---
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- reasoning
- looped transformer
arxiv: 2511.08577
library_name: transformers
datasets:
- open-r1/Mixture-of-Thoughts
base_model:
- Qwen/Qwen3-1.7B-Base
---

This is the general version of Standard-1.7B, trained on a mixture of math, code, and science data, presented in the paper [Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models](https://huggingface.co/papers/2511.08577).

Please visit our [GitHub repo](https://github.com/thu-nics/TaH) for more information.


### Sample Usage

Please see [Github Example](https://github.com/thu-nics/TaH?tab=readme-ov-file#run-an-example-for-tah) for sample usage.