wehub-resource-sync
0d3cb498a3
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
49 lines
2.6 KiB
YAML
49 lines
2.6 KiB
YAML
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
|
description: Evaluating Nscale models for reasoning and creative tasks
|
|
prompts:
|
|
- file://prompts.txt
|
|
providers:
|
|
- id: nscale:openai/gpt-oss-120b
|
|
config:
|
|
temperature: 0.7
|
|
max_tokens: 1024
|
|
- id: nscale:meta/llama-3.3-70b-instruct
|
|
config:
|
|
temperature: 0.5
|
|
max_tokens: 1024
|
|
tests:
|
|
- vars:
|
|
task_type: mathematical reasoning
|
|
task_description: 'Solve this problem step by step: A train leaves Station A at 2:00 PM traveling at 60 mph toward Station B, which is 180 miles away. Another train leaves Station B at 2:30 PM traveling at 80 mph toward Station A. At what time will the two trains meet?'
|
|
assert:
|
|
- type: contains-any
|
|
value: ['3:48', '3:48 PM', 'distance', 'relative speed', 'combined speed']
|
|
- type: llm-rubric
|
|
value: 'The response should show clear step-by-step mathematical reasoning and arrive at the correct answer of 3:48 PM.'
|
|
- vars:
|
|
task_type: creative writing
|
|
task_description: 'Write a short story (2-3 paragraphs) about a librarian who discovers that books in their library are portals to different worlds. Include vivid descriptions and an intriguing plot twist.'
|
|
assert:
|
|
- type: contains-any
|
|
value: ['portal', 'world', 'librarian', 'books', 'discovery']
|
|
- type: llm-rubric
|
|
value: 'The story should be creative, well-structured, include vivid descriptions, and have an interesting plot twist.'
|
|
- vars:
|
|
task_type: logical reasoning
|
|
task_description: "Three friends - Alice, Bob, and Charlie - each have a different favorite color (red, blue, green) and a different pet (cat, dog, bird). Given the clues: 1) Alice doesn't like red, 2) The person who likes blue has a cat, 3) Charlie has a bird, 4) Bob doesn't like green. Determine who has which pet and favorite color."
|
|
assert:
|
|
- type: contains-any
|
|
value: ['Alice', 'Bob', 'Charlie', 'blue', 'cat', 'bird']
|
|
- type: llm-rubric
|
|
value: 'The response should systematically work through the logical constraints and arrive at the correct solution.'
|
|
- vars:
|
|
task_type: scientific explanation
|
|
task_description: "Explain the concept of photosynthesis in a way that a 12-year-old could understand, including why it's important for life on Earth."
|
|
assert:
|
|
- type: contains-any
|
|
value: ['sunlight', 'carbon dioxide', 'oxygen', 'glucose', 'chlorophyll', 'plants']
|
|
- type: llm-rubric
|
|
value: 'The explanation should be age-appropriate, scientifically accurate, and clearly explain the importance of photosynthesis.'
|
|
outputs:
|
|
- type: csv
|