tiny-processor-glmasr / tokenizer_config.json
hf-transformers-bot's picture
Add tiny processor fixture for testing
a26cd09 verified
Raw
History Blame Contribute Delete
4.01 kB
{
"backend": "tokenizers",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": [
"<|endoftext|>",
"[MASK]",
"[gMASK]",
"[sMASK]",
"<sop>",
"<eop>",
"<|system|>",
"<|user|>",
"<|assistant|>",
"<|observation|>",
"<|begin_of_image|>",
"<|end_of_image|>",
"<|begin_of_video|>",
"<|end_of_video|>",
"<|pad|>",
"<|begin_of_audio|>",
"<|end_of_audio|>"
],
"is_local": false,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 65536,
"model_specific_special_tokens": {},
"pad_token": "<|endoftext|>",
"padding_side": "left",
"processor_class": "GlmAsrProcessor",
"remove_space": false,
"tokenizer_class": "TokenizersBackend",
"added_tokens_decoder": {
"500": {
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"501": {
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"502": {
"content": "[gMASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"503": {
"content": "[sMASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"504": {
"content": "<sop>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"505": {
"content": "<eop>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"506": {
"content": "<|system|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"507": {
"content": "<|user|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"508": {
"content": "<|assistant|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"509": {
"content": "<|observation|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"510": {
"content": "<|begin_of_image|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"511": {
"content": "<|end_of_image|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"512": {
"content": "<|begin_of_video|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"513": {
"content": "<|end_of_video|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"514": {
"content": "<|pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"515": {
"content": "<|begin_of_audio|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
"516": {
"content": "<|end_of_audio|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
}
}