testai / tokenizer.json
testaccount-ai's picture
Create tokenizer.json
0cd61d0 verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 151643,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 151644,
"content": "<|user|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 151645,
"content": "<|assistant|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 151646,
"content": "<|system|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": "",
"end_of_word_suffix": "",
"fuse_unk": false,
"byte_fallback": true,
"vocab": {},
"merges": []
},
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"post_processor": {
"type": "TemplateProcessing",
"single": ["$A", "<|endoftext|>"],
"pair": ["$A", "$B", "<|endoftext|>"],
"special_tokens": {
"<|endoftext|>": {
"id": 151643,
"ids": [151643]
}
}
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"normalizer": {
"type": "NFC"
}
}