Frank
87721ab0fe
Cross-cutting rename of the current llama.cpp endpoint on the RTX 3090
(port 7771) from frank-small to frank-secondary:
- Service trio: scripts/{frank-small.env,frank-small.service,
serve-frank-small.sh,download-frank-small.sh} → frank-secondary.*
- Test: tests/frank_small_unit.bats → tests/frank_secondary_unit.bats
- Runbooks: serverAppConfigs-docs/LLM/frank-small-*.md →
frank-secondary-*.md (9 files); the FreeToken runbook stays
freetoken-frank-small.md (it documents the retired CUDA-era service)
- Identifiers: FRANK_SMALL→FRANK_SECONDARY, llm_small→llm_secondary,
LLM_SMALL_*→LLM_SECONDARY_*, deploy_llm_small→deploy_llm_secondary
- Historical references to the OLD frank-small (FreeToken/CUDA on the
3090, and the Dankserver service that became frank-medium) are
preserved verbatim — they describe what the service was called
at the time.
86 lines
2.7 KiB
Bash
Executable File
86 lines
2.7 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Download the source Qwen3.5-9B checkpoint — the ONLY place this model
|
|
# family's MTP head (15 mtp.* tensors) exists. frank-large runs it as the
|
|
# vLLM cross-model MTP draft (MiMo-V2.6-Distill-Qwen-9B itself ships zero
|
|
# mtp tensors; that is why SGLang's NEXTN on frank-secondary draws 0.00
|
|
# acceptance). Public repo — no auth header on the command line.
|
|
#
|
|
# NOTE the odd upstream shard names (model.safetensors-0000N-of-00004...).
|
|
#
|
|
# Usage:
|
|
# scripts/download-frank-large-qwen35.sh [DEST_DIR] [--verify-only]
|
|
set -euo pipefail
|
|
|
|
REPO="Qwen/Qwen3.5-9B"
|
|
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="${DEST:-/home/dank/models/Qwen3.5-9B}"
|
|
|
|
# name bytes sha256(- = non-LFS, size-only check)
|
|
FILES=(
|
|
"model.safetensors-00001-of-00004.safetensors 5276436216 db6f444b43d318c92f360a13a25561a6a65b10c0631b8ed305a426dbaa6c380e"
|
|
"model.safetensors-00002-of-00004.safetensors 5335161512 31c7d7e2dd5d207840b31cc59083c8f4c4718959149e0358c0364052bb9a0330"
|
|
"model.safetensors-00003-of-00004.safetensors 5368717440 7ec36ba3a4176a44c3c0876ad80c56a2f70c84bf008d82e9501df642f17dadec"
|
|
"model.safetensors-00004-of-00004.safetensors 3325995712 b62b0c4cd7e44edee103ee8f4fe225f246d5e768e07bfd5f25b63a8aa1fdd0c6"
|
|
"model.safetensors.index.json 79657 -"
|
|
"config.json 3126 -"
|
|
"chat_template.jinja 7756 -"
|
|
"tokenizer.json 12807982 5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42"
|
|
"tokenizer_config.json 16710 -"
|
|
"vocab.json 6722759 -"
|
|
"merges.txt 3353259 -"
|
|
"preprocessor_config.json 390 -"
|
|
"video_preprocessor_config.json 385 -"
|
|
)
|
|
|
|
mkdir -p "$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 [[ "$sha" == "-" ]] || sha256sum -c --quiet <(printf '%s %s\n' "$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") != $size)"
|
|
status=1
|
|
continue
|
|
fi
|
|
if [[ "$sha" != "-" ]] && ! 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"
|