Frank
54b2d84613
frank-default-large now serves the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT
model with a standalone MTP draft head (Q4_0), f16 K + TurboQuant V KV cache,
and the Sharp chat template. Context is maxed to 262144 (one slot); reasoning
is on with preserve_thinking + preserve_reasoning in the chat kwargs.
- frank-default-large.env: Q8_0 AGENT model paths, CTX_SIZE=262144, REASONING=on,
REASONING_FORMAT=none, CHAT_TEMPLATE_KWARGS {enable_thinking, preserve_thinking,
preserve_reasoning}
- serve-frank-large.sh: standalone draft-mtp profile (already switched off the
Kairic/PromptForge path)
- download-q8agent.sh: reproducible HF fetch of the three payload files
- docs/LLM/kingjones-q8agent-rocmfpx.md: Q8_0 AGENT runbook
- AGENTS.md: topology + ACTIVE runtime section + TTM/GTT load note
- qwen3.8-strix-optimizations, Dankclaw Improvements: TTM pages_limit now 114 GiB
(applied 2026-08-25), full 262k KV + Q8 payload fit in one slot
- frank_large_config.bats: assert 262144 context, reasoning + preserve_* enabled
The TTM/GTT was raised to 114 GiB (29,883,536 pages) to hold the full 262k KV.
64 lines
1.8 KiB
Bash
Executable File
64 lines
1.8 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Download the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT payload for
|
|
# frank-default-large from HuggingFace into /home/dank/models/.../Q8_0-AGENT.
|
|
#
|
|
# Uses the token in ~/.cache/huggingface/token so the ~28 GB main file does not
|
|
# hit the anonymous 10 GB/30 min rate limit. Run on Dankclaw.
|
|
#
|
|
# bash scripts/download-q8agent.sh
|
|
# bash scripts/download-q8agent.sh --verify-only
|
|
set -euo pipefail
|
|
|
|
REPO="kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF"
|
|
DIR="/home/dank/models/kingjones-Qwen3.8-27B-ROCMFPX-Q8_0-AGENT"
|
|
EXPECTED=(
|
|
"Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf:28214425952"
|
|
"mmproj-Qwen3.8-27B-BF16.gguf:931145888"
|
|
"mtp-Qwen3.8-27B-Q4_0.gguf:1680271648"
|
|
)
|
|
|
|
cd -- "$(dirname -- "$0")/.."
|
|
|
|
main() {
|
|
local mode="download"
|
|
[[ "${1:-}" == "--verify-only" ]] && mode="verify"
|
|
mkdir -p "$DIR"
|
|
cd "$DIR"
|
|
|
|
local token
|
|
token="$(cat "$HOME/.cache/huggingface/token")"
|
|
[[ -n "$token" ]] || { echo "no HF token in $HOME/.cache/huggingface/token" >&2; exit 1; }
|
|
|
|
dl() {
|
|
local f="$1"
|
|
curl -fsSL -C - -o "$f" --retry 5 --retry-delay 3 --retry-max-time 3600 \
|
|
-H "Authorization: Bearer $token" \
|
|
"https://huggingface.co/$REPO/resolve/main/$f"
|
|
echo " done: $f ($(du -h "$f" | cut -f1))"
|
|
}
|
|
|
|
if [[ "$mode" == "download" ]]; then
|
|
echo "downloading $REPO into $DIR"
|
|
dl "Qwen3.8-27B-Q8_0_ROCMFPX_AGENT.gguf"
|
|
dl "mmproj-Qwen3.8-27B-BF16.gguf"
|
|
dl "mtp-Qwen3.8-27B-Q4_0.gguf"
|
|
fi
|
|
|
|
echo "verifying sizes"
|
|
local ok=1 f want act
|
|
for entry in "${EXPECTED[@]}"; do
|
|
f="${entry%%:*}"; want="${entry##*:}"
|
|
act="$(stat -c%s "$f")"
|
|
if [[ "$act" -eq "$want" ]]; then
|
|
echo " OK $f ($act bytes)"
|
|
else
|
|
echo " BAD $f ($act bytes, want $want)" >&2
|
|
ok=0
|
|
fi
|
|
done
|
|
[[ "$ok" -eq 1 ]] || exit 1
|
|
echo "all files present and sized correctly"
|
|
}
|
|
|
|
main "$@"
|