Transformers
  • ๐ŸŒGET STARTED
    • Transformers
    • Quick tour
    • Installation
  • ๐ŸŒTUTORIALS
    • Run inference with pipelines
    • Write portable code with AutoClass
    • Preprocess data
    • Fine-tune a pretrained model
    • Train with a script
    • Set up distributed training with BOINC AI Accelerate
    • Load and train adapters with BOINC AI PEFT
    • Share your model
    • Agents
    • Generation with LLMs
  • ๐ŸŒTASK GUIDES
    • ๐ŸŒNATURAL LANGUAGE PROCESSING
      • Text classification
      • Token classification
      • Question answering
      • Causal language modeling
      • Masked language modeling
      • Translation
      • Summarization
      • Multiple choice
    • ๐ŸŒAUDIO
      • Audio classification
      • Automatic speech recognition
    • ๐ŸŒCOMPUTER VISION
      • Image classification
      • Semantic segmentation
      • Video classification
      • Object detection
      • Zero-shot object detection
      • Zero-shot image classification
      • Depth estimation
    • ๐ŸŒMULTIMODAL
      • Image captioning
      • Document Question Answering
      • Visual Question Answering
      • Text to speech
    • ๐ŸŒGENERATION
      • Customize the generation strategy
    • ๐ŸŒPROMPTING
      • Image tasks with IDEFICS
  • ๐ŸŒDEVELOPER GUIDES
    • Use fast tokenizers from BOINC AI Tokenizers
    • Run inference with multilingual models
    • Use model-specific APIs
    • Share a custom model
    • Templates for chat models
    • Run training on Amazon SageMaker
    • Export to ONNX
    • Export to TFLite
    • Export to TorchScript
    • Benchmarks
    • Notebooks with examples
    • Community resources
    • Custom Tools and Prompts
    • Troubleshoot
  • ๐ŸŒPERFORMANCE AND SCALABILITY
    • Overview
    • ๐ŸŒEFFICIENT TRAINING TECHNIQUES
      • Methods and tools for efficient training on a single GPU
      • Multiple GPUs and parallelism
      • Efficient training on CPU
      • Distributed CPU training
      • Training on TPUs
      • Training on TPU with TensorFlow
      • Training on Specialized Hardware
      • Custom hardware for training
      • Hyperparameter Search using Trainer API
    • ๐ŸŒOPTIMIZING INFERENCE
      • Inference on CPU
      • Inference on one GPU
      • Inference on many GPUs
      • Inference on Specialized Hardware
    • Instantiating a big model
    • Troubleshooting
    • XLA Integration for TensorFlow Models
    • Optimize inference using `torch.compile()`
  • ๐ŸŒCONTRIBUTE
    • How to contribute to transformers?
    • How to add a model to BOINC AI Transformers?
    • How to convert a BOINC AI Transformers model to TensorFlow?
    • How to add a pipeline to BOINC AI Transformers?
    • Testing
    • Checks on a Pull Request
  • ๐ŸŒCONCEPTUAL GUIDES
    • Philosophy
    • Glossary
    • What BOINC AI Transformers can do
    • How BOINC AI Transformers solve tasks
    • The Transformer model family
    • Summary of the tokenizers
    • Attention mechanisms
    • Padding and truncation
    • BERTology
    • Perplexity of fixed-length models
    • Pipelines for webserver inference
    • Model training anatomy
  • ๐ŸŒAPI
    • ๐ŸŒMAIN CLASSES
      • Agents and Tools
      • ๐ŸŒAuto Classes
        • Extending the Auto Classes
        • AutoConfig
        • AutoTokenizer
        • AutoFeatureExtractor
        • AutoImageProcessor
        • AutoProcessor
        • Generic model classes
          • AutoModel
          • TFAutoModel
          • FlaxAutoModel
        • Generic pretraining classes
          • AutoModelForPreTraining
          • TFAutoModelForPreTraining
          • FlaxAutoModelForPreTraining
        • Natural Language Processing
          • AutoModelForCausalLM
          • TFAutoModelForCausalLM
          • FlaxAutoModelForCausalLM
          • AutoModelForMaskedLM
          • TFAutoModelForMaskedLM
          • FlaxAutoModelForMaskedLM
          • AutoModelForMaskGenerationge
          • TFAutoModelForMaskGeneration
          • AutoModelForSeq2SeqLM
          • TFAutoModelForSeq2SeqLM
          • FlaxAutoModelForSeq2SeqLM
          • AutoModelForSequenceClassification
          • TFAutoModelForSequenceClassification
          • FlaxAutoModelForSequenceClassification
          • AutoModelForMultipleChoice
          • TFAutoModelForMultipleChoice
          • FlaxAutoModelForMultipleChoice
          • AutoModelForNextSentencePrediction
          • TFAutoModelForNextSentencePrediction
          • FlaxAutoModelForNextSentencePrediction
          • AutoModelForTokenClassification
          • TFAutoModelForTokenClassification
          • FlaxAutoModelForTokenClassification
          • AutoModelForQuestionAnswering
          • TFAutoModelForQuestionAnswering
          • FlaxAutoModelForQuestionAnswering
          • AutoModelForTextEncoding
          • TFAutoModelForTextEncoding
        • Computer vision
          • AutoModelForDepthEstimation
          • AutoModelForImageClassification
          • TFAutoModelForImageClassification
          • FlaxAutoModelForImageClassification
          • AutoModelForVideoClassification
          • AutoModelForMaskedImageModeling
          • TFAutoModelForMaskedImageModeling
          • AutoModelForObjectDetection
          • AutoModelForImageSegmentation
          • AutoModelForImageToImage
          • AutoModelForSemanticSegmentation
          • TFAutoModelForSemanticSegmentation
          • AutoModelForInstanceSegmentation
          • AutoModelForUniversalSegmentation
          • AutoModelForZeroShotImageClassification
          • TFAutoModelForZeroShotImageClassification
          • AutoModelForZeroShotObjectDetection
        • Audio
          • AutoModelForAudioClassification
          • AutoModelForAudioFrameClassification
          • TFAutoModelForAudioFrameClassification
          • AutoModelForCTC
          • AutoModelForSpeechSeq2Seq
          • TFAutoModelForSpeechSeq2Seq
          • FlaxAutoModelForSpeechSeq2Seq
          • AutoModelForAudioXVector
          • AutoModelForTextToSpectrogram
          • AutoModelForTextToWaveform
        • Multimodal
          • AutoModelForTableQuestionAnswering
          • TFAutoModelForTableQuestionAnswering
          • AutoModelForDocumentQuestionAnswering
          • TFAutoModelForDocumentQuestionAnswering
          • AutoModelForVisualQuestionAnswering
          • AutoModelForVision2Seq
          • TFAutoModelForVision2Seq
          • FlaxAutoModelForVision2Seq
      • Callbacks
      • Configuration
      • Data Collator
      • Keras callbacks
      • Logging
      • Models
      • Text Generation
      • ONNX
      • Optimization
      • Model outputs
      • Pipelines
      • Processors
      • Quantization
      • Tokenizer
      • Trainer
      • DeepSpeed Integration
      • Feature Extractor
      • Image Processor
    • ๐ŸŒMODELS
      • ๐ŸŒTEXT MODELS
        • ALBERT
        • BART
        • BARThez
        • BARTpho
        • BERT
        • BertGeneration
        • BertJapanese
        • Bertweet
        • BigBird
        • BigBirdPegasus
        • BioGpt
        • Blenderbot
        • Blenderbot Small
        • BLOOM
        • BORT
        • ByT5
        • CamemBERT
        • CANINE
        • CodeGen
        • CodeLlama
        • ConvBERT
        • CPM
        • CPMANT
        • CTRL
        • DeBERTa
        • DeBERTa-v2
        • DialoGPT
        • DistilBERT
        • DPR
        • ELECTRA
        • Encoder Decoder Models
        • ERNIE
        • ErnieM
        • ESM
        • Falcon
        • FLAN-T5
        • FLAN-UL2
        • FlauBERT
        • FNet
        • FSMT
        • Funnel Transformer
        • GPT
        • GPT Neo
        • GPT NeoX
        • GPT NeoX Japanese
        • GPT-J
        • GPT2
        • GPTBigCode
        • GPTSAN Japanese
        • GPTSw3
        • HerBERT
        • I-BERT
        • Jukebox
        • LED
        • LLaMA
        • LLama2
        • Longformer
        • LongT5
        • LUKE
        • M2M100
        • MarianMT
        • MarkupLM
        • MBart and MBart-50
        • MEGA
        • MegatronBERT
        • MegatronGPT2
        • Mistral
        • mLUKE
        • MobileBERT
        • MPNet
        • MPT
        • MRA
        • MT5
        • MVP
        • NEZHA
        • NLLB
        • NLLB-MoE
        • Nystrรถmformer
        • Open-Llama
        • OPT
        • Pegasus
        • PEGASUS-X
        • Persimmon
        • PhoBERT
        • PLBart
        • ProphetNet
        • QDQBert
        • RAG
        • REALM
        • Reformer
        • RemBERT
        • RetriBERT
        • RoBERTa
        • RoBERTa-PreLayerNorm
        • RoCBert
        • RoFormer
        • RWKV
        • Splinter
        • SqueezeBERT
        • SwitchTransformers
        • T5
        • T5v1.1
        • TAPEX
        • Transformer XL
        • UL2
        • UMT5
        • X-MOD
        • XGLM
        • XLM
        • XLM-ProphetNet
        • XLM-RoBERTa
        • XLM-RoBERTa-XL
        • XLM-V
        • XLNet
        • YOSO
      • ๐ŸŒVISION MODELS
        • BEiT
        • BiT
        • Conditional DETR
        • ConvNeXT
        • ConvNeXTV2
        • CvT
        • Deformable DETR
        • DeiT
        • DETA
        • DETR
        • DiNAT
        • DINO V2
        • DiT
        • DPT
        • EfficientFormer
        • EfficientNet
        • FocalNet
        • GLPN
        • ImageGPT
        • LeViT
        • Mask2Former
        • MaskFormer
        • MobileNetV1
        • MobileNetV2
        • MobileViT
        • MobileViTV2
        • NAT
        • PoolFormer
        • Pyramid Vision Transformer (PVT)
        • RegNet
        • ResNet
        • SegFormer
        • SwiftFormer
        • Swin Transformer
        • Swin Transformer V2
        • Swin2SR
        • Table Transformer
        • TimeSformer
        • UperNet
        • VAN
        • VideoMAE
        • Vision Transformer (ViT)
        • ViT Hybrid
        • ViTDet
        • ViTMAE
        • ViTMatte
        • ViTMSN
        • ViViT
        • YOLOS
      • ๐ŸŒAUDIO MODELS
        • Audio Spectrogram Transformer
        • Bark
        • CLAP
        • EnCodec
        • Hubert
        • MCTCT
        • MMS
        • MusicGen
        • Pop2Piano
        • SEW
        • SEW-D
        • Speech2Text
        • Speech2Text2
        • SpeechT5
        • UniSpeech
        • UniSpeech-SAT
        • VITS
        • Wav2Vec2
        • Wav2Vec2-Conformer
        • Wav2Vec2Phoneme
        • WavLM
        • Whisper
        • XLS-R
        • XLSR-Wav2Vec2
      • ๐ŸŒMULTIMODAL MODELS
        • ALIGN
        • AltCLIP
        • BLIP
        • BLIP-2
        • BridgeTower
        • BROS
        • Chinese-CLIP
        • CLIP
        • CLIPSeg
        • Data2Vec
        • DePlot
        • Donut
        • FLAVA
        • GIT
        • GroupViT
        • IDEFICS
        • InstructBLIP
        • LayoutLM
        • LayoutLMV2
        • LayoutLMV3
        • LayoutXLM
        • LiLT
        • LXMERT
        • MatCha
        • MGP-STR
        • Nougat
        • OneFormer
        • OWL-ViT
        • Perceiver
        • Pix2Struct
        • Segment Anything
        • Speech Encoder Decoder Models
        • TAPAS
        • TrOCR
        • TVLT
        • ViLT
        • Vision Encoder Decoder Models
        • Vision Text Dual Encoder
        • VisualBERT
        • X-CLIP
      • ๐ŸŒREINFORCEMENT LEARNING MODELS
        • Decision Transformer
        • Trajectory Transformer
      • ๐ŸŒTIME SERIES MODELS
        • Autoformer
        • Informer
        • Time Series Transformer
      • ๐ŸŒGRAPH MODELS
        • Graphormer
  • ๐ŸŒINTERNAL HELPERS
    • Custom Layers and Utilities
    • Utilities for pipelines
    • Utilities for Tokenizers
    • Utilities for Trainer
    • Utilities for Generation
    • Utilities for Image Processors
    • Utilities for Audio processing
    • General Utilities
    • Utilities for Time Series
Powered by GitBook
On this page
  • Load WNUT 17 dataset
  • Preprocess
  • Evaluate
  • Train
  • Inference
  1. TASK GUIDES
  2. NATURAL LANGUAGE PROCESSING

Token classification

PreviousText classificationNextQuestion answering

Last updated 1 year ago

Token classification assigns a label to individual tokens in a sentence. One of the most common token classification tasks is Named Entity Recognition (NER). NER attempts to find a label for each entity in a sentence, such as a person, location, or organization.

This guide will show you how to:

  1. Finetune on the dataset to detect new entities.

  2. Use your finetuned model for inference.

The task illustrated in this tutorial is supported by the following model architectures:

, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

Before you begin, make sure you have all the necessary libraries installed:

Copied

pip install transformers datasets evaluate seqeval

We encourage you to login to your BOINC AI account so you can upload and share your model with the community. When prompted, enter your token to login:

Copied

>>> from boincai_hub import notebook_login

>>> notebook_login()

Load WNUT 17 dataset

Start by loading the WNUT 17 dataset from the ๐ŸŒŽ Datasets library:

Copied

>>> from datasets import load_dataset

>>> wnut = load_dataset("wnut_17")

Then take a look at an example:

Copied

>>> wnut["train"][0]
{'id': '0',
 'ner_tags': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 8, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0],
 'tokens': ['@paulwalk', 'It', "'s", 'the', 'view', 'from', 'where', 'I', "'m", 'living', 'for', 'two', 'weeks', '.', 'Empire', 'State', 'Building', '=', 'ESB', '.', 'Pretty', 'bad', 'storm', 'here', 'last', 'evening', '.']
}

Each number in ner_tags represents an entity. Convert the numbers to their label names to find out what the entities are:

Copied

>>> label_list = wnut["train"].features[f"ner_tags"].feature.names
>>> label_list
[
    "O",
    "B-corporation",
    "I-corporation",
    "B-creative-work",
    "I-creative-work",
    "B-group",
    "I-group",
    "B-location",
    "I-location",
    "B-person",
    "I-person",
    "B-product",
    "I-product",
]

The letter that prefixes each ner_tag indicates the token position of the entity:

  • B- indicates the beginning of an entity.

  • I- indicates a token is contained inside the same entity (for example, the State token is a part of an entity like Empire State Building).

  • 0 indicates the token doesnโ€™t correspond to any entity.

Preprocess

The next step is to load a DistilBERT tokenizer to preprocess the tokens field:

Copied

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")

As you saw in the example tokens field above, it looks like the input has already been tokenized. But the input actually hasnโ€™t been tokenized yet and youโ€™ll need to set is_split_into_words=True to tokenize the words into subwords. For example:

Copied

>>> example = wnut["train"][0]
>>> tokenized_input = tokenizer(example["tokens"], is_split_into_words=True)
>>> tokens = tokenizer.convert_ids_to_tokens(tokenized_input["input_ids"])
>>> tokens
['[CLS]', '@', 'paul', '##walk', 'it', "'", 's', 'the', 'view', 'from', 'where', 'i', "'", 'm', 'living', 'for', 'two', 'weeks', '.', 'empire', 'state', 'building', '=', 'es', '##b', '.', 'pretty', 'bad', 'storm', 'here', 'last', 'evening', '.', '[SEP]']

However, this adds some special tokens [CLS] and [SEP] and the subword tokenization creates a mismatch between the input and labels. A single word corresponding to a single label may now be split into two subwords. Youโ€™ll need to realign the tokens and labels by:

  1. Only labeling the first token of a given word. Assign -100 to other subtokens from the same word.

Here is how you can create a function to realign the tokens and labels, and truncate sequences to be no longer than DistilBERTโ€™s maximum input length:

Copied

>>> def tokenize_and_align_labels(examples):
...     tokenized_inputs = tokenizer(examples["tokens"], truncation=True, is_split_into_words=True)

...     labels = []
...     for i, label in enumerate(examples[f"ner_tags"]):
...         word_ids = tokenized_inputs.word_ids(batch_index=i)  # Map tokens to their respective word.
...         previous_word_idx = None
...         label_ids = []
...         for word_idx in word_ids:  # Set the special tokens to -100.
...             if word_idx is None:
...                 label_ids.append(-100)
...             elif word_idx != previous_word_idx:  # Only label the first token of a given word.
...                 label_ids.append(label[word_idx])
...             else:
...                 label_ids.append(-100)
...             previous_word_idx = word_idx
...         labels.append(label_ids)

...     tokenized_inputs["labels"] = labels
...     return tokenized_inputs

Copied

>>> tokenized_wnut = wnut.map(tokenize_and_align_labels, batched=True)

PytorchHide Pytorch contentCopied

>>> from transformers import DataCollatorForTokenClassification

>>> data_collator = DataCollatorForTokenClassification(tokenizer=tokenizer)

TensorFlowHide TensorFlow contentCopied

>>> from transformers import DataCollatorForTokenClassification

>>> data_collator = DataCollatorForTokenClassification(tokenizer=tokenizer, return_tensors="tf")

Evaluate

Copied

>>> import evaluate

>>> seqeval = evaluate.load("seqeval")

Get the NER labels first, and then create a function that passes your true predictions and true labels to compute to calculate the scores:

Copied

>>> import numpy as np

>>> labels = [label_list[i] for i in example[f"ner_tags"]]


>>> def compute_metrics(p):
...     predictions, labels = p
...     predictions = np.argmax(predictions, axis=2)

...     true_predictions = [
...         [label_list[p] for (p, l) in zip(prediction, label) if l != -100]
...         for prediction, label in zip(predictions, labels)
...     ]
...     true_labels = [
...         [label_list[l] for (p, l) in zip(prediction, label) if l != -100]
...         for prediction, label in zip(predictions, labels)
...     ]

...     results = seqeval.compute(predictions=true_predictions, references=true_labels)
...     return {
...         "precision": results["overall_precision"],
...         "recall": results["overall_recall"],
...         "f1": results["overall_f1"],
...         "accuracy": results["overall_accuracy"],
...     }

Your compute_metrics function is ready to go now, and youโ€™ll return to it when you setup your training.

Train

Before you start training your model, create a map of the expected ids to their labels with id2label and label2id:

Copied

>>> id2label = {
...     0: "O",
...     1: "B-corporation",
...     2: "I-corporation",
...     3: "B-creative-work",
...     4: "I-creative-work",
...     5: "B-group",
...     6: "I-group",
...     7: "B-location",
...     8: "I-location",
...     9: "B-person",
...     10: "I-person",
...     11: "B-product",
...     12: "I-product",
... }
>>> label2id = {
...     "O": 0,
...     "B-corporation": 1,
...     "I-corporation": 2,
...     "B-creative-work": 3,
...     "I-creative-work": 4,
...     "B-group": 5,
...     "I-group": 6,
...     "B-location": 7,
...     "I-location": 8,
...     "B-person": 9,
...     "I-person": 10,
...     "B-product": 11,
...     "I-product": 12,
... }

PytorchHide Pytorch content

Copied

>>> from transformers import AutoModelForTokenClassification, TrainingArguments, Trainer

>>> model = AutoModelForTokenClassification.from_pretrained(
...     "distilbert-base-uncased", num_labels=13, id2label=id2label, label2id=label2id
... )

At this point, only three steps remain:

Copied

>>> training_args = TrainingArguments(
...     output_dir="my_awesome_wnut_model",
...     learning_rate=2e-5,
...     per_device_train_batch_size=16,
...     per_device_eval_batch_size=16,
...     num_train_epochs=2,
...     weight_decay=0.01,
...     evaluation_strategy="epoch",
...     save_strategy="epoch",
...     load_best_model_at_end=True,
...     push_to_hub=True,
... )

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=tokenized_wnut["train"],
...     eval_dataset=tokenized_wnut["test"],
...     tokenizer=tokenizer,
...     data_collator=data_collator,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

Copied

>>> trainer.push_to_hub()

TensorFlowHide TensorFlow content

To finetune a model in TensorFlow, start by setting up an optimizer function, learning rate schedule, and some training hyperparameters:Copied

>>> from transformers import create_optimizer

>>> batch_size = 16
>>> num_train_epochs = 3
>>> num_train_steps = (len(tokenized_wnut["train"]) // batch_size) * num_train_epochs
>>> optimizer, lr_schedule = create_optimizer(
...     init_lr=2e-5,
...     num_train_steps=num_train_steps,
...     weight_decay_rate=0.01,
...     num_warmup_steps=0,
... )

Copied

>>> from transformers import TFAutoModelForTokenClassification

>>> model = TFAutoModelForTokenClassification.from_pretrained(
...     "distilbert-base-uncased", num_labels=13, id2label=id2label, label2id=label2id
... )

Copied

>>> tf_train_set = model.prepare_tf_dataset(
...     tokenized_wnut["train"],
...     shuffle=True,
...     batch_size=16,
...     collate_fn=data_collator,
... )

>>> tf_validation_set = model.prepare_tf_dataset(
...     tokenized_wnut["validation"],
...     shuffle=False,
...     batch_size=16,
...     collate_fn=data_collator,
... )

Copied

>>> import tensorflow as tf

>>> model.compile(optimizer=optimizer)  # No loss argument!

Copied

>>> from transformers.keras_callbacks import KerasMetricCallback

>>> metric_callback = KerasMetricCallback(metric_fn=compute_metrics, eval_dataset=tf_validation_set)

Copied

>>> from transformers.keras_callbacks import PushToHubCallback

>>> push_to_hub_callback = PushToHubCallback(
...     output_dir="my_awesome_wnut_model",
...     tokenizer=tokenizer,
... )

Then bundle your callbacks together:

Copied

>>> callbacks = [metric_callback, push_to_hub_callback]

Copied

>>> model.fit(x=tf_train_set, validation_data=tf_validation_set, epochs=3, callbacks=callbacks)

Once training is completed, your model is automatically uploaded to the Hub so everyone can use it!

Inference

Great, now that youโ€™ve finetuned a model, you can use it for inference!

Grab some text youโ€™d like to run inference on:

Copied

>>> text = "The Golden State Warriors are an American professional basketball team based in San Francisco."

Copied

>>> from transformers import pipeline

>>> classifier = pipeline("ner", model="stevhliu/my_awesome_wnut_model")
>>> classifier(text)
[{'entity': 'B-location',
  'score': 0.42658573,
  'index': 2,
  'word': 'golden',
  'start': 4,
  'end': 10},
 {'entity': 'I-location',
  'score': 0.35856336,
  'index': 3,
  'word': 'state',
  'start': 11,
  'end': 16},
 {'entity': 'B-group',
  'score': 0.3064001,
  'index': 4,
  'word': 'warriors',
  'start': 17,
  'end': 25},
 {'entity': 'B-location',
  'score': 0.65523505,
  'index': 13,
  'word': 'san',
  'start': 80,
  'end': 83},
 {'entity': 'B-location',
  'score': 0.4668663,
  'index': 14,
  'word': 'francisco',
  'start': 84,
  'end': 93}]

You can also manually replicate the results of the pipeline if youโ€™d like:

PytorchHide Pytorch content

Tokenize the text and return PyTorch tensors:

Copied

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> inputs = tokenizer(text, return_tensors="pt")

Pass your inputs to the model and return the logits:

Copied

>>> from transformers import AutoModelForTokenClassification

>>> model = AutoModelForTokenClassification.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> with torch.no_grad():
...     logits = model(**inputs).logits

Get the class with the highest probability, and use the modelโ€™s id2label mapping to convert it to a text label:

Copied

>>> predictions = torch.argmax(logits, dim=2)
>>> predicted_token_class = [model.config.id2label[t.item()] for t in predictions[0]]
>>> predicted_token_class
['O',
 'O',
 'B-location',
 'I-location',
 'B-group',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'B-location',
 'B-location',
 'O',
 'O']

TensorFlowHide TensorFlow content

Tokenize the text and return TensorFlow tensors:

Copied

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> inputs = tokenizer(text, return_tensors="tf")

Pass your inputs to the model and return the logits:

Copied

>>> from transformers import TFAutoModelForTokenClassification

>>> model = TFAutoModelForTokenClassification.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> logits = model(**inputs).logits

Get the class with the highest probability, and use the modelโ€™s id2label mapping to convert it to a text label:

Copied

>>> predicted_token_class_ids = tf.math.argmax(logits, axis=-1)
>>> predicted_token_class = [model.config.id2label[t] for t in predicted_token_class_ids[0].numpy().tolist()]
>>> predicted_token_class
['O',
 'O',
 'B-location',
 'I-location',
 'B-group',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'B-location',
 'B-location',
 'O',
 'O']

Mapping all tokens to their corresponding word with the method.

Assigning the label -100 to the special tokens [CLS] and [SEP] so theyโ€™re ignored by the PyTorch loss function (see ).

To apply the preprocessing function over the entire dataset, use ๐ŸŒŽ Datasets function. You can speed up the map function by setting batched=True to process multiple elements of the dataset at once:

Now create a batch of examples using . Itโ€™s more efficient to dynamically pad the sentences to the longest length in a batch during collation, instead of padding the whole dataset to the maximum length.

Including a metric during training is often helpful for evaluating your modelโ€™s performance. You can quickly load a evaluation method with the ๐ŸŒŽ library. For this task, load the framework (see the ๐ŸŒŽ Evaluate to learn more about how to load and compute a metric). Seqeval actually produces several scores: precision, recall, F1, and accuracy.

If you arenโ€™t familiar with finetuning a model with the , take a look at the basic tutorial !

Youโ€™re ready to start training your model now! Load DistilBERT with along with the number of expected labels, and the label mappings:

Define your training hyperparameters in . The only required parameter is output_dir which specifies where to save your model. Youโ€™ll push this model to the Hub by setting push_to_hub=True (you need to be signed in to BOINC AI to upload your model). At the end of each epoch, the will evaluate the seqeval scores and save the training checkpoint.

Pass the training arguments to along with the model, dataset, tokenizer, data collator, and compute_metrics function.

Call to finetune your model.

Once training is completed, share your model to the Hub with the method so everyone can use your model:

If you arenโ€™t familiar with finetuning a model with Keras, take a look at the basic tutorial !

Then you can load DistilBERT with along with the number of expected labels, and the label mappings:

Convert your datasets to the tf.data.Dataset format with :

Configure the model for training with . Note that Transformers models all have a default task-relevant loss function, so you donโ€™t need to specify one unless you want to:

The last two things to setup before you start training is to compute the seqeval scores from the predictions, and provide a way to push your model to the Hub. Both are done by using .

Pass your compute_metrics function to :

Specify where to push your model and tokenizer in the :

Finally, youโ€™re ready to start training your model! Call with your training and validation datasets, the number of epochs, and your callbacks to finetune the model:

For a more in-depth example of how to finetune a model for token classification, take a look at the corresponding or .

The simplest way to try out your finetuned model for inference is to use it in a . Instantiate a pipeline for NER with your model, and pass your text to it:

๐ŸŒ
๐ŸŒ
DistilBERT
WNUT 17
ALBERT
BERT
BigBird
BioGpt
BLOOM
BROS
CamemBERT
CANINE
ConvBERT
Data2VecText
DeBERTa
DeBERTa-v2
DistilBERT
ELECTRA
ERNIE
ErnieM
ESM
Falcon
FlauBERT
FNet
Funnel Transformer
GPT-Sw3
OpenAI GPT-2
GPTBigCode
GPT Neo
GPT NeoX
I-BERT
LayoutLM
LayoutLMv2
LayoutLMv3
LiLT
Longformer
LUKE
MarkupLM
MEGA
Megatron-BERT
MobileBERT
MPNet
MPT
MRA
Nezha
Nystrรถmformer
QDQBert
RemBERT
RoBERTa
RoBERTa-PreLayerNorm
RoCBert
RoFormer
SqueezeBERT
XLM
XLM-RoBERTa
XLM-RoBERTa-XL
XLNet
X-MOD
YOSO
word_ids
CrossEntropyLoss
map
DataCollatorWithPadding
Evaluate
seqeval
quick tour
Trainer
here
AutoModelForTokenClassification
TrainingArguments
Trainer
Trainer
train()
push_to_hub()
here
TFAutoModelForTokenClassification
prepare_tf_dataset()
compile
Keras callbacks
KerasMetricCallback
PushToHubCallback
fit
PyTorch notebook
TensorFlow notebook
pipeline()