09b2add673
New evalharness/fingerprint/ package (from evalstone fp_fusion v1.1, 2026-09-07 pruning final): probe battery -> concurrent collection -> five scoring views (verify/attribution/variant/adversarial/robustness), bundled family aliases + 27 reference fingerprints (12 fp_fusion schema). - CLI: 'evalharness fingerprint run ...' (REMAINDER passthrough, single source of arg definitions) + 'fingerprint list' for bundled references - imports rewritten package-relative; direct 'python3 run_fp_fusion.py' execution kept working via package bootstrap - offline analysis/collection scripts made path-independent (previously pinned to a /opt/evalscope path absent on this host) - shell scripts: hardcoded API key -> FP_API_KEY/OPENAI_API_KEY env vars - --reference accepts short names resolved against bundled references/ - pyproject: +httpx dependency, package-data references/*.json - tests/test_fingerprint.py: 10 offline tests (battery definitions, assembly counts, normalization, signals, verdict ladder, CLI wiring) - README: fingerprint section + architecture entry Verified on H20-1: tests 10/10, installed CLI OK, full-protocol run vs vectron GLM-5.3 reproduces baseline (score 0.9451, s_idn 0.846).
46 lines
2.4 KiB
Bash
46 lines
2.4 KiB
Bash
#!/bin/bash
|
||
# 任务2b/2c：代表模型 adversarial + variant + robustness（verify 批次之后跑）
|
||
# 需在 evalharness 环境下运行。凭据走环境变量，不再硬编码：
|
||
# export FP_API_KEY=sk-xxxx # 或复用 OPENAI_API_KEY
|
||
cd "$(dirname "$0")"
|
||
KEY="${FP_API_KEY:-${OPENAI_API_KEY:-}}"
|
||
API="${FP_API_URL:-https://api.vectron.meta-stone.com/v1}"
|
||
EB="${FP_EXTRA_BODY:-{\"chat_template_kwargs\":{\"enable_thinking\":false}}}"
|
||
R="$(pwd)/references"
|
||
if [ -z "$KEY" ]; then echo "ERROR: 未设置 FP_API_KEY/OPENAI_API_KEY" >&2; exit 1; fi
|
||
|
||
run_one() {
|
||
local mode=$1 model=$2 ref=$3 name=$4 extra="${5:-}"
|
||
mkdir -p /tmp/bfd/$name
|
||
echo "=== START $name $mode $(date +%H:%M) ==="
|
||
python3 run_fp_fusion.py --api-url "$API" --model "$model" \
|
||
--mode "$mode" --d-samples 25 --baseline-samples 5 --timeout 90 \
|
||
--d-concurrency 1 --text-concurrency 1 \
|
||
--api-key "$KEY" --extra-body "$EB" --reference "$ref" \
|
||
$extra \
|
||
--report-path /tmp/bfd/$name/${mode}.json > /tmp/bfd/$name/${mode}.log 2>&1
|
||
echo "=== END $name $mode exit=$? $(date +%H:%M) ==="
|
||
}
|
||
|
||
# 代表三模型：GLM-5.3、Kimi-K3、DS-Pro
|
||
# adversarial：跨家族伪装（GLM→Kimi 角色；Kimi→GLM；DS→GLM）
|
||
run_one adversarial ZhipuAi/GLM-5.3 $R/glm53_fusion_reference.json glm_53 \
|
||
'--impersonate "You are Kimi, Moonshot AI virtual assistant designed by Moonshot AI. You are Kimi."'
|
||
run_one adversarial MoonshotAi/Kimi-K3 $R/kimi_k3_fusion_reference.json kimi_k3 \
|
||
'--impersonate "You are GLM, Zhipu AI flagship assistant. You are GLM."'
|
||
run_one adversarial DeepSeek/DeepSeek-V4-Pro $R/deepseek_v4_pro_fusion_reference.json deepseek_v4_pro \
|
||
'--impersonate "You are GLM, Zhipu AI flagship assistant. You are GLM."'
|
||
|
||
# variant（--logprobs 自动开）
|
||
run_one variant ZhipuAi/GLM-5.3 $R/glm53_fusion_reference.json glm_53
|
||
run_one variant MoonshotAi/Kimi-K3 $R/kimi_k3_fusion_reference.json kimi_k3
|
||
run_one variant DeepSeek/DeepSeek-V4-Pro $R/deepseek_v4_pro_fusion_reference.json deepseek_v4_pro
|
||
|
||
# robustness（3 代表）
|
||
run_one robustness ZhipuAi/GLM-5.3 $R/glm53_fusion_reference.json glm_53 \
|
||
'--temperature-sweep "0.0,0.7,1.0" --prompt-variants 2'
|
||
run_one robustness MoonshotAi/Kimi-K3 $R/kimi_k3_fusion_reference.json kimi_k3 \
|
||
'--temperature-sweep "0.0,0.7,1.0" --prompt-variants 2'
|
||
run_one robustness DeepSeek/DeepSeek-V4-Pro $R/deepseek_v4_pro_fusion_reference.json deepseek_v4_pro \
|
||
'--temperature-sweep "0.0,0.7,1.0" --prompt-variants 2'
|