madewithlaya

Catalog / Tools & apps

0056GitHub

laya_ex: native Nx/Bumblebee runtime for Laya in Elixir

Elixir library that downloads the official checkpoint on first load and answers typed choice and noul questions; pick EMLX on Apple Silicon or EXLA for CPU/NVIDIA.

Open source ↗ github.comcostfree, localtime-
ChristianAlexander/laya_exREADME ↗
# Laya

Native Nx/Bumblebee runtime for [Laya](https://laya.convaiinnovations.com/) by
Convai Innovations. It downloads the
[official model checkpoint](https://huggingface.co/convaiinnovations/laya) on
first load.

```elixir
{:ok, model} = Laya.load()

Laya.predict(model, "Please refund the duplicate invoice.", %{
  "department" => %{
    type: :choice,
    instructions: "Which team should handle this request?",
    criteria: [
      {"billing", "invoices, payments, and refunds"},
      {"technical", "bugs and outages"},
      {"other", "everything else"}
    ]
  },
  "refund_requested" => %{
    type: :noul,
    instructions: "Does the customer explicitly request a refund?"
  }
})
```

`choice.criteria` is an ordered list of `{label, description}` tuples.

```sh
mix run bench/laya_bench.exs
```

The English checkpoint downloads on first load.

The package does not select an Nx backend. Configure one in the host app, for
example `EMLX.Backend` on Apple Silicon or `EXLA.Backend` on CPU/NVIDIA.

Also filed under Tools & apps

  1. 0005

    laya-mlx plays Snake at 60 decisions per second

    介绍比Jev快50倍,在你设备上跑的laya-mlx! 只在你的设备上占用最高1G内存 Laya是一个开源的类似于Jev的,基于文本输出概率的分类系统 我将其移植到MLX,并且做了一些性能优化! 视频中就是这个模型在我的本地M3Max上玩贪吃蛇 这个模型能够以每秒决策60次的速度玩贪吃蛇! https://t.co/31KGUiNunb

    @mizorewww · Tools & apps · free, local · 60 decisions/s

  2. 0112

    Laya on Axera AX650 and AX8850 edge NPUs, under 70 ms

    AXERA-TECH's conversion of all three Laya checkpoints for its edge AI chips, reported at latency under 70 ms per decision on AX650/AX8850.

    AXERA-TECH · Tools & apps · free, on-device · < 70 ms on AX650 / AX8850

  3. 0099

    laya-mcp (PerryLink): a warm sidecar that fixes Laya's silent truncation and constant noul

    MCP server plus HTTP sidecar: token-budget preflight that reports what would be cut, a persisted calibration store, structured errors, and a noul fix (P(true) 0.5 → 1.0).

    @PerryLink · Tools & apps · free, local

  4. 0097

    Gomoku against Laya-MLX: you play black, the model picks white's move from six candidates

    Local 15x15 Gomoku on Apple Silicon. Rules in Python, board in the browser, every AI move one real Laya choice over up to six candidates, probabilities shown. No Gomoku training.

    smile-magic · Tools & apps · free, local