first commit

scripts/prepare_calib_data.py

@@ -22,6 +22,8 @@ BASE_URL = (
     "examples/calibration/calibration_data.txt"
 )
 BLOCK_SPLIT_RE = re.compile(r"\n\s*\n")
+SCRIPT_DIR = Path(__file__).resolve().parent
+ROOT_DIR = SCRIPT_DIR.parent
 
 
 def split_blocks(text: str) -> list[str]:
@@ -130,15 +132,21 @@ def ensure_cached_blocks(
 def main() -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument("--seed", type=int, default=42)
-    parser.add_argument("--base-file", default="calibration_data_v5_rc.txt")
-    parser.add_argument("--output", default="calibration_data_v5_rc_code.txt")
-    parser.add_argument("--data-dir", default="data")
+    parser.add_argument("--base-file", default="calibration/calibration_data_v5_rc.txt")
+    parser.add_argument("--output", default="calibration/calibration_data_v5_rc_code.txt")
+    parser.add_argument("--data-dir", default="calibration/sources")
     parser.add_argument("--force-refresh", action="store_true")
     args = parser.parse_args()
 
-    base_file = Path(args.base_file)
-    output_file = Path(args.output)
-    data_dir = Path(args.data_dir)
+    def resolve_path(path_text: str) -> Path:
+        p = Path(path_text)
+        if p.is_absolute():
+            return p
+        return ROOT_DIR / p
+
+    base_file = resolve_path(args.base_file)
+    output_file = resolve_path(args.output)
+    data_dir = resolve_path(args.data_dir)
     code_cache = data_dir / "code74k_2000.txt"
     openhermes_cache = data_dir / "openhermes_coding_chosen_1000.txt"
 

scripts/upload_to_modelscope.sh

@@ -1,25 +1,58 @@
 #!/usr/bin/env bash
 set -euo pipefail
 
-# 用法：
-#   ./upload_to_modelscope.sh <repo_id> <token>
-# 示例：
-#   ./upload_to_modelscope.sh your_username/your_repo_name ms-xxxxxxxx
+# Usage:
+#   ./scripts/upload_to_modelscope.sh <repo_id> <token> [upload_dir] [mode] [commit_message]
+#
+# Examples:
+#   ./scripts/upload_to_modelscope.sh your_user/your_repo ms-xxxx
+#   ./scripts/upload_to_modelscope.sh your_user/your_repo ms-xxxx modelscope_upload proxy
+#
+# mode:
+#   direct (default): unset proxy vars for direct connection
+#   proxy: keep current proxy environment
 
 REPO_ID="${1:-}"
 TOKEN="${2:-}"
+UPLOAD_DIR_ARG="${3:-modelscope_upload}"
+MODE="${4:-direct}"
+COMMIT_MESSAGE="${5:-Upload model artifacts}"
 
 if [[ -z "${REPO_ID}" || -z "${TOKEN}" ]]; then
-  echo "Usage: $0 <repo_id> <token>"
+  echo "Usage: $0 <repo_id> <token> [upload_dir] [mode] [commit_message]"
   exit 1
 fi
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 ROOT_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+UPLOAD_DIR="${UPLOAD_DIR_ARG}"
+if [[ "${UPLOAD_DIR}" != /* ]]; then
+  UPLOAD_DIR="${ROOT_DIR}/${UPLOAD_DIR}"
+fi
 
-"${ROOT_DIR}/.venv/bin/modelscope" login --token "${TOKEN}"
-"${ROOT_DIR}/.venv/bin/modelscope" upload "${REPO_ID}" "${SCRIPT_DIR}" . \
+if [[ ! -d "${UPLOAD_DIR}" ]]; then
+  echo "Upload directory does not exist: ${UPLOAD_DIR}"
+  exit 2
+fi
+
+MODELSCOPE_BIN="${ROOT_DIR}/.venv/bin/modelscope"
+if [[ ! -x "${MODELSCOPE_BIN}" ]]; then
+  echo "modelscope CLI not found at ${MODELSCOPE_BIN}"
+  exit 3
+fi
+
+if [[ "${MODE}" == "direct" ]]; then
+  RUN_CMD=(env -u HTTP_PROXY -u HTTPS_PROXY -u ALL_PROXY -u NO_PROXY "${MODELSCOPE_BIN}")
+elif [[ "${MODE}" == "proxy" ]]; then
+  RUN_CMD=("${MODELSCOPE_BIN}")
+else
+  echo "Unsupported mode: ${MODE} (use direct|proxy)"
+  exit 4
+fi
+
+"${RUN_CMD[@]}" login --token "${TOKEN}"
+"${RUN_CMD[@]}" upload "${REPO_ID}" "${UPLOAD_DIR}" . \
   --repo-type model \
-  --commit-message "Upload Qwen3.5-27B quantized GGUF weights"
+  --commit-message "${COMMIT_MESSAGE}"
 
 echo "Upload finished: ${REPO_ID}"