William Gill
f5a222fe6f
User confirmed this model works end-to-end after the multi-base-model
search. Settled on it because Qwen 3 VL's fine-tune lineage isn't
damaged by abliteration the way Qwen 3.5's is, so it both calls tools
reliably AND won't refuse to dispatch on NSFW edit prompts.
Updated:
- image_studio.json base_model_id → huihui_ai/qwen3-vl-abliterated:8b
- init-models.sh: pulls the abliterated VL model in place of the
non-working standard qwen3.5:9b
- image_studio.md: setup table base-model row + vision-section
'why this and not the alternatives' explanation
function_calling stays default and tool_choice required. Operator
can flip to native + drop tool_choice once they've verified the new
base behaves with structured tool calls (which would also remove the
need for a separate Task Model for title generation).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
71 lines
2.8 KiB
Bash
71 lines
2.8 KiB
Bash
#!/bin/sh
|
|
# Preseed Ollama with the models the stack should have available at startup.
|
|
# Runs once via the model-init service (see docker-compose.yml). Safe to
|
|
# re-run — already-present models are skipped.
|
|
#
|
|
# Two pull paths:
|
|
# - s3_pull — fetches a tarball from $S3_OLLAMA_BASE (your own mirror,
|
|
# created by mirror-ollama-model.sh) and extracts into
|
|
# Ollama's data dir. Faster + immune to upstream changes.
|
|
# Falls back to ollama pull if S3_OLLAMA_BASE is unset.
|
|
# - pull — standard `ollama pull` against registry.ollama.ai.
|
|
|
|
set -e
|
|
|
|
# Make sure curl is available — ollama/ollama:latest doesn't always include
|
|
# it, and s3_pull needs it. tar is in the base image.
|
|
if ! command -v curl >/dev/null 2>&1; then
|
|
apt-get update -qq && apt-get install -y -qq curl ca-certificates >/dev/null
|
|
fi
|
|
|
|
S3_OLLAMA_BASE="${S3_OLLAMA_BASE:-}"
|
|
OLLAMA_DATA="/root/.ollama"
|
|
|
|
s3_pull() {
|
|
name="$1"; archive="$2"
|
|
if ollama list 2>/dev/null | awk 'NR>1 {print $1}' | grep -qx "$name"; then
|
|
echo "✓ $name already present"
|
|
return
|
|
fi
|
|
if [ -z "$S3_OLLAMA_BASE" ]; then
|
|
echo "→ $name: S3_OLLAMA_BASE unset, falling back to ollama pull"
|
|
ollama pull "$name"
|
|
return
|
|
fi
|
|
url="${S3_OLLAMA_BASE%/}/$archive"
|
|
echo "→ Downloading $name from $url…"
|
|
curl -fL -C - --retry 3 -o "/tmp/$archive" "$url"
|
|
tar -xzf "/tmp/$archive" -C "$OLLAMA_DATA/models/"
|
|
rm -f "/tmp/$archive"
|
|
echo "✓ $name installed (mirror)"
|
|
}
|
|
|
|
pull() {
|
|
name="$1"
|
|
if ollama list 2>/dev/null | awk 'NR>1 {print $1}' | grep -qx "$name"; then
|
|
echo "✓ $name already present"
|
|
else
|
|
echo "→ Pulling $name from registry.ollama.ai…"
|
|
ollama pull "$name"
|
|
fi
|
|
}
|
|
|
|
# ─── S3-mirrored models ─────────────────────────────────────────────────────
|
|
# These live in your own bucket. Create the tarballs once with
|
|
# mirror-ollama-model.sh, upload to S3, then list them here.
|
|
s3_pull "huihui_ai/qwen3.5-abliterated:9b" "qwen3.5-abliterated-9b.tgz"
|
|
|
|
# huihui_ai/qwen3-vl-abliterated — Qwen 3 VL base abliteration (different
|
|
# fine-tune lineage than Qwen 3.5, so its tool-call template stays intact).
|
|
# Used as the Image Studio dispatcher: vision-capable, calls tools
|
|
# reliably, and doesn't refuse to dispatch on NSFW edit prompts. Pulled
|
|
# from registry; no S3 mirror entry yet.
|
|
pull "huihui_ai/qwen3-vl-abliterated:8b"
|
|
|
|
# ─── Direct registry pulls ──────────────────────────────────────────────────
|
|
for model in dolphin3:8b llama3.1:8b ministral-3:8b mistral-nemo:12b qwen3.6:latest; do
|
|
pull "$model"
|
|
done
|
|
|
|
echo "Done."
|