture
Upload folder using huggingface_hub
8e995e0 verified
{
"added_tokens_decoder": {
"163584": {"content": "[BOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163585": {"content": "[EOS]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163586": {"content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163587": {"content": "<|im_user|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163588": {"content": "<|im_assistant|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163590": {"content": "<|start_header_id|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163591": {"content": "<|end_header_id|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163593": {"content": "[EOT]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163594": {"content": "<|im_system|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163595": {"content": "<|tool_calls_section_begin|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163596": {"content": "<|tool_calls_section_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163597": {"content": "<|tool_call_begin|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163598": {"content": "<|tool_call_argument_begin|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163599": {"content": "<|tool_call_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163601": {"content": "<|im_middle|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163606": {"content": "<think>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163607": {"content": "</think>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": false},
"163838": {"content": "[UNK]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true},
"163839": {"content": "[PAD]", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true}
},
"additional_special_tokens": ["<|im_end|>", "<|im_user|>", "<|im_assistant|>", "<|start_header_id|>", "<|end_header_id|>", "[EOT]", "<|im_system|>", "<|im_middle|>"],
"bos_token": "[BOS]",
"clean_up_tokenization_spaces": false,
"eos_token": "[EOS]",
"model_max_length": 262144,
"pad_token": "[PAD]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}