From 598e181c54213f0c9f76272232244f544458e683 Mon Sep 17 00:00:00 2001 From: khatwanimohit Date: Tue, 9 Apr 2024 18:21:50 +0000 Subject: [PATCH] Fix Gemma links --- README.md | 2 +- end_to_end/gemma/Run_Gemma.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 1b19f93aa..5fc1a9700 100644 --- a/README.md +++ b/README.md @@ -45,7 +45,7 @@ For your first time running MaxText, we provide specific [instructions](getting_ MaxText supports training and inference of various open models. Follow user guides in the [getting started](getting_started) folder to know more. Some extra helpful guides: -* [Gemma](https://ai.google.dev/gemma): a family of open-weights Large Language Model (LLM) by [Google DeepMind](https://deepmind.google/), based on Gemini research and technology. You can run decode and finetuning using [these instructions](getting_started/Run_Gemma.md). +* [Gemma](https://ai.google.dev/gemma): a family of open-weights Large Language Model (LLM) by [Google DeepMind](https://deepmind.google/), based on Gemini research and technology. You can run decode and finetuning using [these instructions](end_to_end/gemma/Run_Gemma.md). * [Llama2](https://llama.meta.com/llama2/): a family of open-weights Large Language Model (LLM) by Meta. You can run decode and finetuning using [these instructions](getting_started/Run_Llama2.md). In addition to the getting started guides, there are always other MaxText capabilities that are being constantly being added! The full suite of end-to-end tests is in [end_to_end](end_to_end). We run them with a nightly cadence. They can be a good source for understanding MaxText Alternatively you can see the continuous [unit tests](.github/workflows/UnitTests.yml) which are run almost continuously. diff --git a/end_to_end/gemma/Run_Gemma.md b/end_to_end/gemma/Run_Gemma.md index b099cf883..627cd1e7b 100644 --- a/end_to_end/gemma/Run_Gemma.md +++ b/end_to_end/gemma/Run_Gemma.md @@ -19,7 +19,7 @@ Following the instructions at [kaggle](https://www.kaggle.com/models/google/gemma/frameworks/maxText) will let you download Gemma model weights. You will have to consent to license for Gemma using your kaggle account's [API credentials](https://github.com/Kaggle/kaggle-api?tab=readme-ov-file#api-credentials). -After downloading the weights run [test_convert_chkpt.sh](https://github.com/google/maxtext/blob/main/end_to_end/gemma/test_convert_chkpt.sh), which converts the checkpoint to be compatible with MaxText and uploads them to a GCS bucket. You can run decode and finetuning using instructions mentioned in the test scripts at [end_to_end/gemma](https://github.com/google/maxtext/blob/main/end_to_end/gemma). +After downloading the weights run [convert_gemma_chkpt.py](../../MaxText/convert_gemma_chkpt.py), which converts the checkpoint to be compatible with MaxText and uploads them to a GCS bucket. You can run decode and finetuning using instructions mentioned in the test scripts at [end_to_end/gemma](../../end_to_end/gemma). ## MaxText supports pretraining and finetuning with high performance