Downloads · 30 days
11
14% of all-time downloads
cs-552-2026-Clanker-Scientists
cs-552-2026-Clanker-Scientists/coordinator-qwen3-14b-qlora-grounded
coordinator-qwen3-14b-qlora-grounded is a machine learning model from cs-552-2026-Clanker-Scientists. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Role-matched QLoRA adapter for the drafting stage (iv) of LegalClankerAssistant (CS-552 M3, team Clanker-Scientists): grounded, citation-backed answer drafting over retrieved legal evidence under a quote-first EVIDENC…
Downloads · 30 days
11
14% of all-time downloads
All-time downloads
76
Public
Repo size
525 MB
Likes
0
Public
Click a slice to open those files.
.safetensors514 MB · 97%
From the Hugging Face model README
Role-matched QLoRA adapter for the drafting stage (iv) of LegalClankerAssistant (CS-552 M3, team Clanker-Scientists): grounded, citation-backed answer drafting over retrieved legal evidence under a quote-first EVIDENCE/ANSWER output contract.
This adapter is the corrected successor to
coordinator-qwen3-14b-qlora-hybrid,
which proved inert at this role (0.819 vs base 0.824 strict verbatim on
identical items). The diagnosis: its training data (ContractNLI supervision +
Bar-Exam CoT) never exercised the deployed task. This adapter trains the same
base on role-matched data and moves it.
| axis | base | hybrid | grounded (this) |
|---|---|---|---|
| strict verbatim grounding | 0.824 | 0.819 | 0.962 |
| content verbatim | 0.987 | 0.980 | 0.995 |
| citation validity | 0.933 | 0.911 | 1.000 |
| gold ROUGE-L >= 0.30 | 0.511 | – | 0.587 |
| false refusals (oracle present) | 0.10 | 0.10 | 0.08 |
| strict verbatim under stress (K=4 distractors + 30% oracle drop) | 0.689 | 0.661 | 0.984 |
Mechanism: the fine-tune eliminates the near-miss (cosmetically altered quote) failure class — content-minus-strict gap 0.163 -> 0.033 clean and 0.228 -> 0.000 under stress. Verifier support is flat (0.838 -> 0.820): the entailment channel was never the deficit. Training is worth ~one doubling of inference compute (grounded N=1 composite 0.558 ~= base N=2 0.559).
[doc_id] text.adaptor-marianmt-fr-en ·
safeguard-deberta-ragtruth-v1 ·
coordinator-qwen3-14b-qlora-hybrid