BugReporterZ
BugReporterZ
When multiple users from different clients/PCs try to access the same Kobold server and the server is busy generating a response, the response generation will fail with the following message...
### Please check that this issue hasn't been reported before. - [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports. ### Expected Behavior Axolotl installation instructions for Conda...
This might be more of a general question, but is it possible to use [FlashAttention](https://github.com/Dao-AILab/flash-attention/tree/v1.0.9) with QLoRA in order to further decrease memory requirements when finetuning? I would guess that...
It can be incredibly helpful for readability, especially in those circumstances where Mikupad is used to hand-craft data for training or in-context learning (which most often needs to be formatted...