Skip to content
Other

Laya Minecraft

System-1 мозг для агента в Minecraft

1 min readupdated

Это RLCD-файнтюн английского чекпоинта Laya на базе ModernBERT-large (0,42B). Модель работает как System-1 brain Minecraft-агента: код отбирает допустимые действия, а она за один forward pass выбирает intent и отвечает на бинарный вопрос in_danger. Текст и аргументы инструментов не генерируются.

Ключевые особенности

  • Обучена на 2564 подтверждённых тиках живого агента (runs 187–205).
  • Две choice-задачи за тик: intent среди уже валидных опций и in_danger.
  • Неавторегрессионный forward pass: нечего парсить и негде галлюцинировать.
  • Фильтрация действий по предусловиям и tech tree остаётся в коде агента.
  • Калибровка отдельной температурой для типа вопроса и числа вариантов; веса — 842 MB.

Пример

export LAYA_EXTRA_MODELS='{"english": "thtesche/laya-minecraft-english"}'
.venv/bin/python -m mlaya.cli run -n 10
ПодробнееТочность 0,9325 против 0,9301 до файнтюна; ECE 0,0435 (было 0,0625); Brier 0,1273 (было 0,1402).
Обучение: RLCD, 4 эпохи, 2564 тика; калибровка на 284 held-out items.
Ограничения: только Minecraft survival-действия и две задачи — intent и in_danger; score/noul не обучены.
В eval 4 из 415 примеров пересекаются с train/calibration — это не строго held-out.
Discuss Telegram 0 29

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

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.

    # thtesche/laya-minecraft-english
    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 thtesche/laya-minecraft-english --local-dir ~/models/laya-minecraft-english
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to laya-minecraft-english
  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 laya-minecraft-english (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

thtesche/laya-minecraft-english
Author
thtesche
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

290

Ask AI about this model

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

Comments