DEDUPED Hot AI repos, turned into use cases Get 5 a day

What you can do with Mini Verl

miniVERL is an independent Apache-2.0 Python project that runs verl-style PPO, GRPO and on-policy distillation training on one NVIDIA consumer GPU.

Trended earlier

DaoyuanLi2816/mini-verl on GitHub

Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk.

What do you want to do?

4 use cases

  • Run a first PPO experiment on one GPU

    Install miniVERL, sample prompts and train a Qwen3-0.6B PPO run with a length reward.

    View prompt
    Work in the miniverl repo (DaoyuanLi2816/mini-verl) on this machine. Install it, sample 8 prompts into data/rl-prompts.parquet, run the hydra-ppo example with run ID <run-id>, and report the path to rewards.jsonl. Verify that the dry run passes before the full run starts.

  • Run an existing verl config on one GPU

    Point miniVERL at a verl config tree, switch to GRPO and check the run with a dry run.

    View prompt
    Use the miniverl repo (DaoyuanLi2816/mini-verl) to dry-run a verl config at <verl-config-path> with the ppo_trainer config name and GRPO overrides. Report whether the dry run succeeds and list any overrides that failed. Verify that no training starts during the dry run.

  • Distill a teacher model into a smaller student

    Train a student on its own rollouts using feedback from a teacher model with on-policy distillation.

    View prompt
    Using the miniverl repo (DaoyuanLi2816/mini-verl), follow docs/opd-quickstart.md to set up on-policy distillation with teacher <teacher-model> and student <student-model> on one GPU. Report the path to the exported adapter and the final teacher loss. Verify that the peak reserved VRAM stays within the GPU memory you have.

  • Resume an interrupted run and export its outputs

    Pick up a stopped training run from its checkpoint and export the adapter and configs for hand-off.

    View prompt
    In the miniverl repo (DaoyuanLi2816/mini-verl), resume the run with ID <run-id> from its latest checkpoint and export its adapter and configs to <export-dir>. Report the export paths and the remaining setup listed in the hand-off report. Verify that the resumed run continues from the saved step.

How to use Mini Verl

  1. Check you have what it needs: A single NVIDIA GPU with a CUDA-enabled PyTorch build installed from the PyTorch installer; Python with pip available; Enough GPU memory for the chosen model (see the single-GPU guide and hardware planning docs).
  2. Open DaoyuanLi2816/mini-verl on GitHub and read the README and license.
  3. Install the matching CUDA-enabled PyTorch build from the PyTorch installer, then run python -m pip install "miniverl[train,hydra]".
  4. Create a small prompt set with miniverl data sample --reward-profile target-length --rows 8 --out data/rl-prompts.parquet.
  5. Check the configuration without training using miniverl run --example hydra-ppo --bind reward.provider=target_length --dry-run.
  6. Start the run with miniverl run --example hydra-ppo --bind reward.provider=target_length --run-id local-ppo.

These steps come from our top use case, Run a first PPO experiment on one GPU, which also has a copy-paste agent prompt.

Mini Verl alternatives · Best AI repos for Research

About this repo

  • Who it is forML engineers and researchers with one NVIDIA GPU who want to run reinforcement learning or distillation experiments locally using verl-style configs.
  • Why it is hot
  • LanguagePython
  • Sourcegithub.com/DaoyuanLi2816/mini-verl · Back to Hot repos

Requirements

  • A single NVIDIA GPU with a CUDA-enabled PyTorch build installed from the PyTorch installer
  • Python with pip available
  • Enough GPU memory for the chosen model (see the single-GPU guide and hardware planning docs)
Maintain Mini Verl? Add the Featured on Deduped badge

Paste this into your README:

[![Featured on Deduped](https://dedupedai.com/badge/daoyuanli2816-mini-verl.svg)](https://dedupedai.com/use-cases/daoyuanli2816-mini-verl/?ref=badge)

More badge styles and HTML

Questions about Mini Verl

What is Mini Verl?

miniVERL is an independent Apache-2.0 Python project that runs verl-style PPO, GRPO and on-policy distillation training on one NVIDIA consumer GPU. It is an open-source project on GitHub: https://github.com/DaoyuanLi2816/mini-verl.

Who is Mini Verl for?

ML engineers and researchers with one NVIDIA GPU who want to run reinforcement learning or distillation experiments locally using verl-style configs.

What can I do with Mini Verl?

4 use cases so far, for example: Run a first PPO experiment on one GPU; Run an existing verl config on one GPU; Distill a teacher model into a smaller student. Each has steps and a copy-paste agent prompt.

What do I need to run Mini Verl?

A single NVIDIA GPU with a CUDA-enabled PyTorch build installed from the PyTorch installer; Python with pip available; Enough GPU memory for the chosen model (see the single-GPU guide and hardware planning docs).

What are alternatives to Mini Verl?

Other hot AI repos in Research: Scientific Agent Skills, Speaker Mem R1, DSH Council, Evo Bot, AI Engineering Course.

Is Mini Verl safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.