Rozhina Taghdimi

Glassboro, NJ Hello! I'm Rozhina, a Ph.D. student at RIT. My research focuses on large language models (LLMs).

Results 7 issues of


                                            Rozhina Taghdimi

fine tuning RoBERTa-base with LoRA (ValueError: Classification metrics can't handle a mix of binary and multilabel-indicator targets)

Hello, I'm trying to fine-tune RoBERTa-base with LoRA for a multi-classification task. My compute_metrics function is as follows: def multi_label_metrics(predictions, labels, threshold=0.5): # first, apply sigmoid on predictions which are...

Using Custom Dataset with Different Input Lengths for Model

2

comment

My input dimensions are [1500, 50, 6] and my label dimensions are [1500, 1]. Can I use this model? If so, could you please explain how to configure it correctly?

Using Custom Dataset with Different Input Lengths for Model

3

comment

My input dimensions are [1500, 50, 6] and my label dimensions are [1500, 1]. Can I use this model? If so, could you please explain how to configure it correctly?

Using Custom Dataset with Different Input Lengths for Model

1

comment

My input dimensions are [1500, 50, 6] and my label dimensions are [1500, 1]. Can I use this model? If so, could you please explain how to configure it correctly?

Error in AdditiveAttentionForSeq call function due to incompatible dimensions

Hello, I'm using the attention-GRU-piecewise-linear RUL Prediction.ipynb notebook. There is an error in the AdditiveAttentionForSeq class, specifically in the call function at the line concat = tf.concat((state_rep, encoder_outputs), axis =...

Using Custom Dataset with Different Input Lengths for Model

My input dimensions are [1500, 50, 6] and my label dimensions are [1500, 1]. Can I use this model? If so, could you please explain how to configure it correctly?

Using Custom Dataset with Different Input Lengths for Model

My input dimensions are [1500, 50, 6] and my label dimensions are [1500, 1]. Can I use this model? If so, could you please explain how to configure it correctly?