GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
thu-coai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
thu-coai
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-7B-Instruct1e-50.054096Main SeTox neologism test set, 624 valid samples:
| Checkpoint | Accuracy | Unsafe F1 | Unsafe Recall | Safe F1 |
|---|---|---|---|---|
| checkpoint-200 | 0.9407 | 0.9609 | 0.9286 | 0.8771 |
| checkpoint-175 | 0.9183 | 0.9451 | 0.8959 | 0.8401 |
Live search and generation settings can introduce small drift during reproduction.
See the SeTox code repository for search-augmented inference:
bash
python scripts/run_inference.py \ --model_path thu-coai/SeTox-Qwen2.5-7B \ --search_backend serper \ --input_path data/eval/neologism_test.json \ --output_path outputs/neologism_predictions.jsonFor offline smoke tests, use --mock or --search_backend none.
This model is intended for research on Chinese neologism toxicity detection. It can make mistakes on ambiguous, fast-changing, adversarial, or under-specified terms. Search results may contain noisy or unsafe snippets, and downstream users should apply appropriate safety review before deployment.
This model is fine-tuned from Qwen/Qwen2.5-7B-Instruct and follows the
Apache-2.0 license inherited from the base model.
Please cite the SeTox ACL paper:
bibtex
@inproceedings{cui-etal-2026-setox, title = "{S}e{T}ox: Search-enhanced Reasoning for {LLM}-based Toxicity Detection over {C}hinese Internet Buzzwords", author = "Cui, Yiming and Zhang, Qinglin and Su, Xu and Min, Changyu and Hu, Shilin and Huang, Minlie", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.acl-long.1602/", doi = "10.18653/v1/2026.acl-long.1602", pages = "33018--33034"}python scripts/run_inference.py \ --model_path thu-coai/SeTox-Qwen2.5-7B \ --search_backend serper \ --input_path data/eval/neologism_test.json \ --output_path outputs/neologism_predictions.json@inproceedings{cui-etal-2026-setox, title = "{S}e{T}ox: Search-enhanced Reasoning for {LLM}-based Toxicity Detection over {C}hinese Internet Buzzwords", author = "Cui, Yiming and Zhang, Qinglin and Su, Xu and Min, Changyu and Hu, Shilin and Huang, Minlie", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)", month = jul, year = "2026", address = "San Diego, California, USA", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.acl-long.1602/", doi = "10.18653/v1/2026.acl-long.1602", pages = "33018--33034"}