|
Using TFOpenAIGPTLMHeadModel load pytorch model doesn't work well
|
|
0
|
280
|
September 8, 2021
|
|
Label smoothing and compute_metrics in Trainer
|
|
1
|
1150
|
September 7, 2021
|
|
CLIP Linear Probing?
|
|
0
|
1044
|
September 7, 2021
|
|
Save custom transformer as PreTrainedModel
|
|
1
|
907
|
September 7, 2021
|
|
Translation takes too long - from fine-tuned mbart-large-50 model
|
|
0
|
401
|
September 7, 2021
|
|
Create DPR Tokenizer for non-Bert model
|
|
1
|
308
|
September 7, 2021
|
|
Suggestions on ideal model architecture for sentence correction?
|
|
0
|
265
|
September 6, 2021
|
|
Extract similar word from model
|
|
1
|
2762
|
September 6, 2021
|
|
Wav2Vec2: Inner workings of the Trainer class
|
|
6
|
377
|
September 6, 2021
|
|
Minimum size for Summarization
|
|
0
|
331
|
September 6, 2021
|
|
Attention type 'block_sparse' is not possible if sequence_length: 458 <= num global tokens:
|
|
4
|
1048
|
September 6, 2021
|
|
Problems with Dataset.from_dict() and Feature types
|
|
1
|
2157
|
September 6, 2021
|
|
Finetuning conditional language model generation
|
|
0
|
555
|
September 6, 2021
|
|
Implementing a custom Attention Transformer
|
|
5
|
3161
|
September 6, 2021
|
|
Request: reset api key
|
|
1
|
273
|
September 6, 2021
|
|
Urdu NLP - Introductions šµš°
|
|
1
|
1097
|
September 6, 2021
|
|
Type of model for PubMed article processing
|
|
1
|
353
|
September 6, 2021
|
|
Batching in SageMaker Inference Toolkit
|
|
2
|
971
|
September 5, 2021
|
|
Parameter lm_head returning none in tensorflow but works for pytorch
|
|
0
|
262
|
September 4, 2021
|
|
GPT2: many bad_words_ids leading to slow text generation?
|
|
0
|
1534
|
September 4, 2021
|
|
ONNX exported model outputs different value per inference call for the same input
|
|
1
|
354
|
September 4, 2021
|
|
Logits and labels must have the same shape ((512, 6) vs (6, 1)) - MultiClass Classification with BERT
|
|
0
|
1442
|
September 3, 2021
|
|
How are the inputs tokenized when model deployment?
|
|
13
|
4259
|
September 3, 2021
|
|
Why BigBirdTokenizer canāt load my own vocab or trained BPE resultsļ¼
|
|
2
|
2781
|
September 3, 2021
|
|
Fintuning Transformer on CLEF dataset
|
|
7
|
1083
|
September 3, 2021
|
|
My input sentence is very long(more than 512). What should I do when I want to fintune model about classify?Thanks
|
|
3
|
1069
|
September 3, 2021
|
|
SageMaker Inference for Model Tuned Elsewhere
|
|
4
|
1063
|
September 2, 2021
|
|
GPT-2 Logits to tokens for beam search (Generate method)
|
|
0
|
1311
|
September 2, 2021
|
|
Linear learning rate despite lr_scheduler_type="polynomial"
|
|
4
|
1743
|
September 2, 2021
|
|
Cannot replicate xlm-roberta-large-xnli Results
|
|
0
|
496
|
September 2, 2021
|