WindyITS's picture
Update runtime bundle path
0504829 verified
---
license: other
base_model:
- microsoft/deberta-v3-small
- mlx-community/Qwen3-4B-Instruct-2507-4bit
tags:
- knowledge-graph
- query-planning
- cypher
- transformers
- mlx
- qlora
---
# Business Model KG Query Stack
This repository contains the deployable local query stack for **Business Model
KG**. It is not a standalone chatbot model. It is a runtime bundle used by the
project to decide how a question should be handled and, when safe, to produce a
structured local query plan.
The bundle combines:
- a fine-tuned DeBERTa-v3-small router classifier
- calibrated router thresholds
- an MLX QLoRA planner adapter for `mlx-community/Qwen3-4B-Instruct-2507-4bit`
- the frozen planner system prompt
- the runtime bundle manifest
The package intentionally excludes optimizer states and intermediate training
checkpoints. It is the deployable bundle, not the full training workspace.
## Layout
```text
manifest.json
router/
thresholds.json
model/
planner/
system_prompt.txt
adapter/
```
## Components
Router:
```text
microsoft/deberta-v3-small
```
The router is stored as a full fine-tuned classifier under `router/model/`.
It predicts whether a question is suitable for local answering, should fall back
to a stronger hosted model, or should be refused. Runtime thresholds are stored
in `router/thresholds.json`.
Planner:
```text
mlx-community/Qwen3-4B-Instruct-2507-4bit
```
The planner is stored as an adapter only under `planner/adapter/`. To use it, the
runtime also needs the base model above. The planner system prompt is included in
`planner/system_prompt.txt`.
## Runtime Role
When the router selects the local path, the planner emits a compact supported
query plan. The Business Model KG Python runtime then validates that plan and
compiles it into read-only Cypher. This separation keeps the planner constrained
to the project ontology and avoids letting it execute arbitrary database logic.
## Intended Use
Use this repository as the contents of:
```text
runtime_assets/query_stack/
```
inside the Business Model KG project. The expected file locations are described
by `manifest.json`.
## Training Data
The related training dataset is published separately as:
```text
WindyITS/business-model-kg-query-planner-data
```
The router was trained on 8,000 examples and validated on 1,200 examples across
the labels `local`, `api_fallback`, and `refuse`.
No standalone license has been selected for this release yet. Check the upstream
terms for the base models before redistribution or production use.