chore(deps-dev): bump @huggingface/transformers from 3.8.1 to 4.0.1 (#831)

* chore(deps-dev): bump @huggingface/transformers from 3.8.1 to 4.0.1

Bumps [@huggingface/transformers](https://github.com/huggingface/transformers.js) from 3.8.1 to 4.0.1.
- [Release notes](https://github.com/huggingface/transformers.js/releases)
- [Commits](https://github.com/huggingface/transformers.js/commits)

---
updated-dependencies:
- dependency-name: "@huggingface/transformers"
  dependency-version: 4.0.1
  dependency-type: direct:development
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

* fix: replace deprecated quantized option with dtype for transformers v4

The quantized pipeline option was removed in @huggingface/transformers v4.
Without this fix, the minilm model loads in fp32 precision (~92MB) instead
of q8 (~23MB), quadrupling memory usage.

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: carlos-alm <127798846+carlos-alm@users.noreply.github.com>

Author: dependabot[bot]

package-lock.json

@@ -122,7 +122,7 @@
     "web-tree-sitter": "^0.26.5"
   },
   "peerDependencies": {
-    "@huggingface/transformers": "^3.8.1"
+    "@huggingface/transformers": "^4.0.1"
   },
   "peerDependenciesMeta": {
     "@huggingface/transformers": {
@@ -143,7 +143,7 @@
     "@commitlint/cli": "^20.4",
     "@commitlint/config-conventional": "^20.0",
     "@eagleoutice/tree-sitter-r": "^1.1.2",
-    "@huggingface/transformers": "^3.8.1",
+    "@huggingface/transformers": "^4.0.1",
     "@tree-sitter-grammars/tree-sitter-hcl": "^1.2.0",
     "@tree-sitter-grammars/tree-sitter-lua": "^0.4.1",
     "@tree-sitter-grammars/tree-sitter-zig": "^1.1.2",

package.json

@@ -194,7 +194,7 @@ async function loadModel(modelKey?: string): Promise<{ extractor: unknown; confi
   pipeline = transformers.pipeline;
 
   info(`Loading embedding model: ${config.name} (${config.dim}d)...`);
-  const pipelineOpts = config.quantized ? { quantized: true } : {};
+  const pipelineOpts = config.quantized ? { dtype: 'q8' } : {};
   try {
     extractor =
       await // biome-ignore lint/complexity/noBannedTypes: dynamically loaded transformers pipeline is untyped