Add repository inspector

public-apps/repository-inspector.livemd

@@ -0,0 +1,203 @@
+<!-- livebook:{"app_settings":{"access_type":"public","auto_shutdown_ms":5000,"multi_session":true,"output_type":"rich","show_source":true,"slug":"repository-inspector"}} -->
+
+# Repository inspector
+
+```elixir
+Mix.install([
+  {:kino, "~> 0.10.0"},
+  {:bumblebee, "~> 0.4.1"}
+])
+```
+
+## Info
+
+```elixir
+Kino.Markdown.new("""
+Runs checks against the given HuggingFace repository to verify whether Bumblebee
+supports the given model and any supporting components.
+
+Not all supporting components are necessary for the given model. For example,
+most models use either a tokenizer or a featurizer, but not both. If any of the
+component does not exist it is probably fine, however pay attention to more
+specific error messages.
+""")
+```
+
+## Checks
+
+```elixir
+version = Application.spec(:bumblebee)[:vsn]
+
+Kino.Markdown.new("""
+`bumblebee: #{version}`
+""")
+```
+
+```elixir
+repo_input = Kino.Input.text("HuggingFace repo")
+```
+
+```elixir
+subdir_input = Kino.Input.text("Subdirectory (optional)")
+```
+
+```elixir
+repo = Kino.Input.read(repo_input)
+subdir = Kino.Input.read(subdir_input)
+
+if repo == "" do
+  Kino.interrupt!(:normal, "Enter repository.")
+end
+
+repo =
+  if subdir == "" do
+    {:hf, repo}
+  else
+    {:hf, repo, subdir: subdir}
+  end
+
+repo_snippet = repo |> Macro.escape() |> Macro.to_string()
+```
+
+```elixir
+safe_apply = fn fun ->
+  try do
+    fun.()
+  rescue
+    error -> {:error, Exception.message(error)}
+  end
+end
+```
+
+```elixir
+Kino.Markdown.new("### Model")
+```
+
+````elixir
+case safe_apply.(fn -> Bumblebee.load_spec(repo) end) do
+  {:ok, _spec} ->
+    Kino.Markdown.new("""
+    🚀 Model specification available. This means that **Bumblebee supports this model**.
+
+    ```elixir
+    {:ok, model_info} = Bumblebee.load_model(#{repo_snippet})
+    ```
+    """)
+
+  {:error, message} ->
+    Kino.Markdown.new("""
+    🤷‍♂️ Failed to load, reason: #{message}.
+    """)
+end
+````
+
+```elixir
+Kino.Markdown.new("### Tokenizer")
+```
+
+````elixir
+case safe_apply.(fn -> Bumblebee.load_tokenizer(repo) end) do
+  {:ok, _tokenizer} ->
+    Kino.Markdown.new("""
+    🚀 Tokenizer available.
+
+    ```elixir
+    {:ok, tokenizer} = Bumblebee.load_tokenizer(#{repo_snippet})
+    ```
+    """)
+
+  {:error, message} ->
+    Kino.Markdown.new("""
+    🤷‍♂️ Failed to load, reason: #{message}.
+    """)
+end
+````
+
+```elixir
+Kino.Markdown.new("### Featurizer")
+```
+
+````elixir
+case safe_apply.(fn -> Bumblebee.load_featurizer(repo) end) do
+  {:ok, _featurizer} ->
+    Kino.Markdown.new("""
+    🚀 Featurizer available.
+
+    ```elixir
+    {:ok, featurizer} = Bumblebee.load_featurizer(#{repo_snippet})
+    ```
+    """)
+
+  {:error, message} ->
+    Kino.Markdown.new("""
+    🤷‍♂️ Failed to load, reason: #{message}.
+    """)
+end
+````
+
+```elixir
+Kino.Markdown.new("""
+### Generation config
+
+*Note: this check may give a false positive. Whether you want to load
+a generation config, depends on the task you are performing.*
+""")
+```
+
+````elixir
+default_config = Bumblebee.configure(Bumblebee.Text.GenerationConfig)
+
+case safe_apply.(fn -> Bumblebee.load_generation_config(repo) end) do
+  {:ok, config} ->
+    # Generation attributes should be stored in generation_config.json,
+    # however old repos keep them as part of config.json. This means
+    # that generation config can always be loaded.
+    #
+    # We use a simple heuristic, if all attributes have their default
+    # value, it means there is effectively no generation config.
+    # However, a couple attributes, nameply :bos_token_id, :eos_token_id,
+    # :pad_token_id, may appear in config.json irrespectively of
+    # generation, which causes a false positive.
+
+    if config == default_config do
+      Kino.Markdown.new("""
+      🤷‍♂️ Failed to load, reason: no generation config found in the given repository.
+      """)
+    else
+      Kino.Markdown.new("""
+      🚀 Generation config available.
+
+      ```elixir
+      {:ok, generation_config} = Bumblebee.load_generation_config(#{repo_snippet})
+      ```
+      """)
+    end
+
+  {:error, message} ->
+    Kino.Markdown.new("""
+    🤷‍♂️ Failed to load, reason: #{message}.
+    """)
+end
+````
+
+```elixir
+Kino.Markdown.new("### Scheduler")
+```
+
+````elixir
+case safe_apply.(fn -> Bumblebee.load_scheduler(repo) end) do
+  {:ok, _featurizer} ->
+    Kino.Markdown.new("""
+    🚀 Scheduler available.
+
+    ```elixir
+    {:ok, scheduler} = Bumblebee.load_scheduler(#{repo_snippet})
+    ```
+    """)
+
+  {:error, message} ->
+    Kino.Markdown.new("""
+    🤷‍♂️ Failed to load, reason: #{message}.
+    """)
+end
+````