machinelearningmo/greenlight-extractor-sft-v3-0b2aade3-dae6e098-ba7

Greenlight payment-clause extractor

This is a merged QLoRA derivative of Qwen/Qwen3-4B-Instruct-2507, published for the Greenlight project.

Training used 276 synthetic examples and 138 optimizer steps through Veri. Dataset SHA-256: 0b2aade3cb4a4724ede90442943f63919e1ca832c83555aa415bd39f8ddc79f3. Training job: 95e43036a0b9. Rank 8, 4-bit loading, learning rate 0.0001, sequence limit 1536, micro-batch 1, gradient accumulation 2.

This model proposes bounded structured payment terms. Consult the repository’s matched frozen base/tuned evaluation before making any quality claim.

The corpus contains generated clause text and developer-reviewed labels. No credentials or private customer records were used. Final labels are not uploaded to the trainer. Local tokenization validates the intended completion-only objective; remote effective label tensors were not directly inspected.

Outputs need source validation and owner review. Invoice eligibility, invoice issuance, contractual due date and actual bank settlement are distinct. Financial calculations remain in Greenlight’s deterministic cents engine. This model does not establish cash availability, authenticate documents or authorize payments.

The base model is licensed Apache 2.0. Greenlight’s modifications are the QLoRA fine-tune described above. Quantized merge can change generations; merged weights require their own serving and quality verification. See the source repository for corpus hashes, evaluation boundaries and reproducible owner tooling.