llm: retire the trio service names — fleet services renamed to frank-archon/frank-dragoon/frank-zealot

The 2026-10-09 wire aliases become the service names everywhere: systemd units, serve scripts, env files and FRANK_* variables, deploy-plan/deploy-remote service keys, container names, Prometheus job names + alert rules, Grafana dashboard queries, bats seams, runbook filenames, homepage/AGENTS lore, and historical prose. Rollback tags renamed in lockstep. Residue in the tree: zero. Retired frank-medium/small/npu names are history and stay. Known casualty: scripts/patches/*.patch context lines were rewritten; those retired-era vLLM-fork patches no longer apply byte-exact.
2026-10-10 17:03:14 -07:00
parent 5ced474eb9
commit 55f87fcdce
195 changed files with 2085 additions and 2064 deletions
@@ -0,0 +1,116 @@
+#!/usr/bin/env bash
+# Download kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF for
+# frank-dragoon (Dankclaw iGPU). Public repo — no auth header, and never a token
+# on the command line (it is world-readable in /proc/<pid>/cmdline).
+#
+# The payload is the repo's Q6 AGENT rung:
+#   * Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf — ftype 114, 23.15 GiB.
+#     Q6_0_ROCMFPX tensor type (102) + the AGENT routing, which keeps the
+#     output-head and attention tensors at plain Q8_0 — the variant the card
+#     names for MTP serving ("Take Q6 AGENT (114) if you want protected
+#     heads"). Like every ROCmFPX file it loads on nothing but the fork.
+#
+# The other two files frank-dragoon needs are NOT re-downloaded:
+#   * mtp-Qwen3.8-27B-Q4_0.gguf — the uncensored repo redistributes the
+#     ALIGNED repo's draft head byte for byte (identical Hub LFS oid
+#     051a1764…), so it is hardlinked out of the aligned payload dir when that
+#     dir holds the verified bytes, and fetched from this repo otherwise.
+#   * mmproj-Qwen3.8-27B-BF16.gguf — this repo ships a Q8_0 projector; the
+#     fleet keeps the BF16 one, which is the projector that was verified 4/4
+#     on spatial ground truth on this host. Hardlinked the same way, fetched
+#     from the ALIGNED repo if it is not on disk.
+#
+# Fresh downloads, no resume (`curl -C -` once produced an oversized file on a
+# 31 GiB payload); -f/--fail-with-body so an HTTP 401 is not a success, then
+# byte count and the Hub LFS sha256. Idempotent: complete files are skipped.
+#
+# Usage:
+#   scripts/download-frank-dragoon-kingjones-uncensored.sh [DEST_DIR] [--verify-only]
+set -euo pipefail
+
+REPO="kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP-GGUF"
+ALIGNED_REPO="kingjones777/Qwen3.8-27B-ROCmFP4-STRIX-MTP-GGUF"
+BASE="https://huggingface.co/${REPO}/resolve/main"
+ALIGNED_BASE="https://huggingface.co/${ALIGNED_REPO}/resolve/main"
+SOURCE_DIR="${SOURCE_DIR:-/home/dank/models/kingjones-Qwen3.8-27B-ROCmFP4-STRIX-MTP}"
+
+DEST=""
+VERIFY_ONLY=0
+for arg in "$@"; do
+    case "$arg" in
+        --verify-only) VERIFY_ONLY=1 ;;
+        *) DEST="$arg" ;;
+    esac
+done
+DEST="${DEST:-/home/dank/models/kingjones-Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP}"
+
+# name bytes sha256 base_url may_link — may_link=1 means the same bytes may
+# already exist in SOURCE_DIR (hardlink them instead of re-fetching).
+FILES=(
+  "Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf 24856607008 e966deb3d1a5a1b9ca7765126292f2d822f3dccdedb3b4872e673dec1cddc199 $BASE 0"
+  # The draft head is redistributed byte-identical by both repos; the BF16
+  # projector only exists in the aligned repo.
+  "mtp-Qwen3.8-27B-Q4_0.gguf 1680271648 051a1764cff8c4f3ee6ae8b00593a0364c7539c67fa50ffc58f3f96509fca38e $BASE 1"
+  "mmproj-Qwen3.8-27B-BF16.gguf 931145888 de2a49866988ea272c43dc2a43ee2662c25725a717ca5b9059ea420a97f53fe8 $ALIGNED_BASE 1"
+)
+
+matches() {  # matches FILE SIZE SHA — byte count AND LFS sha256
+    [[ -f "$1" ]] && [[ "$(stat -c%s "$1")" == "$2" ]] \
+        && sha256sum -c --quiet <(printf '%s  %s\n' "$3" "$1")
+}
+
+mkdir -p "$DEST"
+status=0
+
+fetch() {  # fetch NAME SIZE SHA BASE_URL
+    local name="$1" size="$2" sha="$3" url="$4" f="$DEST/$1"
+    echo "FETCHING  $name"
+    curl -fsSL --fail-with-body -o "$f.part" "$url/$name"
+    mv "$f.part" "$f"
+    if [[ "$(stat -c%s "$f")" != "$size" ]]; then
+        echo "SIZE FAIL $name ($(stat -c%s "$f") != $size)"
+        return 1
+    fi
+    if ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
+        echo "SHA FAIL  $name"
+        return 1
+    fi
+    echo "VERIFIED  $name"
+}
+
+for entry in "${FILES[@]}"; do
+    read -r name size sha url may_link <<<"$entry"
+    f="$DEST/$name"
+    if matches "$f" "$size" "$sha"; then
+        echo "OK        $name"
+        continue
+    fi
+    if (( VERIFY_ONLY )); then
+        echo "MISSING   $name"
+        status=1
+        continue
+    fi
+    # Shared bytes: prefer the local copy (same filesystem, so a hardlink costs
+    # nothing) over re-downloading gigabytes that hash identically.
+    if [[ "$may_link" == 1 && -n "${SOURCE_DIR:-}" ]] && matches "$SOURCE_DIR/$name" "$size" "$sha"; then
+        echo "LINKING   $name from $SOURCE_DIR"
+        ln -f "$SOURCE_DIR/$name" "$f" 2>/dev/null || cp -f "$SOURCE_DIR/$name" "$f"
+        if matches "$f" "$size" "$sha"; then
+            echo "VERIFIED  $name"
+            continue
+        fi
+        echo "SHA FAIL  $name (linked copy)"
+        status=1
+        continue
+    fi
+    if ! fetch "$name" "$size" "$sha" "$url"; then
+        status=1
+    fi
+done
+
+if (( status == 0 )); then
+    echo "DOWNLOAD_DONE $DEST"
+else
+    echo "DOWNLOAD_FAILED $DEST" >&2
+fi
+exit "$status"