chore: snapshot in-progress question-gen work before preflight fixes

This commit is contained in:
2026-07-16 04:12:21 -04:00
parent 11a5545f57
commit a4c429b247
39 changed files with 738 additions and 283 deletions
+37
View File
@@ -0,0 +1,37 @@
#!/usr/bin/env bash
# 补生 Video-MME 6 类缺失题型(180 题)
# 背景:原 360 题中 6 类 task_type 使用了错误的自创类型,
# 已归档为 archived_wrong_task_types.tar.gz。
# 本脚本只生成缺失的 6 类,生成完成后手动合并到 accepted_questions.json。
set -euo pipefail
cd "$(dirname "$0")/.."
STORE_DIR="${STORE_DIR:-store}"
CONFIG="${CONFIG:-config/question_gen_180_补.yaml}"
DB_PATH="${DB_PATH:-logs/question_gen_补6类.db}"
export PYTHONUNBUFFERED=1
export HF_HUB_OFFLINE=1
export TRANSFORMERS_OFFLINE=1
# shellcheck source=../.env
source .env
[ "${MODE:-}" = "mock" ] && export LLM_MOCK=1 VLM_MOCK=1
PYTHON="$(conda run -n Video-Tree-TRM which python)"
"${PYTHON}" tools/generate_questions.py generate-v2 \
--store-dir "$STORE_DIR" \
--config "$CONFIG" \
--db-path "$DB_PATH" \
--task-types \
"Attribute Perception" \
"Counting Problem" \
"Information Synopsis" \
"OCR Problems" \
"Spatial Perception" \
"Temporal Perception" \
${SEED:+--seed "$SEED"}