Downloads · 30 days
0
verdict-engine-qwen2.5-7b-lora
hqt2yotoz/verdict-engine-qwen2.5-7b-lora
verdict-engine-qwen2.5-7b-lora is a machine learning model from hqt2yotoz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
A QLoRA fine-tune of Qwen/Qwen2.5-7B-Instruct for opinionated research triage: it reads an item (HF model/dataset/paper) and emits a structured verdict — read-now | skim | skip | archive + novelty score + one-line rea…
Access
Public
Updated Jun 9, 2026
Repo size
173 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors162 MB · 93%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jun 8, 2026
- Updated
- Jun 9, 2026
- SHA
- 0adadd93
Base models
Model card
From the Hugging Face model README
Verdict Engine — verdict-engine-qwen2.5-7b-lora
A QLoRA fine-tune of Qwen/Qwen2.5-7B-Instruct for opinionated research triage: it reads an
item (HF model/dataset/paper) and emits a structured verdict —
read-now | skim | skip | archive + novelty score + one-line reason + tags.
Trained on a Sonnet-4.6-distilled dataset (true distillation, not self-distillation) via PEFT+TRL (bf16 LoRA). Part of a 4-model bake-off: every fine-tune was judged blind against its own base by a 3-lens panel (decisiveness / specificity / calibration).
Training data: hqt2yotoz/verdict-engine-triage-v2 — 468 train + 52 val examples, Sonnet-4.6-distilled (true distillation).
Blind-eval result (this model)
Fine-tune 10 / base 0 over 10 held-out firehose items — beats base. Full leaderboard:
| Model | FT wins | base wins |
|---|---|---|
| Qwen2.5-7B (control) | 10 | 0 |
| Qwen3-4B-2507 | 10 | 0 |
| Qwen3-8B | 10 | 0 |
| SmolLM3-3B | 9 | 1 |
The base over-praises (read-now + inflated novelty); the fine-tune discriminates (skim + honest novelty). The calibration panel rewards the fine-tune.
Built for the HuggingFace Build Small Hackathon. Repo: github.com/setuc/verdict-engine
- License
- apache-2.0
- Created
- Jun 8, 2026
- Updated
- Jun 9, 2026