Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Structure tokens #43

Merged
merged 11 commits into from
Mar 10, 2025
Merged

Structure tokens #43

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
26e5746
lg tokenizer
Mar 6, 2025
8eaa2ac
lg tokenizer assets
Mar 6, 2025
a996864
lint
Mar 7, 2025
542b3ac
vocab.txt
Mar 7, 2025
ae9fc1d
added test and new wor level model v bpe
Mar 8, 2025
f0bc0ba
rename to include coord tokenization explicity
Mar 10, 2025
42a2712
ruff
karinazad Mar 10, 2025
5cc5f70
ruff tests
karinazad Mar 10, 2025
2d20c8f
remove __name__==main
karinazad Mar 10, 2025
28b8eed
use vocab.txt instead of ductionary
Mar 10, 2025
06d87ce
Merge branch 'structure_tokens' of https://github.com/prescient-desig…
Mar 10, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions src/lobster/assets/latent_generator_tokenizer/special_tokens_map.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
{
"cls_token": "<cls>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"pad_token": "<pad>",
"unk_token": "<unk>"
}
358 changes: 358 additions & 0 deletions src/lobster/assets/latent_generator_tokenizer/tokenizer.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,358 @@
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [],
"normalizer": null,
"pre_tokenizer": null,
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"SpecialToken": {
"id": "<cls>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<eos>",
"type_id": 0
}
}
],
"pair": [
{
"SpecialToken": {
"id": "<cls>",
"type_id": 0
}
},
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"SpecialToken": {
"id": "<eos>",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
},
{
"SpecialToken": {
"id": "<eos>",
"type_id": 1
}
}
],
"special_tokens": {
"<cls>": {
"id": "<cls>",
"ids": [
0
],
"tokens": [
"<cls>"
]
},
"<eos>": {
"id": "<eos>",
"ids": [
2
],
"tokens": [
"<eos>"
]
}
}
},
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": "<unk>",
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"vocab": {
"<cls>": 0,
"<pad>": 1,
"<eos>": 2,
"<unk>": 3,
"<mask>": 4,
".": 5,
"a": 6,
"b": 7,
"c": 8,
"d": 9,
"e": 10,
"f": 11,
"g": 12,
"h": 13,
"i": 14,
"j": 15,
"k": 16,
"l": 17,
"m": 18,
"n": 19,
"o": 20,
"p": 21,
"q": 22,
"r": 23,
"s": 24,
"t": 25,
"u": 26,
"v": 27,
"w": 28,
"x": 29,
"y": 30,
"z": 31,
"aa": 32,
"ab": 33,
"ac": 34,
"ad": 35,
"ae": 36,
"af": 37,
"ag": 38,
"ah": 39,
"ai": 40,
"aj": 41,
"ak": 42,
"al": 43,
"am": 44,
"an": 45,
"ao": 46,
"ap": 47,
"aq": 48,
"ar": 49,
"as": 50,
"at": 51,
"au": 52,
"av": 53,
"aw": 54,
"ax": 55,
"ay": 56,
"az": 57,
"ba": 58,
"bb": 59,
"bc": 60,
"bd": 61,
"be": 62,
"bf": 63,
"bg": 64,
"bh": 65,
"bi": 66,
"bj": 67,
"bk": 68,
"bl": 69,
"bm": 70,
"bn": 71,
"bo": 72,
"bp": 73,
"bq": 74,
"br": 75,
"bs": 76,
"bt": 77,
"bu": 78,
"bv": 79,
"bw": 80,
"bx": 81,
"by": 82,
"bz": 83,
"ca": 84,
"cb": 85,
"cc": 86,
"cd": 87,
"ce": 88,
"cf": 89,
"cg": 90,
"ch": 91,
"ci": 92,
"cj": 93,
"ck": 94,
"cl": 95,
"cm": 96,
"cn": 97,
"co": 98,
"cp": 99,
"cq": 100,
"cr": 101,
"cs": 102,
"ct": 103,
"cu": 104,
"cv": 105,
"cw": 106,
"cx": 107,
"cy": 108,
"cz": 109,
"da": 110,
"db": 111,
"dc": 112,
"dd": 113,
"de": 114,
"df": 115,
"dg": 116,
"dh": 117,
"di": 118,
"dj": 119,
"dk": 120,
"dl": 121,
"dm": 122,
"dn": 123,
"do": 124,
"dp": 125,
"dq": 126,
"dr": 127,
"ds": 128,
"dt": 129,
"du": 130,
"dv": 131,
"dw": 132,
"dx": 133,
"dy": 134,
"dz": 135,
"ea": 136,
"eb": 137,
"ec": 138,
"ed": 139,
"ee": 140,
"ef": 141,
"eg": 142,
"eh": 143,
"ei": 144,
"ej": 145,
"ek": 146,
"el": 147,
"em": 148,
"en": 149,
"eo": 150,
"ep": 151,
"eq": 152,
"er": 153,
"es": 154,
"et": 155,
"eu": 156,
"ev": 157,
"ew": 158,
"ex": 159,
"ey": 160,
"ez": 161,
"fa": 162,
"fb": 163,
"fc": 164,
"fd": 165,
"fe": 166,
"ff": 167,
"fg": 168,
"fh": 169,
"fi": 170,
"fj": 171,
"fk": 172,
"fl": 173,
"fm": 174,
"fn": 175,
"fo": 176,
"fp": 177,
"fq": 178,
"fr": 179,
"fs": 180,
"ft": 181,
"fu": 182,
"fv": 183,
"fw": 184,
"fx": 185,
"fy": 186,
"fz": 187,
"ga": 188,
"gb": 189,
"gc": 190,
"gd": 191,
"ge": 192,
"gf": 193,
"gg": 194,
"gh": 195,
"gi": 196,
"gj": 197,
"gk": 198,
"gl": 199,
"gm": 200,
"gn": 201,
"go": 202,
"gp": 203,
"gq": 204,
"gr": 205,
"gs": 206,
"gt": 207,
"gu": 208,
"gv": 209,
"gw": 210,
"gx": 211,
"gy": 212,
"gz": 213,
"ha": 214,
"hb": 215,
"hc": 216,
"hd": 217,
"he": 218,
"hf": 219,
"hg": 220,
"hh": 221,
"hi": 222,
"hj": 223,
"hk": 224,
"hl": 225,
"hm": 226,
"hn": 227,
"ho": 228,
"hp": 229,
"hq": 230,
"hr": 231,
"hs": 232,
"ht": 233,
"hu": 234,
"hv": 235,
"hw": 236,
"hx": 237,
"hy": 238,
"hz": 239,
"ia": 240,
"ib": 241,
"ic": 242,
"id": 243,
"ie": 244,
"if": 245,
"ig": 246,
"ih": 247,
"ii": 248,
"ij": 249,
"ik": 250,
"il": 251,
"im": 252,
"in": 253,
"io": 254,
"ip": 255,
"iq": 256,
"ir": 257,
"is": 258,
"it": 259,
"iu": 260,
"iv": 261
},
"merges": []
}
}
12 changes: 12 additions & 0 deletions src/lobster/assets/latent_generator_tokenizer/tokenizer_config.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
{
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "left",
"unk_token": "<unk>"
}
1 change: 1 addition & 0 deletions src/lobster/tokenization/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@
from ._mgm_tokenizer import MgmTokenizer
from ._mgm_tokenizer_transform import MgmTokenizerTransform
from ._nucleotide_tokenizer import NucleotideTokenizerFast
from ._latent_generator_tokens import LatentGeneratorTokenizerFast
from ._pmlm_custom_concept_tokenizer_transform import (
CUSTOM_TOKENIZER,
UnirefDescriptorTransform,
Expand Down
Loading
Loading