Start-up report of where files are stored

app.py

@@ -203,6 +203,15 @@ speech_pipe = pipeline("automatic-speech-recognition", model=SPEECH_MODEL, torch
                        device="cuda", chunk_length_s=30)
 packs.seal("whisper", SPEECH_MODEL)
 print("[load] done.", flush=True)
+try:        # Where the downloads and packs really are, and what counts towards the disk limits
+    from huggingface_hub import constants as _hub
+    _script = ("du -xsh /root/.cache/* /root/.cache/huggingface/* /root/.zerogpu /data-nvme/* /tmp /home/* 2>/dev/null"
+               " | sort -h | tail -25; uname -r; free -g | head -2")
+    print("[where]", f"HF_HUB_CACHE={_hub.HF_HUB_CACHE} HOME={os.path.expanduser('~')} offload={packs.PACK_DIR}", "|",
+          subprocess.run(["sh", "-c", _script], capture_output=True, text=True, timeout=120).stdout.replace("\n", " | "),
+          flush=True)
+except Exception as e:
+    print(f"[where] failed: {e}", flush=True)
 
 # With a pack per model every job fits the default half-card slice ("large"), which is billed once.
 # Without them ZeroGPU copies all the models on every call, and that needs the whole card.