When i try to use NIM to deploy my custom model (mistral 24B), but the model output it’s very different, I think it hasn’t convert my model in the right way, and I would like to check, when I run the docker it comes up the example, is this example for correction the model or not?
Could you post the outputs you are seeing? Are you able to use the NIM built for the Mistral 24B model? mistral-small-24b-instruct-2501 | NVIDIA NGC