Correct way to save/load adapters and checkpoints in PEFT
|
|
3
|
191
|
March 22, 2024
|
LLaMA 7B GPU Memory Requirement
|
|
17
|
72582
|
March 22, 2024
|
Fine-tuning - tokenize before or when doing a forward pass over batches
|
|
2
|
834
|
March 22, 2024
|
CUDA out of memory error while predicting (evaluation)
|
|
1
|
410
|
March 22, 2024
|
Generate an answer from Questions or everyday conversations without context
|
|
0
|
36
|
March 22, 2024
|
Human pose estimation models
|
|
1
|
68
|
March 21, 2024
|
What is the index of the class token feature vector?
|
|
0
|
38
|
March 21, 2024
|
OCR model suggestion
|
|
0
|
48
|
March 21, 2024
|
PatchTSTForPrediction outputs
|
|
0
|
35
|
March 21, 2024
|
PatchTST issue adding independent variables to the model that help predict one target variable
|
|
0
|
40
|
March 21, 2024
|
Converting CLIPModel to VisionTextDualEncoderModel
|
|
1
|
40
|
March 21, 2024
|
ValueError: Could not interpret optimizer identifier
|
|
0
|
41
|
March 21, 2024
|
How to use peft+base merged models in offline mode?
|
|
3
|
98
|
March 21, 2024
|
Llama 2 repeats its prompt as output without answering the prompt
|
|
2
|
78
|
March 20, 2024
|
Disparity between output from `forward` and `generate` for greedy search (using Whisper)
|
|
2
|
637
|
March 20, 2024
|
Using trasnsformer to get image features
|
|
3
|
2052
|
March 20, 2024
|
Potential error in the documentation relating to Deberta-v2 position_biased_input
|
|
2
|
54
|
March 20, 2024
|
How can you switch between adapters in the inference model?
|
|
0
|
39
|
March 20, 2024
|
How to train SETFIT on a dataset like NLI
|
|
0
|
39
|
March 20, 2024
|
BERT for text classification
|
|
0
|
52
|
March 20, 2024
|
Which transformers version will support this?
|
|
0
|
31
|
March 20, 2024
|
How to load a model fine-tuned with QLoRA
|
|
1
|
97
|
March 19, 2024
|
Tokenizer is not defined
|
|
5
|
5331
|
March 19, 2024
|
[URGENT] Issues with Training RoBERTa Model for Text Prediction with Fill Mask Task
|
|
6
|
100
|
March 19, 2024
|
Problem "Target size must be the same as input size "
|
|
0
|
45
|
March 19, 2024
|
Seq2SeqTrainer produces error during validation when using T5
|
|
0
|
44
|
March 18, 2024
|
Unexpected input type after export
|
|
0
|
45
|
March 18, 2024
|
Mistral trouble when fine-tuning : Don't set pad_token_id = eos_token_id
|
|
0
|
80
|
March 18, 2024
|
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0!
|
|
22
|
61470
|
March 18, 2024
|
ValueError: Expected input batch_size to match target batch_size in Token Classification
|
|
8
|
145
|
March 17, 2024
|