Frank
a02850203d
CTX_SIZE 589824 / PARALLEL 3 -> three independent 196,608-token conversations (a mamba hybrid cannot share one KV cache, so per-slot window = pool/slots; 3 x 262,144 would need 18.4 GiB of KV alone and busts the card). Vision comes back via bartowski's mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf (918,166,048 B, sha256 ff348f31..., fetched + verified by scripts/download-frank-small.sh): the Q5_K_M GGUF ships no v.* tensors, so --mmproj IS the image path. MMPROJ_FILE without a colon default so an explicit empty value is a real text-only opt-out, and the deployer now gates on the projector exactly as the serve script does. Budget is measured, not guessed: the 2 x 262,144 shape used 20,190/24,576 MiB, which prices non-KV cost at 7,390 MiB. Three slots + projector land near 22.5 GiB, i.e. ~2 GiB spare - the bottom of the requested band, to be confirmed by measurement and laddered if it lands outside 2-3 GiB.
84 lines
2.5 KiB
Bash
Executable File
84 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Download the frank-small payload for llama.cpp on the RTX 3090:
|
|
# bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF:Q5_K_M plus its vision projector
|
|
# (the GGUF carries no `v.*` tensors — the tower lives only in the mmproj, so
|
|
# without this file the endpoint is text-only by construction). Public repo —
|
|
# no auth header, and never a token on the command line (it is world-readable
|
|
# in /proc/<pid>/cmdline).
|
|
#
|
|
# Fresh downloads, no resume (`curl -C -` once produced a 213 MB 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.
|
|
#
|
|
# The Q6_K file this endpoint served until 2026-10-01 night stays on disk as
|
|
# the rollback target (7793710624 B, LFS oid
|
|
# ef96d05a2ddf2cbb450d1af1ac3860ec769d3575bafa70692ee5609bda3fad7d) — re-fetch
|
|
# it from the same repo with the same recipe if it is ever needed again.
|
|
#
|
|
# Usage:
|
|
# scripts/download-frank-small.sh [DEST_DIR] [--verify-only]
|
|
set -euo pipefail
|
|
|
|
REPO="bartowski/MiMo-V2.6-Distill-Qwen-9B-GGUF"
|
|
BASE="https://huggingface.co/${REPO}/resolve/main"
|
|
|
|
DEST=""
|
|
VERIFY_ONLY=0
|
|
for arg in "$@"; do
|
|
case "$arg" in
|
|
--verify-only) VERIFY_ONLY=1 ;;
|
|
*) DEST="$arg" ;;
|
|
esac
|
|
done
|
|
DEST="${DEST:-/home/dank/models/MiMo-Q5KM}"
|
|
|
|
# name bytes sha256
|
|
FILES=(
|
|
"MiMo-V2.6-Distill-Qwen-9B-Q5_K_M.gguf 6876124704 04cf46f2b5584ef922697d6c063f94879434fb86c467f1a09e52daf0cddaf35f"
|
|
"mmproj-MiMo-V2.6-Distill-Qwen-9B-f16.gguf 918166048 ff348f3180a63188aa7285db85f550fe38acb61dd013c599eb8bad08d2cc2576"
|
|
)
|
|
|
|
mkdir -p "$DEST"
|
|
status=0
|
|
for entry in "${FILES[@]}"; do
|
|
read -r name size sha <<<"$entry"
|
|
f="$DEST/$name"
|
|
have=0
|
|
if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]]; then
|
|
if sha256sum -c --quiet <(printf '%s %s\n' "$sha" "$f"); then
|
|
have=1
|
|
fi
|
|
fi
|
|
if (( have )); then
|
|
echo "OK $name"
|
|
continue
|
|
fi
|
|
if (( VERIFY_ONLY )); then
|
|
echo "MISSING $name"
|
|
status=1
|
|
continue
|
|
fi
|
|
echo "FETCHING $name"
|
|
tmp="$f.part"
|
|
curl -fsSL --fail-with-body -o "$tmp" "$BASE/$name"
|
|
mv "$tmp" "$f"
|
|
if [[ "$(stat -c%s "$f")" != "$size" ]]; then
|
|
echo "SIZE FAIL $name ($(stat -c%s "$f") != $size)"
|
|
status=1
|
|
continue
|
|
fi
|
|
if ! sha256sum -c --quiet <(printf '%s %s\n' "$sha" "$f"); then
|
|
echo "SHA FAIL $name"
|
|
status=1
|
|
continue
|
|
fi
|
|
echo "VERIFIED $name"
|
|
done
|
|
if (( status == 0 )); then
|
|
echo "DOWNLOAD_DONE $DEST"
|
|
else
|
|
echo "DOWNLOAD_FAILED $DEST" >&2
|
|
fi
|
|
exit "$status"
|