|
Full finetune, LoRA and feature extraction take the same amount of memory and time to train
|
|
0
|
41
|
March 14, 2025
|
|
Pytorch OCR models for deploying to ESP32?
|
|
0
|
131
|
March 12, 2025
|
|
How to train two independent networks
|
|
2
|
88
|
March 4, 2025
|
|
How to implement skip-gram or CBOW in pytorch
|
|
10
|
12056
|
March 4, 2025
|
|
How to handle last batch in LSTM hidden state
|
|
8
|
6370
|
February 22, 2025
|
|
Slow attention when using kvCache
|
|
1
|
79
|
February 21, 2025
|
|
Why facing "CUDA error: device-side assert triggered" while training LSTM model?
|
|
5
|
65
|
February 14, 2025
|
|
LSTM for classification (fraud detection) over several lines of text
|
|
0
|
145
|
February 7, 2025
|
|
Importing torchtext
|
|
1
|
389
|
February 3, 2025
|
|
Left / right side padding
|
|
0
|
36
|
February 1, 2025
|
|
Feed a model with cumulative sum of sampled classified sequences
|
|
0
|
33
|
January 30, 2025
|
|
TransformerDecoder masks shape error using model.eval()
|
|
3
|
273
|
January 27, 2025
|
|
What is the right way to structure `input` and `label` while fine-tuning decoder only model
|
|
0
|
32
|
January 27, 2025
|
|
combining TEXT.build_vocab with BERT Embedding
|
|
0
|
73
|
January 27, 2025
|
|
Multi-node, Multi-gpu training
|
|
0
|
109
|
January 24, 2025
|
|
Why my Traing accuracy remains constant
|
|
2
|
180
|
January 20, 2025
|
|
My Accuracy remains constant
|
|
1
|
77
|
January 18, 2025
|
|
Getting NaN training and validation loss when training BERT model on pytorch
|
|
2
|
202
|
January 17, 2025
|
|
How to properly apply causal mask for next char prediction in MLP
|
|
1
|
424
|
January 10, 2025
|
|
Documents as parametric memory
|
|
0
|
105
|
January 11, 2025
|
|
Need help with Recurrent lstms
|
|
0
|
29
|
January 10, 2025
|
|
Embedding a float into a vector for transformer models
|
|
1
|
167
|
January 7, 2025
|
|
Building a Model for Multi-Output Embedding Generation: Seeking Advice and Insights
|
|
0
|
56
|
January 4, 2025
|
|
Is the code correct for character level generation in lstm?
|
|
12
|
1554
|
December 27, 2024
|
|
Correct way to batch custom masks in SDPA
|
|
0
|
76
|
December 12, 2024
|
|
Weight Decay for tied weights (embedding and linear layers)
|
|
1
|
1260
|
December 10, 2024
|
|
RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect
|
|
10
|
115378
|
December 7, 2024
|
|
Model performance decrease to nearly 1/4 when loading a checkpoint, but works fine for "simpler" data and in-script
|
|
5
|
1821
|
December 6, 2024
|
|
Help Needed: Transformer Model Repeating Last Token During Inference
|
|
3
|
707
|
December 5, 2024
|
|
Understanding logits in GPT2
|
|
0
|
208
|
December 5, 2024
|