maker.py

#! /usr/bin/python3
src="llm-jp/llm-jp-1.3b-v1.0"
tgt="KoichiYasuoka/llm-jp-1.3b-upos"

import os
from transformers import AutoTokenizer,AutoConfig,GPT2ForTokenClassification,DataCollatorForTokenClassification,TrainingArguments,Trainer
from tokenizers.normalizers import Replace
os.system("test -f ja_gsd_modern.conllu || curl -LO https://github.com/KoichiYasuoka/SuPar-UniDic/raw/main/suparunidic/suparmodels/ja_gsd_modern.conllu")

class UPOSFileDataset(object):
  def __init__(self,conllu,tokenizer):
    self.conllu=open(conllu,"r",encoding="utf-8")
    self.tokenizer=tokenizer
    self.seeks=[0]
    label=set(["SYM"])
    s=self.conllu.readline()
    while s!="":
      if s=="\n":
        self.seeks.append(self.conllu.tell())
      else:
        w=s.split("\t")
        if len(w)==10:
          if w[0].isdecimal():
            label.add(w[3] if w[5]=="_" else w[3]+"|"+w[5])
      s=self.conllu.readline()
    lid={}
    for i,l in enumerate(sorted(label)):
      lid[l],lid["B-"+l],lid["I-"+l]=i*3,i*3+1,i*3+2
    self.label2id=lid
  def __call__(*args):
    lid={l:i for i,l in enumerate(sorted(set(sum([list(t.label2id) for t in args],[]))))}
    for t in args:
      t.label2id=lid
    return lid
  def __del__(self):
    self.conllu.close()
  __len__=lambda self:len(self.seeks)-1
  def __getitem__(self,i):
    self.conllu.seek(self.seeks[i])
    form,upos,sp=[],[],False
    while self.conllu.tell()<self.seeks[i+1]:
      w=self.conllu.readline().split("\t")
      if len(w)==10:
        form.append(" "+w[1] if sp else w[1])
        if w[0].isdecimal():
          upos.append(w[3] if w[5]=="_" else w[3]+"|"+w[5])
        sp=w[9].find("SpaceAfter=No")<0
    v=self.tokenizer(form,add_special_tokens=False)
    i,u=[],[]
    for j,(x,y) in enumerate(zip(v["input_ids"],upos)):
      if x!=[]:
        i+=x
        u+=[y] if len(x)==1 else ["B-"+y]+["I-"+y]*(len(x)-1)
    if len(i)<self.tokenizer.model_max_length-3:
      ids=i
      upos=u
    else:
      ids=i[0:self.tokenizer.model_max_length-2]
      upos=u[0:self.tokenizer.model_max_length-2]
    return {"input_ids":ids,"labels":[self.label2id[t] for t in upos]}

tkz=AutoTokenizer.from_pretrained(src)
tkz.backend_tokenizer.normalizer=Replace(" ","\u2581")
trainDS=UPOSFileDataset("ja_gsd_modern.conllu",tkz)
lid=trainDS.label2id
cfg=AutoConfig.from_pretrained(src,num_labels=len(lid),label2id=lid,id2label={i:l for l,i in lid.items()},ignore_mismatched_sizes=True)
arg=TrainingArguments(num_train_epochs=3,per_device_train_batch_size=32,output_dir=tgt,overwrite_output_dir=True,save_total_limit=2,learning_rate=5e-05,warmup_ratio=0.1,save_safetensors=False)
trn=Trainer(args=arg,data_collator=DataCollatorForTokenClassification(tkz),model=GPT2ForTokenClassification.from_pretrained(src,config=cfg,ignore_mismatched_sizes=True),train_dataset=trainDS)
trn.train()
trn.save_model(tgt)
tkz.save_pretrained(tgt)