111wukong

When  I run the Inference on the local server, why is it displayed as Inference images=0? Do you encounter similar situations?

Why am I driving multiple GPUS for training still slow?

3

Does this project not support multiple Gpus.Why am I driving multiple Gpus for training and still slow.

TypeError: LoRAConfig.__init__() got an unexpected keyword argument 'do_qat'[Question]:

2

### 请提出你的问题 Generating train split: 206 examples [00:00, 50584.08 examples/s] Traceback (most recent call last): File "/home/aistudio/PaddleNLP/llm/finetune_generation.py", line 626, in main() File "/home/aistudio/PaddleNLP/llm/finetune_generation.py", line 412, in main lora_config = LoRAConfig(...

BadRequestError: prompt tokens too long

1

我在运行你们的llama-index于er  niebot集成的时候，出现了如下错误，请问，这该怎么解决呢？