keras-nlp

keras-nlp copied to clipboard

Add Electra Weights to Kaggle Models

4

Is there any certain guide to upload weights of pretrained models to kaggle. As per the `CONTRIBUTING_MODELS.md` I have uploaded my weights on GCP as mentioned in #1384.

pranavvp16

Hello folks, I'm new to *Keras_nlp*. From what I've seen till now is that - all the models that are provided by the keras_nlp community are only those that have...

abhaskumarsinha

i installed keras-nlp in pycharm IDE , when in run

6

said-ml

How to add a serialized model and weights of a keras model to keras-nlp?

4

Hello, I'm having some problems with the codebase of the keras_nlp, in case anyone understands the codebase and how model interact within, feel free to say. - Suppose, I do...

abhaskumarsinha

**Describe the bug** Recently [unsloth.ai](https://unsloth.ai/blog/gemma-bugs) has pointed out some discrepancies in **Gemma** model implementations. I think it would be nice to have them verified and addressed. Specially, they mentioned **Keras...

awsaf49

Gemma Model Storing and Loading after Fine tuning

5

Hi there, I encountered a strange bug after trying to load the gemma-2b model using kerasnlp. My finetuning code is the following: ` def fine_tune(self, X, y): data = generate_training_prompts(X,...

kreouzisv

Add CLIP tokenizer to Keras NLP

2

divyashreepathihalli

Add `oov_token` Argument to `BytePairTokenizer`

1

The `` token is not really used by the `BytePairTokenizer`, instead oov tokens will be mapped to -1, That will cause index error for embedding layer. This will only occur...

abuelnasr0

Update ByteTokenizer to remove TensorFlow dependency

1

**Is your feature request related to a problem? Please describe.** When testing Keras 3 in the MLX branch, I got a TensorFlow import error. I explicitly set the environment variable...

stereoplegic

Support tokenization of special tokens for sentencepiece tokenizer

2

This PR enables tokenization of special tokens for `SentencePieceTokenizer` as was suggested in keras-team/keras-nlp#1395 and it's a follow up of this PR keras-team/keras-nlp#1397 .

abuelnasr0