Profluent-E1-300M / tokenizer.json
lhallee's picture
Upload tokenizer.json with huggingface_hub
9459ad6 verified
{
"version": "1.0",
"truncation": null,
"padding": {
"strategy": "BatchLongest",
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<bos_glm>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "<eos_span>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 5,
"content": "?",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "X",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"vocab": {
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"<bos_glm>": 3,
"<eos_span>": 4,
"?": 5,
"1": 6,
"2": 7,
"A": 8,
"B": 9,
"C": 10,
"D": 11,
"E": 12,
"F": 13,
"G": 14,
"H": 15,
"I": 16,
"J": 17,
"K": 18,
"L": 19,
"M": 20,
"N": 21,
"O": 22,
"P": 23,
"Q": 24,
"R": 25,
"S": 26,
"T": 27,
"U": 28,
"V": 29,
"W": 30,
"X": 31,
"Y": 32,
"Z": 33
},
"merges": []
}
}