desperadoola
desperadoola
I don't find the vocab file corresponding to the pre-trained model
The format of `MemoryDecision` task seems to conflict during training and interactive mode. On the Agent Information Page, `MemoryDecision` task is described as below, and we observe the same format...
https://github.com/tatsu-lab/stanford_alpaca/blob/73cac8be49a66ca5d159ee9199428804e1e6aabe/generate_instruction.py#L155
This paper [Low-Rank Bottleneck in Multi-head Attention Models](https://arxiv.org/pdf/2002.07028.pdf) suggests that we could fix the head size and keep hidden size unchanged. Could you support setting `d_k`, `d_q`, `d_v` independently instead...