shivik-m2.1 / tokenizer /tokenizer.json
ziadrone's picture
Upload folder using huggingface_hub
66f623c verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 1,
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 2,
"content": "<bos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 3,
"content": "<eos>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 4,
"content": "<|system|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 5,
"content": "<|user|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 6,
"content": "<|assistant|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 7,
"content": "<|end|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 8,
"content": "<think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 9,
"content": "</think>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 10,
"content": "<context>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 11,
"content": "</context>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 12,
"content": "<answer>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 13,
"content": "</answer>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 14,
"content": "<instruction>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 15,
"content": "<tool>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 16,
"content": "<tool_input>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 17,
"content": "<tool_output>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 18,
"content": "<safety>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 19,
"content": "<e>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 20,
"content": "<branch>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 21,
"content": "</branch>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 22,
"content": "<select>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 23,
"content": "</select>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 24,
"content": "<evaluate>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 25,
"content": "</evaluate>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 26,
"content": "<confidence>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 27,
"content": "</confidence>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 28,
"content": "<merge>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 29,
"content": "</merge>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 30,
"content": "<path_1>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 31,
"content": "<path_2>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
},
{
"id": 32,
"content": "<path_3>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"special": false
}
],
"normalizer": {
"type": "Sequence",
"normalizers": [
{
"type": "NFC"
},
{
"type": "Lowercase"
}
]
},
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": true,
"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": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {},
"merges": []
}
}