maxtext
maxtext copied to clipboard
google
A simple, performant and scalable Jax LLM!
Hi, It would be nice to support beam search. There is [the reference flax implementation in wmt example](https://github.com/google/flax/blob/main/examples/wmt/decode.py) and [the equivalent one from `transformers`](https://github.com/huggingface/transformers/blob/main/src/transformers/generation/flax_utils.py). I am guessing that we could:...
Are there any scripts available for converting trained Gemma/Llama/Mistral MaxText checkpoints to HuggingFace?
Do you have plans to support encoder-decoder models like T5? It will be great to have T5 with flash attention 😃
Fix typos found by running [`codespell`](https://github.com/codespell-project/codespell) on the repository.
Mainly wanted to start with thanking you for making MaxText available. I have been using it for a few days, and the first impression is fantastic. Getting started was really...
For AOT+Hybridsim integration, we need to pull Hybridsim docker image, so we need to install docker for maxtext base image (https://screenshot.googleplex.com/BD3SMwL57tP5cQY). Tested AOT+Hybridsim e2e on a GKE node: https://screenshot.googleplex.com/5LQwBNBp4p6iyLq This...
