Models#
About Model Profiles#
The models for NVIDIA NIM microservices use model engines that are tuned for specific NVIDIA GPU models, number of GPUs, precision, and so on. NVIDIA produces model engines for several popular combinations and these are referred to as model profiles. Each model profile is identified by a unique 64-character string of hexadecimal digits that is referred to as a profile ID.
The NIM microservices support automatic profile selection by determining the GPU model and count on the node and attempting to match the optimal model profile. Alternatively, NIM microservices support running a specified model profile, but this requires that you review the profiles and know the profile ID.
The available model profiles are stored in a file in the NIM container file system.
The file is referred to as the model manifest file and the default path is /opt/nim/etc/default/model_manifest.yaml in the container.
Hive AI Generated Image Detection Model Profiles#
Hive’s AI-Generated Image Detection model is optimized for use with the kind of media generated by popular AI generative engines such as DALL-E, Midjourney, and Stable Diffusion.
The model has two heads. The first head gives a binary classification for all images, identifying whether or not they were AI generated and the accompanying confidence score. The second head provides further details as to the image’s source, with support for the most popular AI art generators currently in use. If the model cannot identify a source, it will return none under the source head.
To select a model profile for deployment, set a specific model profile ID with -e NIM_MODEL_PROFILE=<value>. You can choose a model profile ID for your GPU from the following list:
GPU |
Backend |
Profile ID |
|---|---|---|
H100 |
TensorRT |
999d2a67b77bfc7d7350fb357dce68a93ff35859b8934b407b78fee4c4cbb8c4 |
A100 |
TensorRT |
c1ae702a62775c1a79bc7f4b3a3feb9efb333452c9cb09d6483e31c66559e3f5 |
L40 |
TensorRT |
185fbd9b7db53b83e1ae39a4d79a422f18affc9ec6c87b6b688cf18f5c12bb51 |
A10G |
TensorRT |
92dd744c0c7a13123e133a4db910572150d5c99e38d43af146840cd12c65e6fc |
If you run on an unsupported GPU, NIM chooses a generic, non-optimized profile with profile id 523658e9ea1d0d50ea13b6c8d295bcaf0d88596f3fbab27a921c40c22a7985f7.
Hive Deepfake Image Detection Model Profiles#
Hive’s Deepfake Image Detection model identifies whether or not an image is a deepfake. The model locates faces in an image. For each detected face, this model outputs a bounding box for its location, a classification, and accompanying confidence score. Image classification model that classifies whether an image is a deepfake.
To select a model profile for deployment, set a specific model profile ID with -e NIM_MODEL_PROFILE=<value>. You can choose a model profile ID for your GPU from the following list:
GPU |
Backend |
Profile ID |
|---|---|---|
H100 |
TensorRT |
999d2a67b77bfc7d7350fb357dce68a93ff35859b8934b407b78fee4c4cbb8c4 |
A100 |
TensorRT |
c1ae702a62775c1a79bc7f4b3a3feb9efb333452c9cb09d6483e31c66559e3f5 |
L40 |
TensorRT |
185fbd9b7db53b83e1ae39a4d79a422f18affc9ec6c87b6b688cf18f5c12bb51 |
A10G |
TensorRT |
92dd744c0c7a13123e133a4db910572150d5c99e38d43af146840cd12c65e6fc |
If you run on an unsupported GPU, NIM chooses a generic, non-optimized profile with profile id 523658e9ea1d0d50ea13b6c8d295bcaf0d88596f3fbab27a921c40c22a7985f7.