Model saved into an unique .h5 file (or TensorflowLight)
|
|
5
|
6217
|
July 27, 2022
|
Class prediction in a zero/few-shot setting at inference time
|
|
0
|
401
|
July 27, 2022
|
\multi-node finetuning with Trainer
|
|
0
|
478
|
July 27, 2022
|
Optimum & RoBERTa: how far can we trust a quantized model against its pytorch version?
|
|
10
|
2405
|
July 27, 2022
|
Using Accelerate on an HPC (Slurm)
|
|
10
|
10386
|
July 27, 2022
|
Visualizing named entities
|
|
0
|
321
|
July 27, 2022
|
PreTrain T5 from scratch in Bengali
|
|
5
|
2207
|
July 26, 2022
|
Running mT5 on multiple GPUs
|
|
0
|
520
|
July 26, 2022
|
Why can't the bloom model be run (really slowly) on consumer hardware?
|
|
2
|
558
|
July 26, 2022
|
Tensorflow Models are way slower than Pytorch models, for autoregressive generation?
|
|
3
|
389
|
July 26, 2022
|
Boosting Wav2Vec2-xls-r with an N gram decoder using the transcripts used to train wav2vec2
|
|
1
|
985
|
July 26, 2022
|
Wav2vec2-large-xlsr-53
|
|
4
|
815
|
July 26, 2022
|
Extracting HuBERT hidden units
|
|
1
|
1146
|
July 26, 2022
|
Network is Unreachable Error
|
|
0
|
1559
|
July 26, 2022
|
There is a adamw optimizer in pytorch version.Is there a adamw in tensorflow2 version
|
|
1
|
283
|
July 26, 2022
|
How to add multiple metrics to Huggingface Transformers Trainer?
|
|
1
|
2071
|
July 26, 2022
|
T5 transformer tokens and scores
|
|
0
|
709
|
July 26, 2022
|
Inference Input for Vision Models
|
|
6
|
1312
|
July 26, 2022
|
Dynamic range quantization for HF models seem to be spurious
|
|
0
|
200
|
July 26, 2022
|
Anomaly Detection / Out of Domain Detection with BERT
|
|
0
|
964
|
July 26, 2022
|
Fused Kernel Operations
|
|
0
|
622
|
July 26, 2022
|
Avoid creating certain tokens when training a tokenizer
|
|
0
|
602
|
July 26, 2022
|
How to find closest embedding vectors?
|
|
2
|
1750
|
July 26, 2022
|
Fine-tune OPT 13B: CUDA out of memory error (720gb vram, batch size 1, fp16)!
|
|
6
|
4573
|
July 25, 2022
|
Why Tensorflow Models are way slower than Pytorch models, for autoregressive modeling?
|
|
10
|
2102
|
July 25, 2022
|
How to correctly measure inference time?
|
|
0
|
935
|
July 25, 2022
|
DETR: use torchscripted model on both cpu and gpu
|
|
0
|
456
|
July 25, 2022
|
Segmentation of drone images
|
|
2
|
483
|
July 25, 2022
|
BERT Once-Class Fine-Tuning
|
|
0
|
282
|
July 25, 2022
|
Why can't I pass my directly encoded inputs to a model?
|
|
5
|
4524
|
July 25, 2022
|