Giters
utterworks
/
fast-bert
Super easy library for BERT based NLP models
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1854
Watchers:
42
Issues:
252
Forks:
341
utterworks/fast-bert Issues
Exception has occurred: TypeError object of type 'NoneType' has no len() in learner_cls.py when do Model inference
Updated
5 months ago
How to load model.safetensors using fast_bert using python3.*
Updated
6 months ago
Creation of BertClassificationPredictor breaks
Updated
9 months ago
accuracy function only gives zero-output and breaks for new numpy version
Updated
9 months ago
[Suggestion] Pin requirement versions (specifically python-box)
Updated
a year ago
Comments count
1
How to use cuDNN device with fast-bert
Closed
2 years ago
Comments count
2
How do I clear GPU memory after this program finishes running
Updated
2 years ago
Comments count
1
in case of multi-label classfication there is no way to change label column name in val.csv, and label_col parameter will be a list of label columns from labels.csv?
Updated
2 years ago
Comments count
1
When is the random_seed being used in training. the multi_label classification gives me different results on each running
Updated
2 years ago
Comments count
1
TypeError: forward() got an unexpected keyword argument 'masked_lm_labels'
Updated
2 years ago
DtypeWarning: Columns (0,1) have mixed types. Specify dtype option on import or set low_memory=False
Updated
2 years ago
Comments count
2
[BUG] AttributeError: 'RobertaTokenizer' object has no attribute 'max_len'
Updated
2 years ago
can the version pins for tokenizers and transformers be removed, in requirements.txt?
Updated
3 years ago
Comments count
2
Error in `predict` for BertClassificationPredictor - logger is None
Updated
3 years ago
ValueError: Stop argument for islice() must be None or an integer: 0 <= x <= sys.maxsize.
Updated
3 years ago
Comments count
2
Converting a Pytorch Dataloader to BertDataBunch
Updated
3 years ago
lr_find() taking so much time when running readme.md example
Updated
3 years ago
1.7.0 working notebook/data fails in 1.9.1
Updated
3 years ago
Comments count
3
Any way to save the model artifacts during training?
Updated
3 years ago
Support for Semantic Search/Semantic similarity
Closed
3 years ago
PicklingError: Can't pickle <class 'fast_bert.data_cls.InputFeatures'>: import of module 'fast_bert.data_cls' failed
Updated
3 years ago
Issue with BertNERPredictor.predict_batch(array)
Updated
3 years ago
how to manage output values of prediction (predictor.predict_batch)
Closed
3 years ago
Comments count
2
Missing token-level classification task
Updated
3 years ago
Target Batch Size Doubling: ValueError: Target size (torch.Size([16, 5])) must be the same as input size (torch.Size([8, 5]))
Closed
3 years ago
Comments count
1
CUDA out of memory when runnig the code from example
Updated
3 years ago
Comments count
3
Can not fine tuning lanague model using Colab
Updated
3 years ago
Comments count
1
Not finding CUDA when building docker image
Updated
3 years ago
Index Error
Updated
3 years ago
Comments count
1
CUBLAS_STATUS_ALLOC_FAILED when calling cublasCreate(handle)
Updated
4 years ago
predict from sample_notebook producing error
Updated
4 years ago
bug in data_lm.py
Closed
4 years ago
Would love to see the example of using fast-bert for ner task
Updated
4 years ago
Error: cannot import name 'Unigram' from fast_bert.data_cls import BertDataBunch
Updated
4 years ago
Comments count
2
How to do regression analysis with fast-bert?
Updated
4 years ago
jsonl format for ner task
Updated
4 years ago
BertLearner.from_pretrained_model() shows error: name 'pos_weight' is not defined
Updated
4 years ago
Comments count
2
Error: name 'pos_weight' is not defined (multi-label classification)
Updated
4 years ago
Comments count
1
Using fast-bert to fine-tune pretrained BioBERT model
Updated
4 years ago
Issue with finetuning pretraining Language model using container on sagemaker
Updated
4 years ago
Multilabel fine-tuning fixes
Updated
4 years ago
ERROR: No matching distribution found for itertools (from fast-bert)
Updated
4 years ago
Comments count
4
Is it possible to retrieve original data from fast_bert.data_cls.BertDataBunch object ?
Closed
4 years ago
Comments count
3
Not able to import the module
Updated
4 years ago
OSError: Can't load config for saved_model when deploying on AWS EC2.
Updated
4 years ago
Error for training job failed. reason: algorithmerror: exit code: 127 - SageMaker
Closed
4 years ago
Comments count
1
fast-bert/fast_bert/learner_lm.py syntax error, missing closing '}' on model classes
Closed
4 years ago
Comments count
1
printing / saving out the accuracy results of the learner object
Updated
4 years ago
Problem in prediction AttributeError: 'WindowsPath' object has no attribute 'decode'
Updated
4 years ago
Adding an attention layer to the multiclass classification
Closed
4 years ago
Previous
Next