tinysmokellama-3.2 / tokenizer_config.json
fynnsu's picture
Upload folder using huggingface_hub
e1f7e8a verified
{
"added_tokens_decoder": {
"1024": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1025": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1026": {
"content": "<|reserved_special_token_0|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1027": {
"content": "<|reserved_special_token_1|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1028": {
"content": "<|finetune_right_pad_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1029": {
"content": "<|reserved_special_token_2|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1030": {
"content": "<|start_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1031": {
"content": "<|end_header_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1032": {
"content": "<|eom_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1033": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1034": {
"content": "<|python_tag|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|end_of_text|>",
"extra_special_tokens": {},
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 2048,
"tokenizer_class": "PreTrainedTokenizerFast"
}