BendMlBpeTokenizer.tw: def of bend-ml-bpe-tokenizer@0.1.3.0 Import: import bend-ml-bpe-tokenizer@0.1.3.0/main.bend as BendMlBpeTokenizer Lines 629-637 of bend-ml-bpe-tokenizer@0.1.3.0/main.bend: https://jend.leeeet.dev/read.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&start_line=629&end_line=637 import Base # train.go generates rules with ids next, next+1, ...: none repeats, whatever the corpus def tw(n: Nat, +next: Nat, +xs: List<&2, Tk>, m: Maybe<&1, Cnt>, +done: List<&2, Rule>, +bl: {True{} == below(done, next) : Bool}) -> {True{} == wf.go(train.go(n, next, xs, m), done) : Bool}: match n m: case 0n _: {==} case 1n++p None{}: {==} case 1n++p Some{Cnt{+a, +b, k}}: and_intro(Bool.not(has(done, next)), wf.go(train.go(p, 1n+next, merge(a, b, M{next}, xs), best(count.go(merge(a, b, M{next}, xs), Nil{}))), Rule{next, a, b} <> done), below_fresh(done, next, bl), tw(p, 1n+next, merge(a, b, M{next}, xs), best(count.go(merge(a, b, M{next}, xs), Nil{})), Rule{next, a, b} <> done, below_cons(a, b, done, next, bl))) Uses (18): https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Bool https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Bool.not https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=List https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Maybe https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=Nat https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=Cnt https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=Rule https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=Tk https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=and_intro https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=below https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=below_cons https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=below_fresh https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=best https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=count.go https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=has https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=merge https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=train.go https://jend.leeeet.dev/definition.txt?path=bend-ml-bpe-tokenizer@0.1.3.0/main.bend&name=wf.go