Frank
b2a74004df
Replace the unsloth llama.cpp prebuilt (b11030, Qwen3.8-Flash-Next UD-IQ4_XS, 125B MoE) with the Kairic Edge runtime (ciru-ai/ROCmFPX, branch kairic-edge-qwen38-27b-v1.2, commit 205a3e5) serving jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (27B dense, IU4 W4A4). - Runtime: built from source (scripts/build-kairic-edge-gfx1151.sh), TheRock 7.15.0a20260718 toolchain, CK fdf4bb7f + gfx1151-iu4 patch. - Shape: one stream, full 262144 context (the model's native window), 1 slot, 8 GiB prompt-cache budget. - Spec method: native MTP depth 4 + n-gram drafting (24/64/64). DFlash is NOT available for this model (no DRAFT_DFLASH spec type). - Compatibility mode: the harness needs sampling, tools and a reasoning budget, which fast-greedy rejects. COMPATIBILITY_MODE=1 enables them. - Reasoning: enabled (auto + deepseek format, thoughts land in reasoning_content). - Payload: 4 files (15.5 GiB GGUF + 7.99 GiB FFN + 1.88 GiB GDN + 0.70 GiB GDN-Output), sha256-verified (scripts/download-frank-large-kairic.sh).
111 lines
4.2 KiB
Bash
Executable File
111 lines
4.2 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Download jcbtc/Qwen3.8-27B-IU4-Kairic-Edge (the frank-large model) on
|
|
# Dankclaw.
|
|
#
|
|
# bash scripts/download-frank-large-kairic.sh
|
|
# bash scripts/download-frank-large-kairic.sh --verify-only
|
|
#
|
|
# The Kairic Edge payload is four files: the main IU4 GGUF (15.5 GiB) and
|
|
# three .pfs sidecars (FFN 7.99 GiB, GDN 1.88 GiB, GDN-Output 0.70 GiB).
|
|
# The sidecars are the PromptForge IU4 (W4A4) weight shards the Kairic Edge
|
|
# runtime loads alongside the main GGUF (PROMPTFORGE_IU4_SIDECAR,
|
|
# PROMPTFORGE_GDN_SIDECAR, PROMPTFORGE_GDN_OUTPUT_SIDECAR).
|
|
#
|
|
# Integrity: every file is checked against its declared byte count and sha256
|
|
# (the values below are the LFS oids from the Hub, 2026-09-21). The repo is
|
|
# public (gated: false); an HF token at ~/.cache/huggingface/token is used
|
|
# when present to clear the anonymous rate limit on a 26 GB transfer.
|
|
#
|
|
# Layout after a successful run (MODEL_DIR):
|
|
# Qwen3.8-27B-IU4-Kairic-Edge.gguf 16617792672 main IU4 GGUF
|
|
# Qwen3.8-27B-Kairic-IU4-FFN.pfs 8576856064 FFN sidecar
|
|
# Qwen3.8-27B-Kairic-IU4-GDN.pfs 2019569664 GDN sidecar
|
|
# Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs 756953088 GDN-Output sidecar
|
|
set -euo pipefail
|
|
|
|
REPO="jcbtc/Qwen3.8-27B-IU4-Kairic-Edge"
|
|
MODEL_DIR="/home/dank/models/Qwen3.8-27B-IU4-Kairic-Edge"
|
|
BASE="https://huggingface.co/$REPO/resolve/main"
|
|
|
|
mode="download"
|
|
[[ "${1:-}" == "--verify-only" ]] && mode="verify"
|
|
|
|
token=""
|
|
auth=()
|
|
if [[ -r "$HOME/.cache/huggingface/token" ]]; then
|
|
token="$(tr -d '[:space:]' < "$HOME/.cache/huggingface/token")"
|
|
auth=(-H "Authorization: Bearer $token")
|
|
fi
|
|
|
|
dl() { # dl <relpath>
|
|
local rel="$1" dest="$MODEL_DIR/$rel"
|
|
[[ -s "$dest" ]] && return 0
|
|
mkdir -p "$(dirname "$dest")"
|
|
echo "fetching $rel"
|
|
curl -fL -C - "${auth[@]}" --retry 5 --retry-delay 3 -o "$dest" "$BASE/$rel"
|
|
}
|
|
|
|
# filename size sha256 — the LFS oids from the Hub (2026-09-21)
|
|
FILES=(
|
|
"Qwen3.8-27B-IU4-Kairic-Edge.gguf 16617792672 360caf7381907c3eca7ac0afd1228efc016af747f3f38637fb1c7f94daabac2a"
|
|
"Qwen3.8-27B-Kairic-IU4-FFN.pfs 8576856064 adcbb90a7b429a30a2a39043366d68320d72e8b4816a0f498e882b2f80a2ba2b"
|
|
"Qwen3.8-27B-Kairic-IU4-GDN.pfs 2019569664 82f931316f1c895da104915dec4697163808d06f0e6b2dc027cee7aa3afc0f0e"
|
|
"Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs 756953088 3b07e7b176559e4402924ba0c368532fa6f02118a33c71e70974c809bf6208a3"
|
|
)
|
|
|
|
RELS=()
|
|
for line in "${FILES[@]}"; do
|
|
read -r rel _ _ <<<"$line"
|
|
RELS+=("$rel")
|
|
done
|
|
|
|
# Verify each file's byte count and sha256 (idempotent: a complete file is
|
|
# re-checked, not re-downloaded).
|
|
echo "verifying $MODEL_DIR against declared sizes + sha256"
|
|
python3 - "$MODEL_DIR" "${RELS[@]}" <<'PY'
|
|
import hashlib, os, sys
|
|
model_dir = sys.argv[1]
|
|
rels = sys.argv[2:]
|
|
# (rel, size, sha256) triples, re-parsed from the same source of truth.
|
|
specs = {
|
|
"Qwen3.8-27B-IU4-Kairic-Edge.gguf": (16617792672, "360caf7381907c3eca7ac0afd1228efc016af747f3f38637fb1c7f94daabac2a"),
|
|
"Qwen3.8-27B-Kairic-IU4-FFN.pfs": (8576856064, "adcbb90a7b429a30a2a39043366d68320d72e8b4816a0f498e882b2f80a2ba2b"),
|
|
"Qwen3.8-27B-Kairic-IU4-GDN.pfs": (2019569664, "82f931316f1c895da104915dec4697163808d06f0e6b2dc027cee7aa3afc0f0e"),
|
|
"Qwen3.8-27B-Kairic-IU4-GDN-Output.pfs": (756953088, "3b07e7b176559e4402924ba0c368532fa6f02118a33c71e70974c809bf6208a3"),
|
|
}
|
|
ok = True
|
|
for rel in rels:
|
|
dest = os.path.join(model_dir, rel)
|
|
size, sha = specs[rel]
|
|
if not os.path.isfile(dest):
|
|
print(f" MISSING {rel}")
|
|
ok = False
|
|
continue
|
|
actual_size = os.path.getsize(dest)
|
|
if actual_size != size:
|
|
print(f" SIZE MISMATCH {rel}: {actual_size} != {size}")
|
|
ok = False
|
|
continue
|
|
h = hashlib.sha256()
|
|
with open(dest, "rb") as f:
|
|
for chunk in iter(lambda: f.read(1 << 24), b""):
|
|
h.update(chunk)
|
|
actual_sha = h.hexdigest()
|
|
if actual_sha != sha:
|
|
print(f" SHA256 MISMATCH {rel}: {actual_sha}")
|
|
ok = False
|
|
continue
|
|
print(f" OK {rel} ({actual_size} bytes)")
|
|
if not ok:
|
|
sys.exit(1)
|
|
PY
|
|
|
|
if [[ "$mode" == "download" ]]; then
|
|
for line in "${FILES[@]}"; do
|
|
read -r rel _ _ <<<"$line"
|
|
dl "$rel"
|
|
done
|
|
fi
|
|
|
|
echo "frank-large payload complete: $MODEL_DIR"
|