keras-nlp icon indicating copy to clipboard operation
keras-nlp copied to clipboard

Modular Natural Language Processing workflows with Keras

Results 360 keras-nlp issues
Sort by recently updated
recently updated
newest added

Hi there, I recently came across this blog post: https://www.answer.ai/posts/2024-04-26-fsdp-qdora-llama3.html > [QDoRA] is just as memory efficient and scalable as FSDP/QLoRA, and critically is also as accurate for continued pre-training...

type:feature

This task is part of the KerasHub project ( Consolidating all of KerasCV and KerasNLP models in to one place) Models from KerasCV will be added to KerasNLP in KerasNLP...

stat:contributions welcome
keras-hub
team-created

This task is part of the KerasHub project ( Consolidating all of KerasCV and KerasNLP models in to one place) Models from KerasCV will be added to KerasNLP in KerasNLP...

stat:contributions welcome
keras-hub
team-created

Hi, as it's reported in several issues (#1271, #1413), t5 still lacks some of workflows. Particularly, I'm trying to optimize T5 conditional generation. I started by porting code from `BartSeq2SeqLM`,...

type:feature

https://github.com/keras-team/keras-nlp/blob/bb423c87a0ce35bb6e8f2f07ca3c48e0fead50b0/keras_nlp/src/models/pali_gemma/pali_gemma_causal_lm.py#L53-L110 There are two issues: 1. There is an issue with the [documentation rendering](https://keras.io/api/keras_nlp/models/pali_gemma/pali_gemma_causal_lm/#paligemmacausallm-class) due to brackets (as far as I understand it). 2. The `generate` method does not take...

type:docs
Gemma

## Description of the Change It is an end-to-end image classification model which had to be implemented on KerasHub as a building block towards supporting D-FINE. A number of D-FINE's...

from https://github.com/keras-team/keras-hub/issues/2177 Achieved a smaller error with hf. ```python import os os.environ["KERAS_BACKEND"] = "torch" os.environ["HF_ENDPOINT"] = "https://hf-mirror.com" from keras import ops from transformers.models.esm.modeling_esm import EsmAttention as hf_EsmSelfAttention from transformers import...

Now CasualLM.generate does not have a progress bar, which is very inconvenient to use. Can add a progress bar to it? The code just like ```python if strip_prompt: outputs =...

**Is your feature request related to a problem? Please describe.** **Describe the solution you'd like** **Describe alternatives you've considered** **Additional context**

type:feature
stat:contributions welcome
team-created