huggingface-transformers

tokenizer.save_pretrained TypeError: Object of type property is not JSON serializable Question: I am trying to save the GPT2 tokenizer as follows: from transformers import GPT2Tokenizer, GPT2LMHeadModel tokenizer = GPT2Tokenizer.from_pretrained("gpt2") tokenizer.pad_token = GPT2Tokenizer.eos_token dataset_file = "x.csv" df = pd.read_csv(dataset_file, sep=",") input_ids = tokenizer.batch_encode_plus(list(df["x"]), max_length=1024,padding=’max_length’,truncation=True)["input_ids"] # saving the tokenizer tokenizer.save_pretrained("tokenfile") I am getting the following error: TypeError: …

Error 'img' when applying increment with keras and transformers for image classification Question: I would like to apply VIT for image classification. But I have one problem and I don’t know as resolve it. My error is this "KeyError: ‘img’". The error is shown when I apply the last comand, and I don’t know where …

How do you train Huggingface Maskformer for instance segmentation? Question: I can see an example to train for semantic segmentation but I’m unclear how to fine tune a model for instance segmentation. Specifically how to calculate the loss function assuming the data is in COCO format? Asked By: nickponline || Source Answers: I found a …

Pytorch complaining about input and label batch size mismatch Question: I am using Huggingface to implement a BERT model using BertForSequenceClassification.from_pretrained(). The model is trying to predict 1 of 24 classes. I am using a batch size of 32 and a sequence length of 66. When I try to call the model in training, I …

Train T5/BART to convert a string into multiple strings Question: Is it possible to train a seq2seq model like T5 or BART to convert a string into a list of strings? On my first attempt, the tokenizer complained that my 2D list of labels isn’t the correct data type: File "/home/matt/miniconda3/envs/nlp/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 429, in _batch_encode_plus …

TypeError: unsupported operand type(s) for /: 'SequenceClassifierOutput' and 'int' Question: I am using hugginface library to train a bert model on classification problem. model = BertForSequenceClassification.from_pretrained(‘bert-base-uncased’, num_labels=10) def training_step(self, batch, batch_nb): sequence, label = batch input_ids, attention_mask, labels = self.prepare_batch(sequence=sequence, label=label) loss = self.model(input_ids=input_ids, attention_mask=attention_mask, labels=labels) tensorboard_logs = {‘train_loss’: loss} I am getting the following …

How to split input text into equal size of tokens, not character length, and then concatenate the summarization results for Hugging Face transformers Question: I am using the below methodology to summarize longer than 1024 token size long texts. Current method splits the text by half. I took this from another user’s post and modified …

How to enable GPU for SetFit? Question: I am following this tutorial for SetFit: https://www.philschmid.de/getting-started-setfit When the training is running, it is using my CPU instead of my GPU. Is there a way I can enable it? Here is the main part of the code: from setfit import SetFitModel, SetFitTrainer from sentence_transformers.losses import CosineSimilarityLoss # …

How to fine-tune gpt-j using Huggingface Trainer Question: I’m attempting to fine-tune gpt-j using the huggingface trainer and failing miserably. I followed the example that references bert, but of course, the gpt-j model isn’t exactly like the bert model. The error indicates that the model isn’t producing a loss, which is great, except that I …

The expanded size of the tensor (1011) must match the existing size (512) at non-singleton dimension 1 Question: I have a trained a LayoutLMv2 model from huggingface and when I try to inference it on a single image, it gives the runtime error. The code for this is below: query = ‘/Users/vaihabsaxena/Desktop/Newfolder/labeled/Others/Two.pdf26.png’ image = Image.open(query).convert("RGB") …