evalstone/scripts/build_fingerprint_image.sh
ruoxi_sun 4f274c2c32 add fingerprint model library & fp_fusion integration
- fingerprint benchmark: add fp_fusion(26-cell fusion) to collect_results/run.py
- run_llmmap.py: default model path to evalstone built-in model_library
- add model libraries (llmdetector 11 refs / fp_fusion 8 fusion refs /
  llmmap templates 60 models incl 8 new: GLM-5.2/5.3, DeepSeek-Flash/Pro/
  Flash-0731, Kimi-K3, MiniMax-M2.7, TianGong-Taie)
- add fp_fusion engine (battery/engine/scorer) + docs
- gitignore: exclude binary model weights and temp backups
2026-09-03 02:38:35 +00:00

32 lines
1.1 KiB
Bash
Executable File

#!/usr/bin/env bash
# Build the fingerprint-enabled evalstone image:
# evalscope-complete-py312-fp:<tag>
#
# 用法:
# bash scripts/build_fingerprint_image.sh [tag] # 默认 tag: v1
# TAG=v2 bash scripts/build_fingerprint_image.sh # 指定 tag
#
# 构建完成后,新容器内无需任何环境配置:
# docker run -it --rm \
# -v /data1/eval/evalstone:/workspace/evalscope \
# -v /data1/models:/opt/models \
# evalscope-complete-py312-fp:v1
# cd /workspace/evalscope
# python bash/run.py --suite fingerprint --model <name> --api-url http://<host>:30000/v1
set -euo pipefail
PROJECT_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
TAG="${1:-${TAG:-v1}}"
CTX="$PROJECT_ROOT/docker/fingerprint_context"
# 1) 刷新 build 上下文(工具仓库 + 裁剪后的模型缓存)
bash "$PROJECT_ROOT/scripts/stage_fingerprint_context.sh"
# 2) 构建
docker build -f "$PROJECT_ROOT/docker/Dockerfile.fingerprint" \
-t "evalscope-complete-py312-fp:$TAG" "$CTX"
echo
echo "[build] done: evalscope-complete-py312-fp:$TAG"
docker images | grep evalscope-complete-py312-fp || true