And we added first-class support for post-training Beam yourself.

Get started with Modal Dojo now: https://t.co/Pd4NOcRWlG

Modal Dojo

Source: https://dojo.modal.dev/ Modal Dojo is an open-source library to get started with production-grade LLM training onModal.

To get started, you can go through theQuickstartsection below, or paste the prompt below into your favorite agent:

Install the `modal-dojo` library. Then, install the skill bundle into the local project with `modal-dojo skills install`. Finally, tell the user that they can ask you to do something like: "Walk through tutorials/rl_basics.py and train Qwen3.5-4B to write 5-7-5 haikus from statworx/haiku."

Requirements:

• Python 3.12

Install the package directly:

uv pip install modal-dojo

Or add it to your project’s dependencies:

Set upModaland thedashboard:

Watch the Modal Dojo dashboard substep view.Watch the Modal Dojo dashboard rollout view.

And empower your agents with the Modal Dojo’s skill bundle:

modal-dojo skills install

Then, it’s as easy as:

import refrom modal_dojo import (    HuggingFaceDataset,    Qwen3_5_4B,    Qwen3_5_4B_Recipe,    TrainConfig,)model = Qwen3_5_4B()async def gsm8k_rm(args, sample, **kwargs) -> float:    text = model.parse_response(sample.response or "").content    boxed = re.findall(r"\\boxed\{([^}]+)\}", text)    pred = boxed[-1] if boxed else (re.findall(r"-?[\d,]+(?:\.\d+)?", text) or [""])[-1]    try:        return float(float(pred.replace(",", "")) == float(sample.label))    except ValueError:        return 0.0config = TrainConfig(    model=model,    dataset=HuggingFaceDataset(        hf_repo="skrishna/gsm8k_only_answer",        hf_split="train[:120]",        input_column="text",        output_column="label",        input_format="text",    ),    recipe=Qwen3_5_4B_Recipe(        custom_rm_function=gsm8k_rm,    ),)if __name__ == "__main__":    run = config.launch()    print(run.training_run_id)

For a step-by-step walkthrough, see theGetting started tutorial.

Modal (@modal): Reflection Beam is now available on Modal.

Beam is a 501B-parameter open-weight MoE (23B active) from @reflection_ai built for coding, agentic workflows, and reasoning. It supports a 1M token context window, with token efficiency a core focus.

In early access, the Oura Health