|
Finetuning DPR on Custom Dataset
|
|
4
|
2878
|
April 5, 2024
|
|
Problem with transformer optimizer assertion error
|
|
1
|
429
|
April 4, 2024
|
|
Always getting RuntimeError: CUDA out of memory with Trainer
|
|
10
|
6958
|
April 4, 2024
|
|
[Maybe Bug] When using EarlyStopping Callbacks with Seq2SeqTraininer, training didn't stop
|
|
3
|
1557
|
April 4, 2024
|
|
Problem with EarlyStoppingCallback
|
|
13
|
10904
|
April 4, 2024
|
|
FREQUENT LOSS SPIKING in CONTINUE TRAINING LLM
|
|
2
|
1073
|
April 4, 2024
|
|
What is the data file format of `run_ner.py`?
|
|
2
|
329
|
April 4, 2024
|
|
Custom loss weight for train a different weight for validation
|
|
0
|
195
|
April 4, 2024
|
|
Unable to load a model with added special token
|
|
1
|
582
|
April 3, 2024
|
|
[Request] Provide better examples for each model and task existing in the library [/Request]
|
|
0
|
117
|
April 3, 2024
|
|
Transformers crashes when using mlflow-skinny
|
|
1
|
116
|
April 3, 2024
|
|
How to compare the meaning of documents
|
|
2
|
1012
|
April 3, 2024
|
|
CUDA not working with asr pipeline
|
|
0
|
166
|
April 3, 2024
|
|
Name is not correct
|
|
0
|
107
|
April 3, 2024
|
|
How to train an EncoderDecoderModel with different pretrained encoder and decoder?
|
|
2
|
419
|
April 2, 2024
|
|
Get scores from Whisper using ASR pipeline
|
|
2
|
3866
|
April 2, 2024
|
|
TrOCR expects square images though lines are rectangle images
|
|
0
|
115
|
April 2, 2024
|
|
Task Guides - Image segmentation
|
|
0
|
136
|
April 2, 2024
|
|
Deployment issue in AWS Sagemaker and GCP
|
|
0
|
198
|
April 2, 2024
|
|
Unable to load a pretrained starcoder2 with SFT
|
|
0
|
138
|
April 2, 2024
|
|
Training issue with the Transformer CAPTCHA recognition model: Unable to converge
|
|
5
|
612
|
April 1, 2024
|
|
Model_max_length error in some models
|
|
0
|
204
|
April 1, 2024
|
|
About the return type of BaseImageProcessor preprocess method implementations
|
|
1
|
110
|
April 1, 2024
|
|
Which weights does QLoRA train by default?
|
|
1
|
209
|
April 1, 2024
|
|
Should 8bit quantization make inference faster on GPU?
|
|
1
|
676
|
April 1, 2024
|
|
T5 weird behavior between model.forward() and model.generate
|
|
0
|
112
|
March 31, 2024
|
|
Using GPT4 ORCA embeddings in OpenNMT-py
|
|
0
|
73
|
March 31, 2024
|
|
Variable length batch decoding
|
|
11
|
3967
|
March 31, 2024
|
|
Building Custom AutoModelForTask
|
|
0
|
95
|
March 31, 2024
|
|
Is it possible to access Trainer attributes in the Callback
|
|
0
|
185
|
March 31, 2024
|