Skip to content
Other

MazeNet

нейросетевой решатель лабиринтов

1 min readupdated

MazeNet от laskar-ks — компактная модель (~200 тыс. параметров, файл < 1 МБ), которая решает лабиринты в виде сетки. Модель читает всю карту и многократно применяет одни и те же свёрточные блоки, распространяя от выхода информацию о направлении пути.

Ключевые особенности

  • Формат карты: 1 — стена, 0 — дорога, 2 — старт, 3 — выход; размер произвольный.
  • Информация о направлении к выходу распространяется по карте итеративно, как круги по воде.
  • Результат — стрелки направления в каждой проходимой клетке; solver идёт от старта по стрелкам до выхода.
  • Есть CLI и HTTP API для VPS; вывод в JSON с путём, ходами и числом итераций.
  • Если модель ошибается, может включиться классический BFS fallback; отключается флагом --no-fallback.

Пример

pip install torch --index-url https://download.pytorch.org/whl/cpu
pip install numpy safetensors huggingface_hub
python solve_maze.py --repo USERNAME/maze-solver --file maze.json --show
ПодробнееБенчмарков в карточке нет.
Железо: CPU; модель ~200 тыс. параметров, файл < 1 МБ.
Ограничение: для больших карт нужно больше времени «размышления».
Выход: solved_by может быть model, model_with_corrections или bfs_fallback.
Discuss Telegram 0 26

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.0 GB · ready files0.5 GB
  • BF16weights 0.0 GB0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # laskar-ks/maze-solver
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download laskar-ks/maze-solver --local-dir ~/models/maze-solver
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to maze-solver
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of maze-solver (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

laskar-ks/maze-solver
Author
laskar-ks
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

260

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments