From 988b08561d6447299022353fe77cd5ad24d3285d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=99=93=E9=9B=B7?= Date: Tue, 22 Jul 2025 15:09:53 +0800 Subject: [PATCH] . --- docs/tutorial/quickstart_arealite.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/docs/tutorial/quickstart_arealite.md b/docs/tutorial/quickstart_arealite.md index e2e8e57..ecde238 100644 --- a/docs/tutorial/quickstart_arealite.md +++ b/docs/tutorial/quickstart_arealite.md @@ -10,7 +10,7 @@ To run the experiment, you will need: - Training script: [examples/arealite/gsm8k_grpo.py](../../examples/arealite/gsm8k_grpo.py) - Config YAML: [examples/arealite/configs/gsm8k_grpo.yaml](../../examples/arealite/configs/gsm8k_grpo.yaml) -Our training scripts will automatically download the dataset (openai/gsm8k) and model (Qwen/Qwen3-1.7B). +Our training scripts will automatically download the dataset (openai/gsm8k) and model (Qwen/Qwen2-1.5B-Instruct). To run the example with default configuration, execute from the repository directory: ``` python3 -m arealite.launcher.local examples/arealite/gsm8k_grpo.py --config examples/arealite/configs/gsm8k_grpo.yaml experiment_name= trial_name= @@ -91,4 +91,8 @@ Additional references: ## Next Steps -Check [Getting Started with AReaLite](../arealite/gsm8k_grpo.md) for a complete code walkthrough on the GRPO GSM8K Example. \ No newline at end of file +1. Check [Getting Started with AReaLite](../arealite/gsm8k_grpo.md) for a complete code walkthrough on the GRPO GSM8K Example. +2. Customization guides: +- [Custom dataset](../customization/dataset.md) +- [Custom agentic/RVLR rollout workflows](../customization/agent.md) +- [Custom algorithms](../customization/algorithm.md) \ No newline at end of file