README.md

metadata

base_model: Qwen/Qwen2.5-7B-Instruct
library_name: transformers
tags:
  - compliance
  - legal
  - lora
  - qlora
  - prt
  - policy-reasoning-traces

qwen2.5-7b-prt-gdpr-unstructured-full-policy

Qwen2.5-7B-Instruct fine-tuned on Policy Reasoning Traces (PRTs) for binary compliance assessment, as part of an EMNLP 2026 study.

• Train domain: gdpr — unstructured opus-authored PRTs (format isolated).
• Cross-domain holdout: evaluate on the OTHER domain's held-out test set.
• Prompt format: no-policy zero-shot chain-of-thought; the model reasons step-by-step and ends with Final Verdict: COMPLIANT or Final Verdict: NONCOMPLIANT.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("josephimperial/qwen2.5-7b-prt-gdpr-unstructured-full-policy")
model = AutoModelForCausalLM.from_pretrained("josephimperial/qwen2.5-7b-prt-gdpr-unstructured-full-policy", torch_dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": PROMPT}]  # see prepare_data.build_prompt