John S.

Hi bro, Great excellent job!!! awesome... It worked perfect with yolov3-tiny and yolov3. Time consume compare with yolov3-weight convert to Tensorflow (not lite) take much more. Thank you for guide...

I running from this document https://docs.nvidia.com/nemo-framework/user-guide/latest/playbooks/mistralsft.html Step 1 pass Step 2 Run the container using the following command --> pass Convert the huggingface model to .nemo model --> not pass...

merge_lora.sh killed in Qwen2-7B-Instruct

2

Hi, 1. I finetune model "Qwen2.5-VL-7B-Instruct" with lora and merge lora with "merge_lora.sh" sucessful. When I deploy to use lora model, the result not good if compare with "Qwen2-V:-7B-Instruct" 2....