From ddfc64013f36655740ba5f0521ac36bb7e5f11fa Mon Sep 17 00:00:00 2001 From: Frank Date: Tue, 25 Aug 2026 13:58:50 -0700 Subject: [PATCH] Fix Q6 AGENT projector path --- docs/LLM/kingjones-strix-mtp.md | 2 +- scripts/frank-default-large.env | 2 +- scripts/serve-frank-large.sh | 2 +- tests/frank_large_config.bats | 1 + 4 files changed, 4 insertions(+), 3 deletions(-) diff --git a/docs/LLM/kingjones-strix-mtp.md b/docs/LLM/kingjones-strix-mtp.md index 20203af..d5c927c 100644 --- a/docs/LLM/kingjones-strix-mtp.md +++ b/docs/LLM/kingjones-strix-mtp.md @@ -33,7 +33,7 @@ here; the head is loaded with `--model-draft`. The card ships six text files plus the vision projector. The service uses the Q6 AGENT file (requested for the fleet), the separate MTP draft head -and the Q8 vision projector. +and the Q8 vision projector (`mmproj-Qwen3.8-27B-Q8_0.gguf`). | File | Size | |------|------| diff --git a/scripts/frank-default-large.env b/scripts/frank-default-large.env index 4dc9c42..7980a17 100644 --- a/scripts/frank-default-large.env +++ b/scripts/frank-default-large.env @@ -16,7 +16,7 @@ LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf MTP_DRAFT_FILE=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf -MMPROJ_FILE=mmproj-Qwen3.8-27B-BF16.gguf +MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf # Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp # template drives thinking on by default (medium effort) and produces the diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh index 8ba266f..2eeb4b5 100755 --- a/scripts/serve-frank-large.sh +++ b/scripts/serve-frank-large.sh @@ -16,7 +16,7 @@ fi : "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}" : "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}" : "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}" -: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-BF16.gguf}" +: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}" : "${ALIAS:=frank-default-large}" : "${BIND_ADDR:=0.0.0.0}" : "${LISTEN_PORT:=7770}" diff --git a/tests/frank_large_config.bats b/tests/frank_large_config.bats index f0db0d6..fe6a3ba 100644 --- a/tests/frank_large_config.bats +++ b/tests/frank_large_config.bats @@ -13,6 +13,7 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja" @test "frank-default-large serves the kingjones AGENT model" { grep -q '^MODEL_FILE=Qwen3\.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT\.gguf$' "$ENV_FILE" grep -q '^MTP_DRAFT_FILE=' "$ENV_FILE" + grep -q '^MMPROJ_FILE=mmproj-Qwen3\.8-27B-Q8_0\.gguf$' "$ENV_FILE" ! grep -q -- '--kairic-edge' "$SERVE_FILE" }