DistilBERT question answering on Emily

Mix.install(
  [
    {:emily, "~> 0.3"},
    {:bumblebee, "~> 0.6"},
    {:tokenizers, "~> 0.5"},
    {:nx, "~> 0.10"},
    {:kino, "~> 0.14"}
  ],
  config: [
    nx: [default_backend: Emily.Backend]
  ]
)

Overview

This notebook runs a DistilBERT question-answering pipeline on Emily.Backend. The backend is installed as the Nx global default by the Mix.install/2 config above, so every subsequent Nx call dispatches to MLX without further setup.

The featurizer, tokenizer, and model all come from Bumblebee. The only integration with Emily is the Mix.install config line and, optionally, the Emily.Compiler attachment further down.

Loading the model

{:ok, model_info} =
  Bumblebee.load_model({:hf, "distilbert-base-uncased-distilled-squad"})

{:ok, tokenizer} =
  Bumblebee.load_tokenizer({:hf, "distilbert-base-uncased-distilled-squad"})

The checkpoint is ~250 MB on first fetch; subsequent runs use the Bumblebee cache at ~/.cache/bumblebee.

Building a serving

serving =
  Bumblebee.Text.question_answering(model_info, tokenizer,
    defn_options: [compiler: Emily.Compiler]
  )

Emily.Compiler forwards the walk to Nx.Defn.Evaluator with two adjustments: it pins the result backend to Emily.Backend, and it caps partition concurrency at 1 (use Emily.Stream for per-process concurrency — see the other notebook).

Running a query

context =
  "Elixir is a dynamic, functional programming language that runs on the Erlang VM. " <>
    "It was created by José Valim in 2011."

question = "Who created Elixir?"

Nx.Serving.run(serving, %{question: question, context: context})

The expected output is a map shaped like

%{
  results: [
    %{text: "José Valim", start: _, end: _, score: _}
  ]
}

Telemetry

Emily emits :telemetry events at the evaluation boundary. Attach a handler to sample timing for each forward pass:

:telemetry.attach(
  "distilbert-qa-eval",
  [:emily, :eval, :stop],
  fn _event, %{duration: duration}, _meta, _config ->
    ms = System.convert_time_unit(duration, :native, :millisecond)
    IO.puts("eval #{ms} ms")
  end,
  nil
)

Nx.Serving.run(serving, %{question: question, context: context})

See Emily.Telemetry for the full event catalogue, including the [:emily, :fallback, *] span that fires whenever an op routes through Nx.BinaryBackend.