Frank
d89813363e
Fetches into /home/dank/models/Qwen3.8-Flash-Next-GGUF/ keeping the Hub layout: the six Q8_0 split parts (175.30 GiB — never concatenated, part 1's header advertises file_count=6), the shared Q8_0 MTP drafter head (2.6 GiB — "shared" borrows the target's embeddings; unsloth's MTP guide names it the recommended head), and the BF16 vision projector. Total 191,919,144,448 bytes. Sizes and sha256s captured from the resolve endpoint's x-linked-etag/ x-linked-size on 2026-09-26; every artifact is checked for exact byte count AND sha256, curl -f so an auth error fails instead of writing the error body, resumable via -C -. The repo is public: no token machinery.
93 lines
4.2 KiB
Bash
Executable File
93 lines
4.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Fetch the frank-primary payload: the Qwen3.8-Flash-Next Q8_0 target (six
|
|
# split parts), the shared Q8_0 MTP drafter head and the BF16 vision
|
|
# projector.
|
|
#
|
|
# bash scripts/download-frank-primary.sh
|
|
# bash scripts/download-frank-primary.sh --verify-only
|
|
#
|
|
# The repo (unsloth/Qwen3.8-Flash-Next-GGUF) is PUBLIC and anonymous: no HF
|
|
# token is needed, and none is accepted on the command line (a -H auth
|
|
# header is world-readable in /proc/<pid>/cmdline -- the 2026-09-16 leak).
|
|
#
|
|
# WHY THESE FILES:
|
|
# * Target: Q8_0/ -- unsloth's Q8_0 of Qwen3.8-Flash-Next (125B total /
|
|
# 6B active MoE + the 51B n-gram embedding table). Q_8 is the
|
|
# operator's requested quant (2026-09-26 swap off the lucebox DS4.1
|
|
# engine). The six parts ARE the payload: part 1's header advertises
|
|
# file_count=6, so they are never concatenated (concatenation trips
|
|
# "invalid split file name").
|
|
# * Drafter: MTP/mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf -- the shared
|
|
# MTP head (1 layer). "shared" means it borrows the target's embedding
|
|
# tensors instead of carrying its own copy: 2.6 GiB instead of 3.9,
|
|
# and unsloth's own MTP guide names it as the recommended head. It is
|
|
# loaded via -md (this build never autoloads drafters or projectors).
|
|
# * Vision: mmproj-BF16.gguf -- the BF16 projector, RDNA4-native per the
|
|
# frank-small precedent. Loaded via --mmproj explicitly.
|
|
#
|
|
# The script is resumable (curl -C -) and checks every artifact's exact byte
|
|
# count AND sha256 against the Hub's declared values, so a truncated or
|
|
# mis-fetched file fails here instead of load-crashing the server. Sizes and
|
|
# hashes were captured from the resolve endpoint's x-linked-etag/x-linked-size
|
|
# on 2026-09-26.
|
|
#
|
|
# Total: 191,919,144,448 bytes (178.74 GiB), of which 175.30 GiB is the
|
|
# target itself. Destination keeps the Hub layout so the serve script can
|
|
# name paths exactly as they appear upstream.
|
|
set -euo pipefail
|
|
|
|
REPO="unsloth/Qwen3.8-Flash-Next-GGUF"
|
|
DEST="/home/dank/models/Qwen3.8-Flash-Next-GGUF"
|
|
|
|
# path|bytes|sha256
|
|
MANIFEST=(
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00001-of-00006.gguf|10946624|2dabcbb53ca537a7947bc7d20414fd464eeaf4d66d43021b5b2556cc87544ad2"
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00002-of-00006.gguf|682434912|494ca4ed3dbf97bc28da88af3890b8877b9032f909812d00c0526a9ca5e91d2e"
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00003-of-00006.gguf|54400261312|34efd79a80a1ce540a517a5d56171924b66ce1c38b04c904f17ad6d8ef17cf20"
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00004-of-00006.gguf|49446841216|bfa634025fabbd2658bf7694bc80b90e571699c768723f844c934c7ef06c691a"
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00005-of-00006.gguf|49668930400|232a8f14cc0fa4262e7efe8593774b136fe40909e39c7a020342ddaa27259a97"
|
|
"Q8_0/Qwen3.8-Flash-Next-Q8_0-00006-of-00006.gguf|34015618784|538a93bca918064983409a41187ad4c68640f9aced6f29564da8f551bf86d7a5"
|
|
"MTP/mtp-Qwen3.8-Flash-Next-shared-Q8_0.gguf|2786568256|5ff54097406a905cf3a724c709124ceb0e3e10235ee862298969e91c96fa96e6"
|
|
"mmproj-BF16.gguf|907542944|2e788f8c511d8093c7b43cb87b2fd7e14228340318057f8fb20c86df2efe2355"
|
|
)
|
|
|
|
mode="download"
|
|
[[ "${1:-}" == "--verify-only" ]] && mode="verify"
|
|
|
|
if [[ "$mode" == "download" ]]; then
|
|
for entry in "${MANIFEST[@]}"; do
|
|
path="${entry%%|*}"
|
|
mkdir -p "$DEST/$(dirname "$path")"
|
|
echo "fetching $path"
|
|
# -f: a 401/403 must FAIL the fetch, not write the error body as
|
|
# the artifact (the 2026-09-16 gated-repo incident). -C -: resume
|
|
# partial files.
|
|
curl -fL -C - -o "$DEST/$path" --retry 10 --retry-delay 5 \
|
|
--retry-max-time 21600 \
|
|
"https://huggingface.co/$REPO/resolve/main/$path"
|
|
done
|
|
fi
|
|
|
|
echo "verifying sizes and sha256"
|
|
ok=1
|
|
for entry in "${MANIFEST[@]}"; do
|
|
path="${entry%%|*}"; rest="${entry#*|}"
|
|
size="${rest%%|*}"; sha256="${rest#*|}"
|
|
file="$DEST/$path"
|
|
act="$(stat -c%s "$file" 2>/dev/null || echo 0)"
|
|
if [[ "$act" -ne "$size" ]]; then
|
|
echo " BAD-SIZE $file ($act bytes, want $size)" >&2
|
|
ok=0
|
|
continue
|
|
fi
|
|
act_sha="$(sha256sum "$file" | cut -d' ' -f1)"
|
|
if [[ "$act_sha" != "$sha256" ]]; then
|
|
echo " BAD-SHA $file ($act_sha)" >&2
|
|
ok=0
|
|
continue
|
|
fi
|
|
echo " OK $path ($act bytes)"
|
|
done
|
|
[[ "$ok" -eq 1 ]] || exit 1
|
|
echo "all artifacts present, sized and hashed correctly"
|