initial release

README.md

@@ -0,0 +1,42 @@
+---
+language:
+- "sr"
+tags:
+- "serbian"
+- "token-classification"
+- "pos"
+- "dependency-parsing"
+base_model: jerteh/gpt2-orao
+datasets:
+- "universal_dependencies"
+license: "cc-by-sa-4.0"
+pipeline_tag: "token-classification"
+widget:
+- text: "Да има сира и масла и моја би мати знала гибати гибаницу."
+- text: "Da ima sira i masla i moja bi mati znala gibati gibanicu."
+---
+
+# gpt2-large-serbian-upos
+
+## Model Description
+
+This is a GPT-2 model in Serbian (Cyrillic and Latin) for POS-tagging and dependency-parsing, derived from [gpt2-orao](https://huggingface.co/jerteh/gpt2-orao). Every word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/).
+
+## How to Use
+
+```py
+from transformers import pipeline
+nlp=pipeline("upos","KoichiYasuoka/gpt2-large-serbian-upos",trust_remote_code=True,aggregation_strategy="simple")
+```
+
+or
+
+```py
+import esupar
+nlp=esupar.load("KoichiYasuoka/gpt2-large-serbian-upos")
+```
+
+## See Also
+
+[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa/GPT models
+

maker.py

@@ -0,0 +1,75 @@
+#! /usr/bin/python3
+src="jerteh/gpt2-orao"
+tgt="KoichiYasuoka/gpt2-large-serbian-upos"
+
+import os
+from transformers import AutoTokenizer,AutoConfig,GPT2ForTokenClassification,DataCollatorForTokenClassification,TrainingArguments,Trainer
+from tokenizers.pre_tokenizers import Sequence,Punctuation
+for d in ["UD_Serbian-SET","UD_Croatian-SET"]:
+  os.system("test -d "+d+" || git clone --depth=1 https://github.com/UniversalDependencies/"+d)
+os.system("for F in train dev test ; do cat UD_*-SET/*-$F.conllu > $F.conllu ; done")
+
+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=[self.tokenizer.cls_token_id],["SYM"]
+    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+[self.tokenizer.sep_token_id]
+      upos=u+["SYM"]
+    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,cls_token="<s>",pad_token="<pad>",sep_token="</s>",unk_token="<unk>",mask_token="<mask>",bos_token="<s>",eos_token="</s>",model_max_length=1024)
+tkz.backend_tokenizer.pre_tokenizer=Sequence([Punctuation(),tkz.backend_tokenizer.pre_tokenizer])
+trainDS=UPOSFileDataset("train.conllu",tkz)
+devDS=UPOSFileDataset("dev.conllu",tkz)
+testDS=UPOSFileDataset("test.conllu",tkz)
+lid=trainDS(devDS,testDS)
+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=16,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)

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e79c31736f0b0cf2bcaf5dc509f7b65255482b49262ab9cbe53c807db57386
+size 3104317858

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

supar.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36285110f969df8e894fd9756d8a6567554677aa28c3ce79043791978c21814
+size 3144851074

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "GPT2TokenizerFast",
+  "unk_token": "<unk>"
+}

upos.py

@@ -0,0 +1,41 @@
+from transformers import TokenClassificationPipeline
+
+class BellmanFordTokenClassificationPipeline(TokenClassificationPipeline):
+  def __init__(self,**kwargs):
+    import numpy
+    super().__init__(**kwargs)
+    x=self.model.config.label2id
+    y=[k for k in x if not k.startswith("I-")]
+    self.transition=numpy.full((len(x),len(x)),numpy.nan)
+    for k,v in x.items():
+      for j in ["I-"+k[2:]] if k.startswith("B-") else [k]+y if k.startswith("I-") else y:
+        self.transition[v,x[j]]=0
+  def check_model_type(self,supported_models):
+    pass
+  def postprocess(self,model_outputs,**kwargs):
+    import numpy
+    if "logits" not in model_outputs:
+      return self.postprocess(model_outputs[0],**kwargs)
+    m=model_outputs["logits"][0].numpy()
+    e=numpy.exp(m-numpy.max(m,axis=-1,keepdims=True))
+    z=e/e.sum(axis=-1,keepdims=True)
+    for i in range(m.shape[0]-1,0,-1):
+      m[i-1]+=numpy.nanmax(m[i]+self.transition,axis=1)
+    k=[numpy.nanargmax(m[0]+self.transition[0])]
+    for i in range(1,m.shape[0]):
+      k.append(numpy.nanargmax(m[i]+self.transition[k[-1]]))
+    w=[{"entity":self.model.config.id2label[j],"start":s,"end":e,"score":z[i,j]} for i,((s,e),j) in enumerate(zip(model_outputs["offset_mapping"][0].tolist(),k)) if s<e]
+    if "aggregation_strategy" in kwargs and kwargs["aggregation_strategy"]!="none":
+      for i,t in reversed(list(enumerate(w))):
+        p=t.pop("entity")
+        if p.startswith("I-"):
+          w[i-1]["score"]=min(w[i-1]["score"],t["score"])
+          w[i-1]["end"]=w.pop(i)["end"]
+        elif p.startswith("B-"):
+          t["entity_group"]=p[2:]
+        else:
+          t["entity_group"]=p
+    for t in w:
+      t["text"]=model_outputs["sentence"][t["start"]:t["end"]]
+    return w
+