| language: | |
| - en | |
| pipeline_tag: text-generation | |
| tags: | |
| - qwen3 | |
| - hallucination-detection | |
| - sopo | |
| # SOPO-4B | |
| Official release of the 4B [SOPO (Socratic Policy Optimization)](https://github.com/patsnap/SOPO) model for span-level hallucination detection. See the [evaluation instructions](https://github.com/patsnap/SOPO#evaluation) for the RAGTruth test set. | |
| ## RoPE configuration and compatibility | |
| **This checkpoint requires a RoPE base (`rope_theta`) of `5000000`, not the default `10000`.** The original `config.json` saved with Transformers 5.8.1 contained this value only under `rope_parameters.rope_theta`. With some older inference stacks, including Transformers 4.57.1 and vLLM 0.14.0, the absent top-level `rope_theta` can default to `10000` and override the nested value without an error or warning. This can seriously degrade predictions and cause unusually long, token-limited generations. | |
| The updated `config.json` sets **both** `rope_theta` and `rope_parameters.rope_theta` to `5000000` for compatibility. The model weights are unchanged. If you downloaded the checkpoint before this correction, re-download `config.json` (or add `"rope_theta": 5000000` at the top level of your local copy) before running inference. Check that the effective RoPE base in your serving stack is `5000000`, especially when using older Transformers or vLLM versions. | |
| ## Related resources | |
| - [SOPO source code and evaluation script](https://github.com/patsnap/SOPO) | |
| - [RL training dataset](https://huggingface.co/datasets/OverwhelmingFit/SOPO-RL-RAGTruth10k) | |
| - [Reasoning-augmented SFT training dataset](https://huggingface.co/datasets/OverwhelmingFit/SOPO-SFT-RAGTruth5k-Reasoning) | |