Mixtral_AI_TinyTronSpeech / tokenizer_config.json
LeroyDyer's picture
Upload folder using huggingface_hub
2362f1c verified
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<|bos|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "<|ASSISTANT|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "<|USER|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32005": {
"content": "<|startthought|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32006": {
"content": "<|endthought|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32007": {
"content": "<image>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32008": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|startthought|>",
"<|endthought|>",
"<|startthought|>",
"<image>",
"<pad>"
],
"bos_token": "<|bos|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": true,
"max_length": 1536,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation": true,
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": true
}