|
What's a good replacement for torchtext?
|
|
0
|
289
|
December 18, 2024
|
|
Correct way to batch custom masks in SDPA
|
|
0
|
46
|
December 12, 2024
|
|
Weight Decay for tied weights (embedding and linear layers)
|
|
1
|
951
|
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
|
110007
|
December 7, 2024
|
|
Model performance decrease to nearly 1/4 when loading a checkpoint, but works fine for "simpler" data and in-script
|
|
5
|
1642
|
December 6, 2024
|
|
Help Needed: Transformer Model Repeating Last Token During Inference
|
|
3
|
269
|
December 5, 2024
|
|
Understanding logits in GPT2
|
|
0
|
110
|
December 5, 2024
|
|
Flex_attention returning logits
|
|
0
|
70
|
December 4, 2024
|
|
Unable to import torchtext (from torchtext.datasets import IMDB from torchtext.vocab import vocab)
|
|
4
|
1990
|
December 1, 2024
|
|
How does one set the pad token correctly (not to eos) during fine-tuning to avoid model not predicting EOS?
|
|
0
|
473
|
November 29, 2024
|
|
How to compute the Validation loss
|
|
2
|
30
|
November 24, 2024
|
|
Computation of nn.Linear and nn.Embedding
|
|
1
|
111
|
November 22, 2024
|
|
Log softmax probabilities all equal in rnn decoder because pointer network scores are all < -90.0
|
|
0
|
98
|
November 19, 2024
|
|
How to correct TypeError: zip argument #1 must support iteration training in multiple GPU
|
|
6
|
1117
|
November 13, 2024
|
|
Training starting again in sampling code
|
|
3
|
35
|
November 9, 2024
|
|
AutoModelForCausalLM dataset process
|
|
1
|
195
|
November 9, 2024
|
|
Can someone explain the benefits of Batches?
|
|
2
|
85
|
November 8, 2024
|
|
Teacher forcing ratio
|
|
0
|
160
|
November 8, 2024
|
|
Search in documents
|
|
2
|
133
|
November 7, 2024
|
|
Torch using two GPUs with NV link
|
|
8
|
407
|
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
|
2003
|
October 29, 2024
|
|
Regarding Scaled Dot Product Attention
|
|
4
|
173
|
October 25, 2024
|
|
Memory Leak with a simple code
|
|
3
|
58
|
October 22, 2024
|
|
Build Auto Tagging System
|
|
7
|
231
|
October 22, 2024
|
|
Why transformer model is predicting only one random word repetatively in every iteration
|
|
1
|
61
|
October 19, 2024
|
|
LogSoftmax vs Softmax
|
|
26
|
55222
|
October 15, 2024
|
|
Why transformer model is behaving like this?
|
|
1
|
38
|
October 14, 2024
|
|
Variable length time series data
|
|
1
|
112
|
October 12, 2024
|
|
I want to eliminate the accumulation of memory usage during the learning loop
|
|
0
|
21
|
October 7, 2024
|
|
The forward function of a multi-layer Elman RNN from tutorial has two errors
|
|
0
|
12
|
October 1, 2024
|