Created Lab 6

content/labs/lab-6-evaluation-and-red-teaming/mmlu-promptfoo-config.yaml

@@ -0,0 +1,36 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Local MMLU evaluation
+
+providers:
+  - id: http:https://ai.zuccaro.me/api/v1
+    config:
+      headers:
+        Authorization: "Bearer sk-6e396c0dea144eaf8a0c39b84b2904c2"
+      body:
+        model: qwen3-llm-red-team-level-1
+        prompt: "{{prompt}}"
+    label: Open WebUI
+
+prompts:
+  - |
+    Question: {{question}}
+
+    A) {{option_a}}
+    B) {{option_b}}
+    C) {{option_c}}
+    D) {{option_d}}
+
+    Answer:
+
+defaultTest:
+  assert:
+    - type: llm-rubric
+      value: |
+        Compare the model's answer to the correct answer: {{answer}}.
+        The model should select the correct choice and show clear reasoning.
+        Score as PASS if the answer is correct.
+  options:
+    transformVars: '{ ...vars, sessionId: context.uuid }'
+
+tests:
+  - huggingface://datasets/CohereLabs/Global-MMLU-Lite?config=en&split=test