|
Why my Traing accuracy remains constant
|
|
2
|
156
|
January 20, 2025
|
|
My Accuracy remains constant
|
|
1
|
56
|
January 18, 2025
|
|
Getting NaN training and validation loss when training BERT model on pytorch
|
|
2
|
162
|
January 17, 2025
|
|
How to properly apply causal mask for next char prediction in MLP
|
|
1
|
294
|
January 10, 2025
|
|
Documents as parametric memory
|
|
0
|
88
|
January 11, 2025
|
|
Need help with Recurrent lstms
|
|
0
|
18
|
January 10, 2025
|
|
How to Implement Flash Attention in a Pre-Trained BERT Model on custom dataset?
|
|
0
|
156
|
January 8, 2025
|
|
Embedding a float into a vector for transformer models
|
|
1
|
115
|
January 7, 2025
|
|
Building a Model for Multi-Output Embedding Generation: Seeking Advice and Insights
|
|
0
|
35
|
January 4, 2025
|
|
Is the code correct for character level generation in lstm?
|
|
12
|
1522
|
December 27, 2024
|
|
Correct way to batch custom masks in SDPA
|
|
0
|
63
|
December 12, 2024
|
|
Weight Decay for tied weights (embedding and linear layers)
|
|
1
|
1093
|
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
|
113780
|
December 7, 2024
|
|
Model performance decrease to nearly 1/4 when loading a checkpoint, but works fine for "simpler" data and in-script
|
|
5
|
1736
|
December 6, 2024
|
|
Help Needed: Transformer Model Repeating Last Token During Inference
|
|
3
|
493
|
December 5, 2024
|
|
Understanding logits in GPT2
|
|
0
|
163
|
December 5, 2024
|
|
Flex_attention returning logits
|
|
0
|
90
|
December 4, 2024
|
|
Unable to import torchtext (from torchtext.datasets import IMDB from torchtext.vocab import vocab)
|
|
4
|
2842
|
December 1, 2024
|
|
How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?
|
|
0
|
832
|
November 29, 2024
|
|
How to compute the Validation loss
|
|
2
|
45
|
November 24, 2024
|
|
Computation of nn.Linear and nn.Embedding
|
|
1
|
171
|
November 22, 2024
|
|
Log softmax probabilities all equal in rnn decoder because pointer network scores are all < -90.0
|
|
0
|
124
|
November 19, 2024
|
|
How to correct TypeError: zip argument #1 must support iteration training in multiple GPU
|
|
6
|
1120
|
November 13, 2024
|
|
Training starting again in sampling code
|
|
3
|
48
|
November 9, 2024
|
|
AutoModelForCausalLM dataset process
|
|
1
|
261
|
November 9, 2024
|
|
Can someone explain the benefits of Batches?
|
|
2
|
160
|
November 8, 2024
|
|
Teacher forcing ratio
|
|
0
|
239
|
November 8, 2024
|
|
Search in documents
|
|
2
|
177
|
November 7, 2024
|
|
Torch using two GPUs with NV link
|
|
8
|
662
|
November 5, 2024
|
|
Could not get the file at http://www.quest.dcs.shef.ac.uk/wmt16_files_mmt/training.tar.gz. [RequestException] None
|
|
6
|
2061
|
October 29, 2024
|