CLeaf_873981784

how to launch local inference

1

I tried python -m mmgpt.engine.serve.cli --model-path ./mmgpt/engine/serve/merlin --image-file ./mmgpt/engine/serve/examples/waterview.jpg but there is error File "/merlin-main/mmgpt/engine/serve/cli.py", line 53, in main image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values'].half().cuda() AttributeError: 'NoneType' object has no attribute 'preprocess'

about training cost

1

what's the difference between Merlin and Merlin-Chat models? How long time does it cost to train the model? how many GPUs does the model need to train?

hi, thank you for the excellent work! I wonder how you do the experiment of Fig.12. can you release the code of how to draw the heatmap?