Frank
d4ce76b68b
Every comment that invoked a 'law' (50 word-boundary sites across 28 tracked files) now states what is going on and why, in terms that transfer to any project: gate twins drift until one side greenlights what the other refuses; a tag re-points while a digest pins; a restrictive engine behavior belongs to the runtime that imposed it and must be re-tested, not inherited; a speculative head is tensors in the file, not a flag; snapshot links dangle where the container resolves them; exit 0 is a clean stop to systemd, so a self-exiting daemon on on-failure goes dark reporting success. Event narratives and dates are gone from these comments; the mechanics carry the argument. Behavior-identical: bash -n, py_compile, yaml parse, full bats suite 408/408 green. One symbol rename rides along (stack script local scale_law -> scale_contract, with its log text).
79 lines
3.5 KiB
Bash
Executable File
79 lines
3.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# download-frank-dragoon-halogen.sh — fetch frank-dragoon'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 a token
|
|
# would never travel in argv: command lines are world-readable through
|
|
# /proc, so a secret placed there leaks to any process-listing tool).
|
|
#
|
|
# The fetch rules, uniform across every sibling script: curl -f so an
|
|
# access error fails loudly instead of writing the error body as a
|
|
# "successful" tiny artifact; the exact byte count from the model card;
|
|
# LFS sha256 verification; --verify-only to re-check an existing payload
|
|
# without downloading.
|
|
set -euo pipefail
|
|
|
|
DEST="${FRANK_DRAGOON_MODEL_DIR:-$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
|
|
tokenizer/tokenizer.json
|
|
tokenizer/vocab.json
|
|
tokenizer/merges.txt
|
|
tokenizer/chat_template.jinja
|
|
tokenizer/tokenizer_config.json)
|
|
# Byte sizes as published by the Hub on 2026-10-05, plus sha256 (the LFS
|
|
# oid) where the Hub stores an LFS object — plain git blobs carry no oid
|
|
# and are size-checked only. Re-check with:
|
|
# curl -s "https://huggingface.co/api/models/peonist-ai/halogen-qwen3.8-27b/tree/main?recursive=true"
|
|
SIZES=(35865565184 12809320 6722759 3353259 8952 17928)
|
|
SHAS=(274c3fc767fb57faf025dd03c76376b1fc1b32448aef45aaf02d1898fa962089
|
|
0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3 - - - -)
|
|
|
|
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/$f"
|
|
mkdir -p "$(dirname "$path")"
|
|
if [ "$VERIFY_ONLY" -eq 0 ]; then
|
|
# A file already at the published size skips the fetch entirely:
|
|
# resuming it would ask the CDN for a range past EOF (416 -> curl
|
|
# error under set -e), and re-pulling 33.4 GiB to prove a point is
|
|
# not what --verify-only is for. sha256 below still decides.
|
|
if [ -f "$path" ] && [ "$(stat -c %s "$path")" = "$want" ]; then
|
|
echo "HAVE $f ($want bytes) — skipping fetch"
|
|
else
|
|
echo "FETCH $f -> $path"
|
|
# HF answers /resolve/ with a 302 to the Xet CDN and curl DROPS
|
|
# the Range header across redirects — a naive -C - then
|
|
# "resumes" by pulling the ~1 KB redirect body (measured
|
|
# 2026-10-05: file frozen 14 MiB short, curl exit 0). Resolve
|
|
# the effective URL first, then resume against the CDN, which
|
|
# honors Range.
|
|
url=$(curl -sfIL -o /dev/null -w '%{url_effective}' "$BASE/$f") \
|
|
|| { echo "cannot resolve $BASE/$f" >&2; exit 1; }
|
|
curl -fL --retry 5 -C - -o "$path" "$url"
|
|
fi
|
|
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 where the Hub publishes an LFS oid..."
|
|
for i in "${!FILES[@]}"; do
|
|
f="${FILES[$i]}"; sha="${SHAS[$i]}"
|
|
if [ "$sha" = "-" ]; then
|
|
echo "OK $f (plain git blob, size-checked)"
|
|
continue
|
|
fi
|
|
got="$(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"
|