-
I decided to try the nnx vs. equinox for performance and am seeing significant differences (3'ish times slower for nnx). Could be that I wrote a poor MLP implementation or made a collosal profiling m…
-
Hi,
I am trying to fine tune BERT using TPU on my own dataset. To fine tune BERT I wrote the following code:
`def create_model(is_training, input_ids, input_mask, segment_ids, labels,
…
-
I have been using pre-trained cross-encoder/ms-marco-MiniLM-L-6-v2 on a dataset similar to MS-MARCO for re-ranking paragraphs based on a query/question. The top-3 accuracy results have been pretty goo…
-
-
## Description
I encountered an error when trying to use a trained model for prediction. The model was initially trained using a GPU, but when attempting to run predictions using the same model on …
-
**Are you willing to contribute?**: Yes
**Describe the problem**:
Classification head implementations in keras-cv and keras.applications are different.
From `keras.applications`:
https://gith…
-
Would it make sense to utilise PoET for binding affinity prediction (ic50 score) of short peptide sequences (8-16 amino acids)? If yes, do you have any suggestions/comments on how to do it? Is it poss…
-
Vision LLMs like [Llava](https://huggingface.co/docs/transformers/en/model_doc/llava) or [Idefics](https://huggingface.co/docs/transformers/v4.39.3/en/model_doc/idefics#transformers.IdeficsImageProces…
-
Hi!
I tried to use llama2-7b 4bit model, got this error
`RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn`
Code:
```
from unsloth import FastLanguageMod…
-
I'm working on a multi-class classification problem using XGBoost, and when I do a summary_plot, the output is expressed as log odds instead of probabilities. I saw that in the force_plot method there…