prereasoner/prereasoner-weights

Prereasoner Runtime Weights

This repository contains the public, manifest-pinned runtime weights for Prereasoner, an interpretable table-question-answering system. Learned components produce semantic evidence and candidate SQL; a typed AST planner validates every candidate and owns joins, calculation verification, arbitration, rendering, and execution. The bundle is not a standalone text-to-SQL model.

Install

No Hugging Face account or token is required:

git clone https://github.com/ManiDoraisamy/prereasoner-data.git
cd prereasoner-data
python -m engine.fetch_weights

engine/data/weights_manifest.json pins this repository at an immutable commit and records the SHA-256 digest of every required file. The fetcher downloads into a temporary directory, verifies the complete bundle, and only then installs it.

Bundle Contents

File	Purpose
encoder.pt	State dictionary for the relational semantic readout
encoder_meta.pt	Readout allocation and constructor configuration
qwen_lora/adapter_model.safetensors	LoRA adapter for Qwen/Qwen2.5-0.5B
qwen_lora/adapter_config.json	PEFT adapter configuration
sql_proposer/adapter_model.safetensors	LoRA adapter for Qwen/Qwen2.5-0.5B (causal LM) that proposes own-data SQL candidates
sql_proposer/adapter_config.json	PEFT adapter configuration
anchor_assignment.npz	Calibrated named-dimension thresholds
primitives.npz	Learned primitive-composition head
schema_property_head.pt	Calibrated Schema.org named-property evidence head

The source repository contains the small ontology, calibration, taxonomy, arbiter, and manifest artifacts. The base Qwen model is downloaded separately from its publisher.

Model Boundary

The encoder adapter emits named Schema.org property probabilities, calibrated class proposals, embeddings for structural intent and ranking, and calculation operand signals. A released class may propose a coarse resolver family, but no score can authorize a table, join, calculation, or answer. The SQL proposer adapter decodes candidate SQL; Prereasoner uses a candidate only after mapping it into its typed AST and validating it, and a fitted arbiter chooses among validated candidates that execute. Deterministic code applies ontology mapping, exact source grounding, typed constraints, abstention rules, and execution checks.

Schema.org 30.0 supplies the named semantic coordinate system. Wikidata and publisher datasets supply observations mapped into those coordinates; mutable source facts are not intended to be memorized as answers.

Evaluation And Provenance

See the source repository's model card, data card, and Spider results for component boundaries, denominators, and limitations.

The bytes in this bundle are immutable and hash-verified. The promoted Schema.org head has a machine-readable corpus, split, seed, dependency, encoder, and held-out metric manifest. The shared encoder's historical training run has less completely recorded source-corpus provenance; do not combine metrics from the two tracks. All 926 Schema.org classes are representable, but only the released calibrated subset is servable. Unsupported and under-calibrated coordinates abstain.

Intended Use

• Semantic evidence for the matching Prereasoner source revision.
• Research on deterministic SQL planning informed by named learned dimensions.
• Local table and spreadsheet question answering with inspectable plans.

Out Of Scope

• Standalone SQL or answer generation.
• Authoritative identity or entity classification.
• High-stakes medical, legal, tax, financial, or safety decisions without source-specific review.
• Using the files with an unverified or incompatible source revision.

License

The Prereasoner weight bundle is released under Apache-2.0. The base model and source datasets retain their own licenses and terms. The sql_proposer/ adapter was trained on Spider TRAIN (Yu et al., EMNLP 2018; CC BY-SA 4.0); keep that attribution when redistributing it. See THIRD_PARTY.md.