An MLX LoRA adapter for generating and repairing DAX expressions.

Download this repository, then load its directory as the adapter path:

The adapter was trained and evaluated with mlx-community/gpt-oss-20b-MXFP4-Q8. Its upstream base model is openai/gpt-oss-20b. It is not a merged model and does not include base-model weights.

adapters.safetensors is the final step-300 adapter. Its SHA-256 is:

adapter_config.json contains the MLX runtime parameters needed to load the adapter. adapter_manifest.json records portable training provenance. The local MLX training config is intentionally excluded because it contains machine-specific absolute paths.

This adapter was trained on synthetic DAX examples.

Both variants use the same MLX gpt-oss-20b-MXFP4-Q8 base model and consistent generation settings with an 8192-token output cap. In the saved comparison outputs, both variants emitted final-answer channels for every evaluated prompt. The independent-evaluation answer match is a normalized text-similarity heuristic, and the metadata-reference check is a regex-based screen for undeclared model references. DAXBench answer match uses exact or approved alternative answers; static DAX validation is parser/analyzer validation, not Power BI execution. Scores are indicative rather than a guarantee of correctness for every Power BI model.

The fine-tuned adapter produced answers faster and with much shorter responses:

Shorter responses generally use fewer output tokens, which can reduce output usage and waiting time. Actual results depend on your hardware, serving setup, prompts, and output limits.

Generated DAX must be validated against the target semantic model, including its tables, columns, relationships, date-table behavior, calculation groups, and RLS. Do not use this adapter as a substitute for production validation.

The upstream GPT-OSS base model and this adapter are Apache-2.0. The training curriculum is synthetic.