Update README.md

README.md

@@ -20,7 +20,58 @@ should probably proofread and complete it, then remove this comment. -->
 Russian NER model fine-tuned on RURED2.
 https://github.com/denis-gordeev/rured2
 
-# multilabel_ner
+This model outputs multiple possible labels for a single token. So for proper usage you can use it like in the following code:
+```
+import torch
+from torch import nn
+from transformers import (AutoTokenizer, AutoModelForTokenClassification, 
+ TrainingArguments, Trainer)
+
+model_name = "denis-gordeev/rured2-ner-microsoft-mdeberta-v3-base"
+model = AutoModelForTokenClassification.from_pretrained(
+ model_name).to('cuda')
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def predict(text:str, glue_tokens=False, output_together=True, glue_words=True):
+ sigmoid = nn.Sigmoid()
+ tokenized = tokenizer(text)
+ input_ids = torch.tensor(
+ [tokenized["input_ids"]], dtype=torch.long
+ ).to("cuda")
+ token_type_ids = torch.tensor(
+ [tokenized["token_type_ids"]], dtype=torch.long
+ ).to("cuda")
+ attention_mask = torch.tensor(
+ [tokenized["attention_mask"]], dtype=torch.long
+ ).to("cuda")
+ preds = model(**{"input_ids": input_ids, "token_type_ids": token_type_ids, "attention_mask": attention_mask})
+ logits = sigmoid(preds.logits)
+
+ output_tokens = []
+ output_preds = []
+ for i, token in enumerate(input_ids[0]):
+ if token > 3:
+ class_ids = (logits[0][i] > 0.5).nonzero()
+ if class_ids.shape[0] >= 1:
+ class_names = [id_to_label[int(cl)] for cl in class_ids]
+ else:
+ class_names = [id_to_label[int(logits[0][i].argmax())]]
+ converted_token = tokenizer.convert_ids_to_tokens([token])[0]
+ new_word_bool = converted_token.startswith("▁")
+ converted_token = converted_token.replace("▁", "")
+ if glue_words and not(new_word_bool) and output_tokens:
+ output_tokens[-1] += converted_token
+ else:
+ output_tokens.append(converted_token)
+ output_preds.append(class_names)
+ else:
+ class_names = []
+ if output_together:
+ return [[output_tokens[t_i], output_preds[t_i]] for t_i in range(len(output_tokens))]
+ return output_tokens, output_preds
+```
+# denis-gordeev/rured2-ner-microsoft-mdeberta-v3-base
 
 This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set: