Text Classification
Transformers
Safetensors
English
Korean
qwen3_5
image-text-to-text
ztc
answer-verification
hallucination-detection
zero-token
confidence-estimation
Instructions to use FINAL-Bench/ZTC-Judge-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FINAL-Bench/ZTC-Judge-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="FINAL-Bench/ZTC-Judge-9B")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("FINAL-Bench/ZTC-Judge-9B") model = AutoModelForMultimodalLM.from_pretrained("FINAL-Bench/ZTC-Judge-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "ztc_version": "1.0", | |
| "base_model": "Qwen/Qwen3.5-9B", | |
| "base_revision": "c202236235762e1c871ad0ccb60c8ee5ba337b9a", | |
| "probe_file": "ztc_probe.npz", | |
| "curve_probe_file": "ztc_curve_probe.npz", | |
| "hidden_dim": 4096, | |
| "layer": "last", | |
| "token": "last_non_pad", | |
| "max_length": 2048, | |
| "template": "다음은 어떤 문제와 그에 대한 답변이다. 이 답변이 옳은지 판단하라.\n\n[문제]\n%s\n\n[답변]\n%s\n\n이 답변은 옳은가?", | |
| "thresholds": { | |
| "review": -0.3499426770249868, | |
| "clear": 0.11775459663604514 | |
| }, | |
| "measured": { | |
| "leaderboard_auc": 0.6506, | |
| "surface_baseline": 0.6223, | |
| "n": 2018, | |
| "n_wrong": 508, | |
| "per_domain_lodo": { | |
| "전문시험(법·수학·생물)": 0.7623, | |
| "생물·의학": 0.631, | |
| "상식·다단계추론": 0.5881, | |
| "재난·안전 지침": 0.5862, | |
| "과학추론": 0.6764 | |
| }, | |
| "per_domain_baseline": { | |
| "전문시험(법·수학·생물)": 0.7138, | |
| "생물·의학": 0.5908, | |
| "상식·다단계추론": 0.542, | |
| "재난·안전 지침": 0.5949, | |
| "과학추론": 0.7272 | |
| }, | |
| "protocol": "2,018 items, corrected set; leave-one-domain-out; hyper-parameters chosen inside training domains only; per-domain then size-weighted. Curved probe produces the reported figure." | |
| } | |
| } |