First, we need a dataset for which we’ll be able to tell if the model has trained. Let's create one that will make our model talk like Yoda. We can get a bunch of questions from TriviaQA, and generate responses by prompting an LLM to answer the question while pretending it’s Yoda. Running the script, I get a few thousand prompts and responses that look something like this:
黔西市新仁苗族乡化屋村掩映在青山绿水间，白墙黛瓦的民居依山而建，农家乐里挂起的红灯笼透着浓厚年味，令游客们流连忘返。。Snipaste - 截图 + 贴图对此有专业解读
，详情可参考手游
Follow topics & set alerts with myFT
ВСУ вновь атаковали Севастополь02:33，更多细节参见safew
The startup says no, and it has the independent test results to prove it. The test, which was yet again conducted by state-owned VTT …