All Questions
268 questions
0
votes
1
answer
124
views
torch.OutOfMemoryError: CUDA out of memory. (Google Colab)
I tried to adapt the mBERT model to an existing code. However, I received the following issue even though I tried different solutions.
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 20....
- 55
0
votes
0
answers
78
views
Emotion Analysis with bhadresh-savani/bert-base-uncased-emotion
Hope I can get some help here please!
I am trying to run an emotion analysis model from Hugging Face rep. (bhadresh-savani/bert-base-uncased-emotion) and I am struggling with the model run as it's ...
2
votes
1
answer
39
views
How to convert character indices to BERT token indices
I am working with a question-answer dataset UCLNLP/adversarial_qa.
from datasets import load_dataset
ds = load_dataset("UCLNLP/adversarial_qa", "adversarialQA")
How do I map ...
- 632
0
votes
0
answers
17
views
Bert models show tokenizing statistics
Is there any built-in way to request some tokenizing statistics when using BertTokenizer.from_pretrained('bert-base-uncased') and BertModel.from_pretrained('bert-base-uncased') to understand how ...
2
votes
1
answer
58
views
Dutch sentiment analysis RobBERTje outputs just positive/negative labels, netural label is missing
When I run Dutch sentiment analysis RobBERTje, it outputs just positive/negative labels, netural label is missing in the data.
https://huggingface.co/DTAI-KULeuven/robbert-v2-dutch-sentiment
There are ...
- 473
0
votes
1
answer
65
views
Why is Keras pretrained BERT MaskedLM producing inconsistent predictions?
I am trying to use keras-nlp with a pretrained masked BERT model to predict some tokens in a sequence. However the model produces inconsistent results. What could be wrong or am i misunderstanding ...
- 67
0
votes
1
answer
326
views
How do I freeze only some embedding indices with tied embeddings?
I found in Is it possible to freeze only certain embedding weights in the embedding layer in pytorch? a nice way to freeze only some indices of an embedding layer.
However, while including it in a ...
- 11
0
votes
1
answer
84
views
SBERT Fine-tuning always stops before finish all epochs
I'm working on a project using the SBERT pre-trained models (specifically MiniLM) for a text classification project with 995 classifications. I am following the steps laid out here for the most part ...
- 11
1
vote
2
answers
70
views
Identify starting row of actual data in Pandas DataFrame with merged header cells
My original df looks like this -
df
Note in the data frame:
The headers are there till row 3 & from row 4 onwards, the values for those headers are starting.
The numbers of rows & columns ...
- 11
0
votes
0
answers
66
views
BERT embedding cosine similarities look very random and useless
I thought you can use BERT embeddings to determine semantic similarity. I was trying to group some words in categories using this, but the results were very bad.
E.g. here is a small example with ...
- 93
0
votes
0
answers
49
views
The Impact of Pretraining on Fine-tuning and Inference
I am working on a binary prediction classification task, primarily focusing on fine-tuning a BERT model to learn the association between CVEs and CWEs. I've structured my task into three phases: first,...
- 19
0
votes
1
answer
51
views
Trying to run GermanSentiment in Python on 10k to 30k texts, keeps crashing? Possibly too large dataset?
I want to do sentiment analysis on 2 datasets of tweets, one with 9k strings and one with 30k strings. I have imported GermanSentiment and it ran just fine with the demo code from GitHub, but when I ...
- 91
0
votes
0
answers
114
views
How to fix RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
I am trying to use a custom csv dataset to finetune a model: TheBloke/Mistral-7B-Instruct-v0.1-GPTQ.I performed data preprocessing and I split the dataset into train, validation and test set and then ...
- 29
0
votes
0
answers
60
views
Issues Tokenizing SQL Data for BERT Model
I'm working on a project where I need to extract references from a SQL database, preprocess them, and use them to train a BERT model for token classification. Below is the code I have so far:
# -*- ...
- 29
0
votes
0
answers
132
views
TypeError: cross_entropy_loss(): argument 'target' (position 2) must be Tensor, not NoneType
Purpose:
I tried to build a text classification pipeline using PyTorch and the Huggingface transformers library. The plan was to tokenize text data and combine it with numerical features for training ...
- 101