William yan

@karlzipple You can go to Bard.py to change the functionality of 'def ask(self, message: str) -> dict:', print out the 'json_chat_data' to see what is your task-oriented requirement, and customize...

trainable params: 884,736 || all params: 168,246,528 || trainable%: 0.5258569139685307 {'loss': 0.0, 'learning_rate': 0.0, 'epoch': 0.21} Same issue here, any hint might be helpful

Run on T5-flan-base, 8*A6000 48G server, can use CUDA_VISIABLE_DEVICES to launch by set (= 0 | 0,1 | 0,1,2), but when use more than 3 GPUs, the same "ValueError: You...

I pulled on aws, it worked, and then scp the checkpoint to my local machine.

any update lately?

you can try lower the temperature hyperparameters @Dineshkumar-Anandan-ZS0367 > Same prompt and same ocr text from image. Each request the llm gives different results, how can I maintain the results....