Frank
fece3ffdd0
Runtime swap ROCmFPX llama.cpp -> peonist-ai/halogen (image digest dc0a39a0, tag 0.1.4), serving qwen3.8-27b-p1w4d-d2.hgn (33.4 GiB, the .hgn format loads in no other engine) with HALOGEN_DRAFTER=2 (DFlash2) on ONE slot of 200700 ctx: slots>1 disables the drafter (engine law). Accepted: TEXT-ONLY (vision encoder ignored; frank-small owns images) and the censored base (rollback = revert this commit; payload, fork build and build-rocmfpx.sh pin stay on disk). - serve script: podman run under the root unit, exec podman wait so Restart=always is real; gates image digest, checkpoint byte-count, flat regular-file tokenizer, GPU nodes; engine stdout to log. - deploy handler: gates the artifacts, sweeps the legacy bare llama-server + old container name by NAME (never pkill llama-server: frank-small), retires the 2026-09 quadlet, port cutover 7770. - fetch script: -C - resume, -f, byte count, sha256, --verify-only. - seam rewritten (17 tests): halogen is now the deployed runtime.
50 lines
2.0 KiB
Bash
Executable File
50 lines
2.0 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# download-frank-large-halogen.sh — fetch frank-large's halogen payload:
|
|
# the qwen3.8-27b .hgn checkpoint and the export tokenizer, from the
|
|
# PUBLIC peonist-ai/halogen-qwen3.8-27b repo (no token — and per the fleet
|
|
# secret law, none would ever touch argv).
|
|
#
|
|
# The fetch law, same as every sibling script: curl -f (an access error
|
|
# must not become a "successful" 153-byte artifact), exact byte count from
|
|
# the model card, LFS sha256 verification, --verify-only to re-check an
|
|
# existing payload without downloading.
|
|
set -euo pipefail
|
|
|
|
DEST="${FRANK_LARGE_MODEL_DIR:-$HOME/models/halogen-qwen3.8-27b}"
|
|
BASE="https://huggingface.co/peonist-ai/halogen-qwen3.8-27b/resolve/main"
|
|
|
|
FILES=(qwen3.8-27b-p1w4d-d2.hgn frank-large.tokenizer.gguf)
|
|
# Byte sizes and sha256 (LFS oid) as published by the Hub on 2026-10-05 —
|
|
# re-check with: curl -s "https://huggingface.co/api/models/peonist-ai/halogen-qwen3.8-27b/tree/main?recursive=true"
|
|
SIZES=(35880329102 1293343)
|
|
SHAS=(40874e7a5c27efcf1c83c44374db85726fa4086355b3c8aae1b363644d7e6234
|
|
4c1ab3a19932f7d16eefc2c7fa60715c91133fe99c6dce683a3a7f11d463e7e9)
|
|
|
|
VERIFY_ONLY=0
|
|
[ "${1:-}" = "--verify-only" ] && VERIFY_ONLY=1
|
|
|
|
mkdir -p "$DEST"
|
|
|
|
for i in "${!FILES[@]}"; do
|
|
f="${FILES[$i]}"; want="${SIZES[$i]}"; sha="${SHAS[$i]}"
|
|
path="$DEST/$f"
|
|
if [ "$VERIFY_ONLY" -eq 0 ]; then
|
|
echo "FETCH $f -> $path"
|
|
# -C - resumes a partial file; -f keeps HTTP errors fatal.
|
|
curl -fL --retry 5 -C - -o "$path" "$BASE/$f"
|
|
fi
|
|
[ -f "$path" ] || { echo "MISSING $path (run without --verify-only)" >&2; exit 1; }
|
|
got="$(stat -c %s "$path")"
|
|
[ "$got" = "$want" ] || { echo "SIZE $path: $got != $want" >&2; exit 1; }
|
|
echo "OK $f ($got bytes)"
|
|
done
|
|
|
|
echo "byte counts match; verifying sha256 (one pass over 33.4 GiB)..."
|
|
for i in "${!FILES[@]}"; do
|
|
f="${FILES[$i]}"; sha="${SHAS[$i]}"
|
|
got="$(sha256sum "$DEST/$f" | cut -d' ' -f1)"
|
|
[ "$got" = "$sha" ] || { echo "SHA256 $f: $got != $sha" >&2; exit 1; }
|
|
echo "OK $f sha256"
|
|
done
|
|
echo "DOWNLOAD_DONE $DEST"
|