|
Flex Attention Extremely Slow
|
|
1
|
604
|
September 20, 2024
|
|
How tokens per second calculated for LLM training
|
|
0
|
76
|
September 18, 2024
|
|
Drop row from tensor in cuda
|
|
3
|
316
|
September 14, 2024
|
|
Unhashable list while training sbert
|
|
0
|
151
|
September 14, 2024
|
|
RuntimeError: CUDA error: device-side assert triggered, LayoutLM Fine-Tuning
|
|
10
|
1163
|
September 10, 2024
|
|
Model predicted almost correct sentences at the time of training but is only predicting <START> token at the time of test
|
|
0
|
59
|
September 10, 2024
|
|
Self Self-attention implementation results are 'a bit' suprising
|
|
0
|
154
|
September 10, 2024
|
|
Extracting embeddings from log probabilities
|
|
0
|
157
|
September 9, 2024
|
|
Can transformer automatically learn the length of sequences?
|
|
0
|
94
|
September 9, 2024
|
|
Finen tuning Llama with using pytorch in colab
|
|
1
|
248
|
August 29, 2024
|
|
Output.loss is None when training model
|
|
0
|
151
|
August 26, 2024
|
|
HELP with multilabel classification and BCEWithLogitsLoss
|
|
1
|
186
|
August 14, 2024
|
|
Torchtext not supported
|
|
3
|
1719
|
August 13, 2024
|
|
NLP indexing question
|
|
3
|
295
|
August 13, 2024
|
|
Next step after NLP specialization
|
|
1
|
198
|
August 12, 2024
|
|
Integrated gradients with captum and handmade transformer model
|
|
8
|
1939
|
August 9, 2024
|
|
Custom Model with 2 GPT2 models from huggingface
|
|
0
|
181
|
August 7, 2024
|
|
SDPA backend routes requirement
|
|
0
|
303
|
August 6, 2024
|
|
I'm trying to build up a rag_chain, but encountering this error——TypeError: embedding(): argument 'indices' (position 2) must be Tensor, not ChatPromptValue
|
|
1
|
399
|
August 5, 2024
|
|
Sizes of tensors must match except in dimension 1
|
|
6
|
5015
|
August 3, 2024
|
|
Multi-task learning: Bottleneck, multi-GPU
|
|
0
|
229
|
July 31, 2024
|
|
Different value between BertSDPA scratch and pretrained sequence classification
|
|
0
|
193
|
July 30, 2024
|
|
How do I apply Batch Normalization on a sequential data?
|
|
5
|
2978
|
July 28, 2024
|
|
OpenNMT beam.py beam search class for seq2seq language models
|
|
0
|
221
|
July 25, 2024
|
|
Which is better TorchServe Batching or ClientSide Batching for text classification
|
|
0
|
76
|
July 24, 2024
|
|
Discrepancy Between key_padding_mask and attn_mask in MultiheadAttention Layer
|
|
9
|
2722
|
July 23, 2024
|
|
Have a question on `W_ii @ x_t` in lstm
|
|
0
|
48
|
July 20, 2024
|
|
nn.TransformerEncoder for classification
|
|
9
|
9064
|
July 20, 2024
|
|
How to reduce TPU RAM usage when calculating large tensors
|
|
1
|
281
|
July 19, 2024
|
|
Can someone help me understand how to use a .pt file?
|
|
2
|
288
|
July 16, 2024
|