|
Is attention of different encoder layers comprabale?
|
|
0
|
281
|
December 6, 2022
|
|
Fine-tuning T5 with long sequence length, using activation checkpointing with Deepspeed
|
|
6
|
2932
|
December 5, 2022
|
|
ð£ Weights & Biases - Feedback
|
|
2
|
629
|
December 5, 2022
|
|
Seq2SeqTrainer: enabled must be a bool (got NoneType)
|
|
15
|
3966
|
December 5, 2022
|
|
Manually Downloading Models in docker build with snapshot_download
|
|
2
|
17371
|
December 5, 2022
|
|
Will masking more tokens speed up training and use less memory in HuggingFace's Bert or Roberta?
|
|
1
|
294
|
December 3, 2022
|
|
Model pre-training precision database: fp16, fp32, bf16
|
|
4
|
7085
|
December 3, 2022
|
|
If use mix precision training using fp16, need torchdynamo (TensorRT)?
|
|
3
|
745
|
December 2, 2022
|
|
Make ModelForLinearTransformation available as a generic head for all model types?
|
|
5
|
563
|
December 1, 2022
|
|
Can we use mixed precision with all? (fp16 + fp32 + bf16)
|
|
0
|
273
|
December 1, 2022
|
|
Get warning "Could not estimate the number of tokens of the input, floating-point operations will not be computed" when use a customize Trainer and customize data collator
|
|
5
|
6186
|
November 30, 2022
|
|
How to accessing the input_ids in EvalPrediction.predictions in Seq2SeqTrainer?
|
|
5
|
2257
|
November 25, 2022
|
|
Change training data in Trainer with callback
|
|
3
|
1228
|
November 29, 2022
|
|
Error with runing bert question-answering fine-tuning
|
|
1
|
306
|
November 29, 2022
|
|
Bert2Bert passing input_ids to compute_metrics through the Seq2SeqTrainingArguments
|
|
0
|
260
|
November 29, 2022
|
|
When does the third conditional branch of the project function that generates hidden_statesâquery,value in T5 work?
|
|
0
|
181
|
November 29, 2022
|
|
Bert Model with Different Architectures Understanding and Make Custom Model (architecture) Using Transformer Library
|
|
0
|
394
|
November 29, 2022
|
|
Gradual Layer Freezing
|
|
6
|
4666
|
November 28, 2022
|
|
How to obtain GPT2 tokens without Transformers library?
|
|
0
|
252
|
November 28, 2022
|
|
How to provide "negative topics" for OPTForCausalLM?
|
|
0
|
218
|
November 26, 2022
|
|
Batch size for trainer.predict()
|
|
4
|
6933
|
November 26, 2022
|
|
PyTorch Transformers: TypeError: forward() got an unexpected keyword argument 'encoder_hidden_states'
|
|
0
|
2987
|
November 26, 2022
|
|
Validation loss shows 'No log'
|
|
0
|
843
|
November 25, 2022
|
|
Options for feature addition
|
|
0
|
1008
|
November 24, 2022
|
|
How to add Sentence Bert to keras sequential model?
|
|
0
|
569
|
November 24, 2022
|
|
What is point of tokenizer.json in MT0?
|
|
0
|
223
|
November 24, 2022
|
|
How to avoid RAM and Memory errors
|
|
0
|
328
|
November 24, 2022
|
|
How tokenize natural words by using Tokenizer from transformer pretrained models
|
|
0
|
223
|
November 23, 2022
|
|
Cuda memory error even when passing the no_cuda argument
|
|
0
|
612
|
November 23, 2022
|
|
Metric while training and after one are different
|
|
0
|
241
|
November 23, 2022
|