|
How to do few shot in context learning using GPT-NEO
|
|
0
|
1670
|
September 13, 2021
|
|
Using a fixed vocab.txt with AutoTokenizer?
|
|
1
|
2271
|
September 13, 2021
|
|
Hyperparameter Optimization of end-to-end pretraining + fine tuning
|
|
0
|
480
|
September 12, 2021
|
|
BertGeneration generate from input
|
|
0
|
224
|
September 12, 2021
|
|
Bert model on Acceptability Judgement Task || Optimizer Grouped Parameters
|
|
0
|
554
|
September 11, 2021
|
|
Optimal methods to monitor attention matrices when doing training/inference using BERT-type models
|
|
2
|
705
|
September 11, 2021
|
|
RuntimeError: CUDA out of memory. Tried to allocate 1.91 GiB (GPU 0; 15.78 GiB total capacity; 12.36 GiB already allocated; 302.75 MiB free; 14.16 GiB reserved in total by PyTorch)
|
|
2
|
1316
|
September 11, 2021
|
|
Can T5 "forget" Appendix D tasks after fine-tuning?
|
|
0
|
313
|
September 11, 2021
|
|
Which Bert model should we use for this problem. Next Word prediction using LM? Or Keyword Extraction problem?
|
|
1
|
1339
|
September 10, 2021
|
|
Question about Gradient Accumulation step in Trainer
|
|
2
|
2582
|
September 10, 2021
|
|
Class weights in Trainer() instance
|
|
1
|
690
|
September 10, 2021
|
|
Loading opus-mt-es-en fails
|
|
0
|
774
|
September 10, 2021
|
|
Get sentence embedding vector using API?
|
|
0
|
335
|
September 10, 2021
|
|
Hyper parameter tuning on Colab?
|
|
0
|
292
|
September 10, 2021
|
|
Finetuning T5 on translation task
|
|
0
|
487
|
September 10, 2021
|
|
Get next word probability values for words in text
|
|
0
|
368
|
September 10, 2021
|
|
BART from finetuned BERT
|
|
2
|
470
|
September 9, 2021
|
|
Save map cache to s3 bucket
|
|
2
|
693
|
September 9, 2021
|
|
GPT2 chat-bot single interaction… Attribute Error: 'NoneType' object has no attribute 'multiprocessing_chunksize'
|
|
0
|
273
|
September 9, 2021
|
|
[Call for participation] Interactive Grounded Language Understanding in a Collaborative Environment (IGLU) Competition@NeurIPS2021
|
|
0
|
725
|
September 9, 2021
|
|
Load model weights in a different model architecture
|
|
0
|
513
|
September 9, 2021
|
|
Train wordpiece from scratch
|
|
2
|
1409
|
September 9, 2021
|
|
Inference API Issues
|
|
0
|
2713
|
September 9, 2021
|
|
Run_summarization.py Rouge in eval cf. in final eval, predict
|
|
0
|
671
|
September 8, 2021
|
|
Extending a GPT2 Model (Dialo)
|
|
0
|
571
|
September 9, 2021
|
|
Continual pre-training from an initial checkpoint with MLM and NSP
|
|
4
|
4252
|
September 8, 2021
|
|
Identifying and getting right embeddings from the fine tuned BERT on domain specific data
|
|
0
|
1327
|
September 8, 2021
|
|
Training Model on CPU instead of GPU
|
|
1
|
4780
|
September 8, 2021
|
|
Arabic NLP - Resources
|
|
2
|
2032
|
September 8, 2021
|
|
Any fast NER models that work in the browser?
|
|
0
|
393
|
September 8, 2021
|