| { |
| "version": "1.0", |
| "truncation": null, |
| "padding": null, |
| "added_tokens": [ |
| { |
| "id": 50256, |
| "content": "<|endoftext|>", |
| "single_word": false, |
| "lstrip": false, |
| "rstrip": false, |
| "normalized": false, |
| "special": true |
| } |
| ], |
| "normalizer": { |
| "type": "Sequence", |
| "normalizers": [ |
| { |
| "type": "NFC" |
| } |
| ] |
| }, |
| "pre_tokenizer": { |
| "type": "Split", |
| "pattern": { |
| "Regex": "'s|'t|'re|'ve|'m|'ll|'d| ?\\p{L}+| ?\\p{N}+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+" |
| }, |
| "behavior": "removed" |
| }, |
| "post_processor": { |
| "type": "TemplateProcessing", |
| "single": [ |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| } |
| ], |
| "pair": [ |
| { |
| "Sequence": { |
| "id": "A", |
| "type_id": 0 |
| } |
| }, |
| { |
| "Sequence": { |
| "id": "B", |
| "type_id": 0 |
| } |
| } |
| ], |
| "special_tokens": { |
| "<|endoftext|>": { |
| "id": "<|endoftext|>", |
| "ids": [ |
| 50256 |
| ] |
| } |
| } |
| }, |
| "decoder": { |
| "type": "ByteLevel", |
| "add_prefix_space": false, |
| "trim_offsets": false, |
| "use_regex": true |
| }, |
| "model": { |
| "type": "BPE", |
| "dropout": null, |
| "unk_token": "<|endoftext|>", |
| "continuing_subword_prefix": "", |
| "end_of_word_suffix": "", |
| "fuse_unk": false, |
| "byte_fallback": true, |
| "vocab": { |
| "<0x00>": 0, |
| "<0x01>": 1, |
| "<0x02>": 2, |
| "<0x03>": 3, |
| "<0x04>": 4, |
| "<0x05>": 5, |
| "<0x06>": 6, |
| "<0x07>": 7, |
| "<0x08>": 8, |
| "<0x09>": 9, |
| "<0x0a>": 10, |
| "<0x0b>": 11, |
| "<0x0c>": 12, |
| "<0x0d>": 13, |
| "<0x0e>": 14, |
| "<0x0f>": 15, |
| "<0x10>": 16, |
| "<0x11>": 17, |
| "<0x12>": 18, |
| "<0x13>": 19, |
| "<0x14>": 20, |
| "<0x15>": 21, |
| "<0x16>": 22, |
| "<0x17>": 23, |
| "<0x18>": 24, |
| "<0x19>": 25, |
| "<0x1a>": 26, |
| "<0x1b>": 27, |
| "<0x1c>": 28, |
| "<0x1d>": 29, |
| "<0x1e>": 30, |
| "<0x1f>": 31, |
| "<0x20>": 32, |
| "<0x21>": 33, |
| "<0x22>": 34, |
| "<0x23>": 35, |
| "<0x24>": 36, |
| "<0x25>": 37, |
| "<0x26>": 38, |
| "<0x27>": 39, |
| "<0x28>": 40, |
| "<0x29>": 41, |
| "<0x2a>": 42, |
| "<0x2b>": 43, |
| "<0x2c>": 44, |
| "<0x2d>": 45, |
| "<0x2e>": 46, |
| "<0x2f>": 47, |
| "<0x30>": 48, |
| "<0x31>": 49, |
| "<0x32>": 50, |
| "<0x33>": 51, |
| "<0x34>": 52, |
| "<0x35>": 53, |
| "<0x36>": 54, |
| "<0x37>": 55, |
| "<0x38>": 56, |
| "<0x39>": 57, |
| "<0x3a>": 58, |
| "<0x3b>": 59, |
| "<0x3c>": 60, |
| "<0x3d>": 61, |
| "<0x3e>": 62, |
| "<0x3f>": 63, |
| "<0x40>": 64, |
| "<0x41>": 65, |
| "<0x42>": 66, |
| "<0x43>": 67, |
| "<0x44>": 68, |
| "<0x45>": 69, |
| "<0x46>": 70, |
| "<0x47>": 71, |
| "<0x48>": 72, |
| "<0x49>": 73, |
| "<0x4a>": 74, |
| "<0x4b>": 75, |
| "<0x4c>": 76, |
| "<0x4d>": 77, |
| "<0x4e>": 78, |
| "<0x4f>": 79, |
| "<0x50>": 80, |
| "<0x51>": 81, |
| "<0x52>": 82, |
| "<0x53>": 83, |
| "<0x54>": 84, |
| "<0x55>": 85, |
| "<0x56>": 86, |
| "<0x57>": 87, |
| "<0x58>": 88, |
| "<0x59>": 89, |
| "<0x5a>": 90, |
| "<0x5b>": 91, |
| "<0x5c>": 92, |
| "<0x5d>": 93, |
| "<0x5e>": 94, |
| "<0x5f>": 95, |
| "<0x60>": 96, |
| "<0x61>": 97, |
| "<0x62>": 98, |
| "<0x63>": 99, |
| "<0x64>": 100, |
| "<0x65>": 101, |
| "<0x66>": 102, |
| "<0x67>": 103, |
| "<0x68>": 104, |
| "<0x69>": 105, |
| "<0x6a>": 106, |
| "<0x6b>": 107, |
| "<0x6c>": 108, |
| "<0x6d>": 109, |
| "<0x6e>": 110, |
| "<0x6f>": 111, |
| "<0x70>": 112, |
| "<0x71>": 113, |
| "<0x72>": 114, |
| "<0x73>": 115, |
| "<0x74>": 116, |
| "<0x75>": 117, |
| "<0x76>": 118, |
| "<0x77>": 119, |
| "<0x78>": 120, |
| "<0x79>": 121, |
| "<0x7a>": 122, |
| "<0x7b>": 123, |
| "<0x7c>": 124, |
| "<0x7d>": 125, |
| "<0x7e>": 126, |
| "<0x7f>": 127, |
| "<0x80>": 128, |
| "<0x81>": 129, |
| "<0x82>": 130, |
| "<0x83>": 131, |
| "<0x84>": 132, |
| "<0x85>": 133, |
| "<0x86>": 134, |
| "<0x87>": 135, |
| "<0x88>": 136, |
| "<0x89>": 137, |
| "<0x8a>": 138, |
| "<0x8b>": 139, |
| "<0x8c>": 140, |
| "<0x8d>": 141, |
| "<0x8e>": 142, |
| "<0x8f>": 143, |
| "<0x90>": 144, |
| "<0x91>": 145, |
| "<0x92>": 146, |
| "<0x93>": 147, |
| "<0x94>": 148, |
| "<0x95>": 149, |
| "<0x96>": 150, |
| "<0x97>": 151, |
| "<0x98>": 152, |
| "<0x99>": 153, |
| "<0x9a>": 154, |
| "<0x9b>": 155, |
| "<0x9c>": 156, |
| "<0x9d>": 157, |
| "<0x9e>": 158, |
| "<0x9f>": 159, |
| "<0xa0>": 160, |
| "<0xa1>": 161, |
| "<0xa2>": 162, |
| "<0xa3>": 163, |
| "<0xa4>": 164, |
| "<0xa5>": 165, |
| "<0xa6>": 166, |
| "<0xa7>": 167, |
| "<0xa8>": 168, |
| "<0xa9>": 169, |
| "<0xaa>": 170, |
| "<0xab>": 171, |
| "<0xac>": 172, |
| "<0xad>": 173, |
| "<0xae>": 174, |
| "<0xaf>": 175, |
| "<0xb0>": 176, |
| "<0xb1>": 177, |
| "<0xb2>": 178, |
| "<0xb3>": 179, |
| "<0xb4>": 180, |
| "<0xb5>": 181, |
| "<0xb6>": 182, |
| "<0xb7>": 183, |
| "<0xb8>": 184, |
| "<0xb9>": 185, |
| "<0xba>": 186, |
| "<0xbb>": 187, |
| "<0xbc>": 188, |
| "<0xbd>": 189, |
| "<0xbe>": 190, |
| "<0xbf>": 191, |
| "<0xc0>": 192, |
| "<0xc1>": 193, |
| "<0xc2>": 194, |
| "<0xc3>": 195, |
| "<0xc4>": 196, |
| "<0xc5>": 197, |
| "<0xc6>": 198, |
| "<0xc7>": 199, |
| "<0xc8>": 200, |
| "<0xc9>": 201, |
| "<0xca>": 202, |
| "<0xcb>": 203, |
| "<0xcc>": 204, |
| "<0xcd>": 205, |
| "<0xce>": 206, |
| "<0xcf>": 207, |
| "<0xd0>": 208, |
| "<0xd1>": 209, |
| "<0xd2>": 210, |
| "<0xd3>": 211, |
| "<0xd4>": 212, |
| "<0xd5>": 213, |
| "<0xd6>": 214, |
| "<0xd7>": 215, |
| "<0xd8>": 216, |
| "<0xd9>": 217, |
| "<0xda>": 218, |
| "<0xdb>": 219, |
| "<0xdc>": 220, |
| "<0xdd>": 221, |
| "<0xde>": 222, |
| "<0xdf>": 223, |
| "<0xe0>": 224, |
| "<0xe1>": 225, |
| "<0xe2>": 226, |
| "<0xe3>": 227, |
| "<0xe4>": 228, |
| "<0xe5>": 229, |
| "<0xe6>": 230, |
| "<0xe7>": 231, |
| "<0xe8>": 232, |
| "<0xe9>": 233, |
| "<0xea>": 234, |
| "<0xeb>": 235, |
| "<0xec>": 236, |
| "<0xed>": 237, |
| "<0xee>": 238, |
| "<0xef>": 239, |
| "<0xf0>": 240, |
| "<0xf1>": 241, |
| "<0xf2>": 242, |
| "<0xf3>": 243, |
| "<0xf4>": 244, |
| "<0xf5>": 245, |
| "<0xf6>": 246, |
| "<0xf7>": 247, |
| "<0xf8>": 248, |
| "<0xf9>": 249, |
| "<0xfa>": 250, |
| "<0xfb>": 251, |
| "<0xfc>": 252, |
| "<0xfd>": 253, |
| "<0xfe>": 254, |
| "<0xff>": 255, |
| "<|endoftext|>": 50256 |
| }, |
| "merges": [ |
| "a0 b0", |
| "a1 b1", |
| "a2 b2", |
| "a3 b3", |
| "a4 b4", |
| "a5 b5", |
| "a6 b6", |
| "a7 b7", |
| "a8 b8", |
| "a9 b9", |
| "a10 b10", |
| "a11 b11", |
| "a12 b12", |
| "a13 b13", |
| "a14 b14", |
| "a15 b15", |
| "a16 b16", |
| "a17 b17", |
| "a18 b18", |
| "a19 b19", |
| "a20 b20", |
| "a21 b21", |
| "a22 b22", |
| "a23 b23", |
| "a24 b24", |
| "a25 b25", |
| "a26 b26", |
| "a27 b27", |
| "a28 b28", |
| "a29 b29", |
| "a30 b30", |
| "a31 b31", |
| "a32 b32", |
| "a33 b33", |
| "a34 b34", |
| "a35 b35", |
| "a36 b36", |
| "a37 b37", |
| "a38 b38", |
| "a39 b39", |
| "a40 b40", |
| "a41 b41", |
| "a42 b42", |
| "a43 b43", |
| "a44 b44", |
| "a45 b45", |
| "a46 b46", |
| "a47 b47", |
| "a48 b48", |
| "a49 b49", |
| "a50 b50", |
| "a51 b51", |
| "a52 b52", |
| "a53 b53", |
| "a54 b54", |
| "a55 b55", |
| "a56 b56", |
| "a57 b57", |
| "a58 b58", |
| "a59 b59", |
| "a60 b60", |
| "a61 b61", |
| "a62 b62", |
| "a63 b63", |
| "a64 b64", |
| "a65 b65", |
| "a66 b66", |
| "a67 b67", |
| "a68 b68", |
| "a69 b69", |
| "a70 b70", |
| "a71 b71", |
| "a72 b72", |
| "a73 b73", |
| "a74 b74", |
| "a75 b75", |
| "a76 b76", |
| "a77 b77", |
| "a78 b78", |
| "a79 b79", |
| "a80 b80", |
| "a81 b81", |
| "a82 b82", |
| "a83 b83", |
| "a84 b84", |
| "a85 b85", |
| "a86 b86", |
| "a87 b87", |
| "a88 b88", |
| "a89 b89", |
| "a90 b90", |
| "a91 b91", |
| "a92 b92", |
| "a93 b93", |
| "a94 b94", |
| "a95 b95", |
| "a96 b96", |
| "a97 b97", |
| "a98 b98", |
| "a99 b99" |
| ] |
| } |
| } |