Sandesh Katakam

icon indicating a website link https://sandeshkatakam.github.io/

icon location Hyderabad, INDIA icon location Deep Learning, Reinforcement Learning, Generative Models, Machine Learning Systems (MLSys)

Results 6 comments of Sandesh Katakam

Support RLHF and other instruction fine-tuning options beyond supervised fine-tuning.

Hi, I'd love to contribute to adding RLHF and instruction fine-tuning support to Keras Hub. Could you clarify the scope? Are we focusing on specific model architectures and dataset standards?...

Support RLHF and other instruction fine-tuning options beyond supervised fine-tuning.

> Hi [@sandeshkatakam](https://github.com/sandeshkatakam) we have not scoped this out yet. It would be great if you can add a [keras io](https://github.com/keras-team/keras-io) guide or example and we can probably pull that...

[Question] Integrate something like jaxtyping for more specific type annotations and runtime type-checking

Hey, I was actually considering opening an issue to explore adding jaxtyping support as well. It sounds like we're aligned in our interests, and If you like, I’d love to...

[Question] Integrate something like jaxtyping for more specific type annotations and runtime type-checking

> @sandeshkatakam I'd be glad to collaborate. How should we do it best? > > One idea would be that, I open a feature branch on my fork. You'll need...

[Question] Integrate something like jaxtyping for more specific type annotations and runtime type-checking

> @sandeshkatakam I'd be glad to collaborate. How should we do it best? > > One idea would be that, I open a feature branch on my fork. You'll need...

[Question] Integrate something like jaxtyping for more specific type annotations and runtime type-checking

> @sandeshkatakam I'll open the PR at the latest on Thu. hey did you open the PR??