Jun 13
Orca paper from Microsoft instruction-tuned LLAMA 13b with millions of GPT4-generated reasoning prompts. Now, to work on an open source version of that https://arxiv.org/abs/2306.02707 
Orca: Progressive Learning from Complex Explanation Traces of GPT-4 Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation...
Orca: Progressive Learning from Complex Explanation Traces of GPT-4 Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation... 