chore: import upstream snapshot with attribution

examples/provider-transformers-local/README.md

@@ -0,0 +1,69 @@
+# provider-transformers-local (Fully Local LLM Evaluation)
+
+This example demonstrates a completely local LLM evaluation setup using Transformers.js - no API keys or external services required.
+
+## Prerequisites
+
+Install the optional Transformers.js dependency:
+
+```bash
+npm install @huggingface/transformers
+```
+
+## Usage
+
+```bash
+npx promptfoo@latest init --example provider-transformers-local
+cd provider-transformers-local
+npx promptfoo@latest eval
+```
+
+## What This Example Shows
+
+- **Local text generation** with `onnx-community/Qwen3-0.6B-ONNX` (latest Qwen3 model with thinking capabilities)
+- **Local embeddings** with `Xenova/all-MiniLM-L6-v2` for similarity assertions
+- Fully offline evaluation after initial model download
+- No API keys needed
+
+## Models Used
+
+| Model                            | Task            | Size   | Purpose               |
+| -------------------------------- | --------------- | ------ | --------------------- |
+| `onnx-community/Qwen3-0.6B-ONNX` | Text Generation | ~600MB | Generate responses    |
+| `Xenova/all-MiniLM-L6-v2`        | Embeddings      | ~23MB  | Similarity assertions |
+
+## First Run
+
+The first evaluation downloads both models (cached for subsequent runs):
+
+```text
+Downloading Qwen3-0.6B-ONNX... ~600MB
+Downloading all-MiniLM-L6-v2... ~23MB
+```
+
+Subsequent runs use cached models and are much faster.
+
+## Configuration Highlights
+
+```yaml
+providers:
+  - id: transformers:text-generation:onnx-community/Qwen3-0.6B-ONNX
+    config:
+      maxNewTokens: 100
+      temperature: 0.6
+      topP: 0.95
+      doSample: true
+
+defaultTest:
+  options:
+    provider:
+      embedding:
+        id: transformers:feature-extraction:Xenova/all-MiniLM-L6-v2
+```
+
+## Notes
+
+- Runs entirely on CPU by default
+- For faster inference, use `device: webgpu` if your system supports it
+- Use `dtype: q4` for smaller memory footprint with quantized models
+- Run with `-j 1` for systems with limited RAM

examples/provider-transformers-local/promptfooconfig.yaml

@@ -0,0 +1,53 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Fully local LLM evaluation with Transformers.js
+
+prompts:
+  - 'Explain {{concept}} to a beginner in 2-3 sentences.'
+
+providers:
+  # Local text generation with Qwen3-0.6B (latest Qwen3 with thinking capabilities)
+  # First run downloads ~600MB model, then cached for subsequent runs
+  - id: transformers:text-generation:onnx-community/Qwen3-0.6B-ONNX
+    config:
+      maxNewTokens: 100
+      temperature: 0.6
+      topP: 0.95
+      doSample: true
+
+defaultTest:
+  options:
+    provider:
+      # Local embeddings for similarity assertions
+      embedding:
+        id: transformers:feature-extraction:Xenova/all-MiniLM-L6-v2
+        config:
+          pooling: mean
+          normalize: true
+
+tests:
+  - vars:
+      concept: machine learning
+    assert:
+      - type: similar
+        value: 'Machine learning is a type of AI where computers learn patterns from data to make predictions'
+        threshold: 0.5
+      - type: javascript
+        value: output.length > 50
+
+  - vars:
+      concept: photosynthesis
+    assert:
+      - type: similar
+        value: 'Photosynthesis is how plants convert sunlight into energy using chlorophyll'
+        threshold: 0.5
+      - type: javascript
+        value: output.length > 50
+
+  - vars:
+      concept: gravity
+    assert:
+      - type: similar
+        value: 'Gravity is the force that attracts objects with mass toward each other'
+        threshold: 0.4
+      - type: javascript
+        value: output.length > 50