68 lines
3 KiB
Text
68 lines
3 KiB
Text
# =============================================================================
|
|
# CORE — environment variable template
|
|
# Copy to .env and fill in real values. .env is git-ignored.
|
|
# =============================================================================
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# OpenAI
|
|
# Used by: evals/frontier_compare/providers.py (OpenAIAdapter)
|
|
# Benchmarks: determinism, truth_lock, axis_orthogonality (provider=openai)
|
|
# ---------------------------------------------------------------------------
|
|
OPENAI_API_KEY=
|
|
|
|
# Model to use when PROVIDER=openai is not otherwise overridden per-benchmark.
|
|
# Defaults to gpt-4o if unset. Set to a specific snapshot for reproducibility,
|
|
# e.g. gpt-4o-2024-08-06 — see docs/models/openai.md
|
|
OPENAI_MODEL=gpt-4o
|
|
|
|
# Optional: override the base URL (e.g. for Azure OpenAI or a local proxy)
|
|
# OPENAI_BASE_URL=https://api.openai.com/v1
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Anthropic
|
|
# Used by: evals/frontier_compare/providers.py (AnthropicAdapter)
|
|
# Benchmarks: determinism, truth_lock, axis_orthogonality (provider=anthropic)
|
|
# ---------------------------------------------------------------------------
|
|
ANTHROPIC_API_KEY=
|
|
|
|
# Model to use when PROVIDER=anthropic is not otherwise overridden per-benchmark.
|
|
# Defaults to claude-opus-4-5 if unset. Use a dated version slug for
|
|
# reproducibility — see docs/models/anthropic.md
|
|
ANTHROPIC_MODEL=claude-opus-4-5
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Ollama (local open-weight models)
|
|
# Used by: evals/frontier_compare/providers.py (OllamaAdapter)
|
|
# Benchmarks: any benchmark with provider=ollama
|
|
# ---------------------------------------------------------------------------
|
|
OLLAMA_URL=http://localhost:11434
|
|
|
|
# API key — leave empty for a stock local Ollama install.
|
|
# Set if running behind a proxy that requires a key.
|
|
OLLAMA_API_KEY=
|
|
|
|
# Default model tag to pull and run. Must be a tag known to your Ollama
|
|
# install. See docs/models/ollama.md for tested model cards.
|
|
OLLAMA_MODEL=llama3.2
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Benchmark-level controls
|
|
# ---------------------------------------------------------------------------
|
|
|
|
# Comma-separated list of providers to include when running a multi-provider
|
|
# benchmark sweep. Valid tokens: openai, anthropic, ollama, core
|
|
# Example: BENCHMARK_PROVIDERS=core,openai,anthropic
|
|
BENCHMARK_PROVIDERS=core
|
|
|
|
# Default number of repeated runs per prompt (determinism suite).
|
|
# Increase to 10+ for publication-grade stability claims.
|
|
BENCHMARK_RUNS=3
|
|
|
|
# Temperature passed to all frontier provider calls.
|
|
# Use 0 to minimise stochastic variation in comparison benchmarks.
|
|
# CORE itself ignores this — it is deterministic by construction.
|
|
BENCHMARK_TEMPERATURE=0
|
|
|
|
# Directory for writing JSON benchmark reports.
|
|
# Relative to the repository root. Created if absent.
|
|
BENCHMARK_REPORT_DIR=reports
|