|
How can I replace modules in a pretrained model?
|
|
4
|
4020
|
January 24, 2025
|
|
RuntimeError: result type Float can't be cast to the desired output type Long
|
|
1
|
68
|
January 24, 2025
|
|
Difference in model prediction before saving and after loafing
|
|
4
|
253
|
January 23, 2025
|
|
Upgrading to transformers 4.9.1?
|
|
3
|
742
|
January 23, 2025
|
|
AI-Generated Text Detection: Is There a Feature in transformers?
|
|
2
|
60
|
January 22, 2025
|
|
Outputs change if re-using KVCache (past_key_values) for model.forward and generation
|
|
5
|
92
|
January 22, 2025
|
|
The state_dict export by peft.get_peft_model_state_dict doesn't contain adapter name
|
|
7
|
58
|
January 22, 2025
|
|
torch.distributed.elastic.multiprocessing.errors.ChildFailedError
|
|
19
|
38819
|
January 22, 2025
|
|
Seq2SeqTrainer multiple GPUs
|
|
2
|
47
|
January 22, 2025
|
|
Accessing a model with model.generate via remote only
|
|
1
|
15
|
January 22, 2025
|
|
GPU utilization almost always 0 during training
|
|
2
|
153
|
January 22, 2025
|
|
Finetuning llama for classification
|
|
2
|
920
|
January 21, 2025
|
|
Adding Audio-MAE to Transformers
|
|
1
|
26
|
January 21, 2025
|
|
Dataset for multilabel classification
|
|
1
|
91
|
January 20, 2025
|
|
Having the 'The model did not return a loss from the inputs, only the following keys: logits.' error only when predict_with_generate = True
|
|
2
|
52
|
January 20, 2025
|
|
Fine-Tuning a Text2Text Model using different tokenizer
|
|
5
|
54
|
January 20, 2025
|
|
[Announcement] Generation: Get probabilities for generated output
|
|
63
|
39173
|
January 20, 2025
|
|
Perhaps your features (`output` in this case) have excessive nesting (inputs type `list` where type `int` is expected)
|
|
19
|
294
|
January 20, 2025
|
|
Pip install optimum[exporters-tf]
|
|
3
|
50
|
January 18, 2025
|
|
Pretrained Model for Fine-Tuning has 100% Trainable Parameters
|
|
2
|
69
|
January 17, 2025
|
|
DONUT: Reading order for pseudo-OCR pre-training task
|
|
0
|
22
|
January 16, 2025
|
|
Unable to load a newly trained tokenizer from local files
|
|
4
|
55
|
January 16, 2025
|
|
Issues Fine Tuning RT-DETR
|
|
1
|
114
|
January 15, 2025
|
|
Change the classifcation threshold
|
|
2
|
96
|
January 15, 2025
|
|
Python code for Gemma models
|
|
1
|
41
|
January 15, 2025
|
|
RuntimeError: Failed to import transformers.models.roberta.modeling_tf_roberta because of the following error (look up to see its traceback): No module named 'keras.engine'
|
|
6
|
5771
|
January 14, 2025
|
|
Initializing a big model on GPU with random weights
|
|
2
|
42
|
January 14, 2025
|
|
What is `self.loss_function` in `forward()` of newly released LLM?
|
|
0
|
22
|
January 14, 2025
|
|
ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length
|
|
4
|
34751
|
January 13, 2025
|
|
Qwen Not work anymore
|
|
1
|
124
|
January 13, 2025
|