Ling-3.0-flash-singprobe

inclusionAI/Ling-3.0-flash-singprobe

Ling-3.0-flash-singprobe is a machine learning model from inclusionAI. 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 mit.

<p align="center"<bEnglish</b | <a href="https://huggingface.co/inclusionAI/Ling-3.0-flash-singprobe/blob/main/READMECN.md"中文</a</p

Downloads · 30 days

204

86% of all-time downloads

All-time downloads

236

Public

Parameters

5.2M

10.4 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors10.4 MB · 100%

At a glance

License: mit
Model type: sing_probe_attn
Access: Public
Created: Sep 1, 2026
Updated: Sep 1, 2026
SHA: 872e3b3e

Base models

inclusionAI/Ling-3.0-flash

Model card

From the Hugging Face model README

Ling3-SingProbe

<p align="center"><b>English</b> | <a href="https://huggingface.co/inclusionAI/Ling-3.0-flash-singprobe/blob/main/README_CN.md">中文</a></p>

Model Description

SingProbe is an intrinsic streaming guardrail for inclusionAI/Ling-3.0-flash-singprobe, built on inclusionAI/Ling-3.0-flash. Rather than running a separate safety model, this lightweight probe reuses the base model's hidden states during generation to score, at every token, query intent, response unsafety, and hallucination risk. It adds less than 0.5% decode-time overhead.

Base model	Probe parameters	Tapped layers	Outputs
`inclusionAI/Ling-3.0-flash-singprobe`	5.18M	`[13, 26, 40]`	8 intents + unsafe + hallucination

See the technical report for methodology and complete results. Training codes are available at inclusionAI/SingProbe.

Evaluation

Higher is better for every metric. Results are averages over the benchmark suites specified below.

Task	Metric	Ling-3.0-flash-singprobe	Reference baseline
Query intent classification (6 benchmarks)	F1	0.8674	YuFeng-XGuard-Reason-8B: 0.8714
Response safety classification (8 benchmarks)	F1	0.8728	Qwen3Guard-Gen-8B-strict: 0.8604
Streaming safety (3 benchmarks)	R-AUC / T-AUC	0.9887 / 0.9481	Qwen3Guard-Stream-8B-strict: 0.9640 / 0.8893
Hallucination detection (6 benchmarks)	AUC	0.8012	DRIFT: 0.8000

Deployment characteristic	Result
Benign-response false-positive rate	0.03% average across 5 datasets
Online free-generation performance	0.9641 accuracy / 0.6452 F1 (leave-one-out)
Decode overhead	< 0.5%

Quick Start

SingProbe is supported through the SGLang integration branch or vLLM integration branch. Load the probe by its Hugging Face ID at server launch:

python -m sglang.launch_server \
  --model-path inclusionAI/Ling-3.0-flash \
  --probe-ckpt inclusionAI/Ling-3.0-flash-singprobe \
  --port 30000

The integrations return one score dictionary per generated token (label_0–label_9). They currently support Ling-3.0 (BailingMoeV3ForCausalLM) base models only. Use the exact base-model/probe pair: inclusionAI/Ling-3.0-flash with this checkpoint.

Citation

@article{singteam2026singprobe,
  title = {SingProbe Technical Report},
  author = {Sing Team},
  journal = {arXiv preprint arXiv:2608.30703},
  year = {2026},
}

Type: sing_probe_attn
License: mit
Created: Sep 1, 2026
Updated: Sep 1, 2026