| language: en | |
| tags: | |
| - gpt2 | |
| # CRiPT Model (Critical Thinking Intermediarily Pretrained Transformer) | |
| Base version of the trained model (GPT2 architecture) presented in the paper "Critical Thinking for Language Models" (Betz, Richardson and Voigt 2020). See also: | |
| * [blog entry](https://debatelab.github.io/journal/critical-thinking-language-models.html) | |
| * [GitHub repo](https://github.com/debatelab/aacorpus) | |
| * [paper](https://arxiv.org/pdf/2009.07185) | |