How can I change the forward function of BertForSequenceClassification
|
|
0
|
1861
|
August 14, 2021
|
Error: 'AlbertModel' object has no attribute 'bias' -Trying to use custom corpus pretrained Albert chkpt
|
|
0
|
380
|
August 14, 2021
|
When will layoutlmv2 be merged into a stable branch
|
|
0
|
292
|
August 14, 2021
|
Reproducibility problem while using GPT-2
|
|
0
|
819
|
August 14, 2021
|
Is there a way to correctly load a pre-trained transformers model without the configuration file?
|
|
6
|
17593
|
August 13, 2021
|
Huge difference in speed when finetuning summarization with different scripts
|
|
4
|
889
|
August 13, 2021
|
Auto-generation of Messages to Commits | Project Proposing
|
|
4
|
1576
|
August 13, 2021
|
How to save my tokenizer using save_pretrained?
|
|
5
|
28096
|
August 13, 2021
|
Pad Token and attention mask. What is the difference?
|
|
0
|
961
|
August 13, 2021
|
BertForTokenClassification Classifying [PAD] tokens
|
|
0
|
280
|
August 13, 2021
|
Word casing affects NER tagging
|
|
0
|
274
|
August 12, 2021
|
Tokenizer vs. TokenizerFast
|
|
5
|
6762
|
August 12, 2021
|
How to align sub words to words in Sentencepiece like Albert for NER?
|
|
0
|
207
|
August 12, 2021
|
What is the purpose of save_pretrained()?
|
|
4
|
44788
|
August 12, 2021
|
T5 masking - spans of text tokens or encoded tokens?
|
|
0
|
811
|
August 12, 2021
|
Topic classification: is zero-shot the way?
|
|
0
|
300
|
August 12, 2021
|
Equivalent of `inputs_embeds` for `FlaxGPT2Model`
|
|
0
|
251
|
August 12, 2021
|
Extracting attention weights of summarization model
|
|
0
|
436
|
August 12, 2021
|
How can I get the score from Question-Answer Pipeline? Is there a bug when Question-answer pipeline is used?
|
|
1
|
863
|
August 11, 2021
|
T5 spans - need to predict EMPTY or not
|
|
0
|
408
|
August 11, 2021
|
Unable to use custom dataset when training a tokenizer
|
|
2
|
360
|
August 11, 2021
|
How does the Trainer work for Text Generation?
|
|
0
|
1010
|
August 11, 2021
|
Object has no attribute 'parameters'
|
|
5
|
3672
|
August 11, 2021
|
Pre-training/fine-tuning Seq2Seq model for spelling and/or grammar correction in French
|
|
6
|
1998
|
August 11, 2021
|
Custom files for run_ner.py
|
|
0
|
539
|
August 11, 2021
|
Padding causes wrong predictions?
|
|
2
|
1543
|
August 11, 2021
|
Tokenization in a NER context
|
|
5
|
5627
|
August 11, 2021
|
I can't concatenate_datasets because features are not sorted. How do I sort it?
|
|
3
|
5406
|
August 11, 2021
|
Multiple sentences in RoBERTa training
|
|
0
|
573
|
August 10, 2021
|
Is there a way to finetune GPT2 775M on 16GB VRAM and 24GB RAM?
|
|
1
|
867
|
August 10, 2021
|