Merge branch 'main' into vaibhj/deprecatespark33

assets/aml-benchmark/components/batch_output_formatter/spec.yaml

@@ -1,5 +1,5 @@
 name: batch_output_formatter
-version: 0.0.14
+version: 0.0.15
 display_name: Batch Output Formatter
 is_deterministic: True
 type: command

assets/aml-benchmark/components/batch_resource_manager/spec.yaml

@@ -4,7 +4,7 @@ is_deterministic: False
 name: batch_resource_manager
 display_name: Batch Inference Resource Manager
 description: Resource Manager for batch inference.
-version: 0.0.7
+version: 0.0.8
 
 inputs:
   wait_input:

assets/aml-benchmark/components/benchmark_embedding_model/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: benchmark_embedding_model
 display_name: Benchmark Embedding Model
 description: Component for benchmarking an embedding model via MTEB.
-version: 0.0.3
+version: 0.0.4
 
 inputs:
   endpoint_url:

assets/aml-benchmark/components/benchmark_result_aggregator/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: benchmark_result_aggregator
 display_name: Benchmark result aggregator
 description: Aggregate quality metrics, performance metrics and all of the metadata from the pipeline. Also add them to the root run.
-version: 0.0.13
+version: 0.0.14
 is_deterministic: false
 
 inputs:

assets/aml-benchmark/components/compute_performance_metrics/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: compute_performance_metrics
 display_name: Compute Performance Metrics
 description: Performs performance metric post processing using data from a model inference run.
-version: 0.0.10
+version: 0.0.11
 is_deterministic: true
 
 inputs:

assets/aml-benchmark/components/dataset_downloader/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: dataset_downloader
 display_name: Dataset Downloader
 description: Downloads the dataset onto blob store.
-version: 0.0.10
+version: 0.0.11
 
 inputs:
   dataset_name: 

assets/aml-benchmark/components/dataset_preprocessor/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name:  dataset_preprocessor 
 display_name: Dataset Preprocessor
 description: Dataset Preprocessor
-version: 0.0.10
+version: 0.0.11
 is_deterministic: true
 
 inputs:

assets/aml-benchmark/components/dataset_sampler/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: dataset_sampler
 display_name: Dataset Sampler
 description: Samples a dataset containing JSONL file(s).
-version: 0.0.10
+version: 0.0.11
 
 inputs:
   dataset: 

assets/aml-benchmark/components/inference_postprocessor/spec.yaml

@@ -4,7 +4,7 @@ type: command
 name: inference_postprocessor
 display_name: Inference Postprocessor
 description: Inference Postprocessor
-version: 0.0.11
+version: 0.0.12
 is_deterministic: true
 
 inputs:

assets/aml-benchmark/components/prompt_crafter/spec.yaml

@@ -6,7 +6,7 @@ display_name: Prompt Crafter
 description: This component is used to create prompts from a given dataset. From a 
   given jinja prompt template, it will generate prompts. It can also create 
   few-shot prompts given a few-shot dataset and the number of shots.
-version: 0.0.13
+version: 0.0.14
 is_deterministic: true
 
 inputs:

assets/inference/environments/minimal-ubuntu20.04-py39-cpu-inference/tests/minimal_inference_test.py

@@ -32,10 +32,10 @@ def test_minimal_cpu_inference():
 
     env_docker_context = Environment(
         build=BuildContext(path=this_dir / BUILD_CONTEXT),
-        name="minimal_cpu_inference",
+        name=env_name,
         description="minimal 20.04 py39 cpu inference environment created from a Docker context.",
     )
-    ml_client.environments.create_or_update(env_docker_context)
+    returned_env = ml_client.environments.create_or_update(env_docker_context)
 
     # create the command
     job = command(
@@ -44,7 +44,7 @@ def test_minimal_cpu_inference():
         inputs=dict(
             score="valid_score.py",
         ),
-        environment=f"{env_name}@latest",
+        environment=returned_env,
         compute=os.environ.get("cpu_cluster"),
         display_name="minimal-cpu-inference-example",
         description="A test run of the minimal 20.04 py39 cpu inference curated environment",

assets/inference/environments/minimal-ubuntu20.04-py39-cpu-inference/tests/requirements.txt

@@ -1,3 +1,3 @@
-azure-ai-ml==0.1.0b4
-azure.identity==1.10.0
-requests==2.31.0
+azure-ai-ml==1.2.0
+azure.identity
+requests

assets/inference/environments/minimal-ubuntu22.04-py311-cpu-inference/tests/minimal_inference_test.py

@@ -32,10 +32,10 @@ def test_minimal_cpu_inference():
 
     env_docker_context = Environment(
         build=BuildContext(path=this_dir / BUILD_CONTEXT),
-        name="minimal_cpu_inference",
+        name=env_name,
         description="minimal 22.04 py311 cpu inference environment created from a Docker context.",
     )
-    ml_client.environments.create_or_update(env_docker_context)
+    returned_env = ml_client.environments.create_or_update(env_docker_context)
 
     # create the command
     job = command(
@@ -44,7 +44,7 @@ def test_minimal_cpu_inference():
         inputs=dict(
             score="valid_score.py",
         ),
-        environment=f"{env_name}@latest",
+        environment=returned_env,
         compute=os.environ.get("cpu_cluster"),
         display_name="minimal-cpu-inference-example",
         description="A test run of the minimal 22.04 py311 cpu inference curated environment",

assets/inference/environments/minimal-ubuntu22.04-py311-cpu-inference/tests/requirements.txt

@@ -1,2 +1,2 @@
-azure-ai-ml==0.1.0b4
-azure.identity==1.10.0
+azure-ai-ml==1.2.0
+azure.identity

assets/inference/environments/mlflow-ubuntu20.04-py39-cpu-inference/context/conda_dependencies.yaml

@@ -8,6 +8,4 @@ dependencies:
 - pip:
   - azureml-inference-server-http=={{latest-pypi-version}}
   - azureml-ai-monitoring=={{latest-pypi-version}}
-  - numpy
-  - mlflow
-  - azureml-contrib-services
+  - mlflow

assets/inference/environments/mlflow-ubuntu20.04-py39-cpu-inference/tests/mlflow_test.py

@@ -32,10 +32,10 @@ def test_mlflow_cpu_inference():
 
     env_docker_context = Environment(
         build=BuildContext(path=this_dir / BUILD_CONTEXT),
-        name="mlflow_py39_inference",
+        name=env_name,
         description="mlflow 20.04 py39 cpu inference environment created from a Docker context.",
     )
-    ml_client.environments.create_or_update(env_docker_context)
+    returned_env = ml_client.environments.create_or_update(env_docker_context)
 
     # create the command
     job = command(
@@ -47,7 +47,7 @@ def test_mlflow_cpu_inference():
             score_input="sample_2_0_input.txt",
             model_dir="mlflow_2_0_model_folder"
         ),
-        environment=f"{env_name}@latest",
+        environment=returned_env,
         compute=os.environ.get("cpu_cluster"),
         display_name="mlflow-py39-inference-example",
         description="A test run of the mlflow 20.04 py39 cpu inference curated environment",

assets/models/system/Phi-4/spec.yaml

@@ -40,5 +40,6 @@ tags:
       Standard_ND96asr_v4,
       Standard_ND96amsr_A100_v4
     ]
+  benchmark: "quality"
 
 version: 1

assets/models/system/financial-reports-analysis/spec.yaml

@@ -15,6 +15,7 @@ tags:
   Featured: ""
   languages: "en"
   keywords: ""
+  industry: financial-services
   inference_supported_envs:
     - vllm
   license: mit

assets/models/system/microsoft-rad-dino/description.md

@@ -2,32 +2,22 @@
 
 # Model card for RAD-DINO
 
-<!-- Provide a quick summary of what the model is/does. -->
-
 ## Model description
 
-<!-- Provide a longer summary of what this model is. -->
-
 RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method [DINOv2](https://openreview.net/forum?id=a68SUt6zFt).
 
 RAD-DINO is described in detail in [RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision (F. Pérez-García, H. Sharma, S. Bond-Taylor, et al., 2024)](https://arxiv.org/abs/2401.10815).
 
 - **Developed by:** Microsoft Health Futures
 - **Model type:** Vision transformer
-- **License:** [MSRLA](./LICENSE)
+- **License:** MSRLA
 - **Finetuned from model:** [`dinov2-base`](https://huggingface.co/facebook/dinov2-base)
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 RAD-DINO is shared for research purposes only.
 It is **not meant to be used for clinical practice**.
 
-<!-- ### Downstream use -->
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
 The model is a vision backbone that can be plugged to other models for downstream tasks.
 Some potential uses are:
 
@@ -39,14 +29,8 @@ Some potential uses are:
 
 Fine-tuning RAD-DINO is typically not necessary to obtain good performance in downstream tasks.
 
-<!-- ### Out-of-scope use -->
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
 ## Biases, risks, and limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
 RAD-DINO was trained with data from three countries, therefore it might be biased towards population in the training data.
 Underlying biases of the training datasets may not be well characterized.
 
@@ -122,8 +106,6 @@ torch.Size([1, 768, 37, 37])
 
 ### Training data
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
 We used images from five public, deidentified chest X-ray datasets to train this checkpoint of RAD-DINO.
 
 | Dataset   | Num. images |
@@ -144,8 +126,6 @@ We used 16 nodes with 4 A100 GPUs each, and a batch size of 40 images per GPU.
 
 ### Training procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
 We refer to the [manuscript](https://arxiv.org/abs/2401.10815) for a detailed description of the training procedure.
 
 #### Preprocessing
@@ -156,45 +136,12 @@ All DICOM files were resized using B-spline interpolation so that their shorter
 
 - **Training regime:** fp16 using PyTorch-FSDP mixed-precision.
 
-<!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
 Our evaluation is best described in the [manuscript](https://arxiv.org/abs/2401.10815).
 
-<!-- ### Testing data, factors & metrics
-
-#### Testing Data
-
-[More Information Needed]
-
-#### Factors
-
-[More Information Needed]
-
-#### Metrics
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary -->
-
 ## Environmental impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-<!-- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). -->
-
-<!-- Hardware type: A100 PCIe -->
-<!-- Hours: 1d 16h = 40h -->
-<!-- Cloud provider: Azure -->
-<!-- Region: Italy North -->
-
 - **Hardware type:** NVIDIA A100 GPUs
 - **Hours used:** 40 hours/GPU × 16 nodes × 4 GPUs/node = 2560 GPU-hours
 - **Cloud provider:** Azure
@@ -216,8 +163,6 @@ We used [SimpleITK](https://simpleitk.org/) and [Pydicom](https://pydicom.github
 
 ## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
 **BibTeX:**
 
 ```bibtex
@@ -235,10 +180,11 @@ We used [SimpleITK](https://simpleitk.org/) and [Pydicom](https://pydicom.github
 
 > Pérez-García, F., Sharma, H., Bond-Taylor, S., Bouzid, K., Salvatelli, V., Ilse, M., Bannur, S., Castro, D.C., Schwaighofer, A., Lungren, M.P., Wetscherek, M.T., Codella, N., Hyland, S.L., Alvarez-Valle, J., & Oktay, O. (2024). *RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision*. ArXiv, abs/2401.10815.
 
-## Model card contact
-
-Fernando Pérez-García ([`[email protected]`](mailto:[email protected])).
+### Inference samples
 
+Inference type|Python sample (Notebook)|CLI with YAML
+|--|--|--|
+Real time|<a href="https://aka.ms/azureml-infer-sdk-image-embeddings" target="_blank">image-embeddings-online-endpoint.ipynb</a>|<a href="https://aka.ms/azureml-infer-cli-image-embeddings" target="_blank">image-embeddings-online-endpoint.sh</a>
 
 ### Sample inputs and outputs
 

assets/models/system/microsoft-rad-dino/spec.yaml

@@ -26,4 +26,6 @@ tags:
   license: msrla
   author: Microsoft
   task: embeddings
+  industry: health-and-life-sciences
+  hiddenlayerscanned: "true"
 version: 1

assets/models/system/supply-chain-trade-regulations/spec.yaml

@@ -15,6 +15,7 @@ tags:
   Featured: ""
   languages: "en"
   keywords: ""
+  industry: manufacturing
   inference_supported_envs:
     - vllm
   license: mit

assets/pipelines/environments/mldesigner-minimal/environment.yaml

@@ -9,4 +9,4 @@ image:
     - conda_dependencies.yaml
   publish:
     location: mcr
-    visibility: unlisted
+    visibility: public

assets/pipelines/environments/mldesigner/environment.yaml

@@ -9,4 +9,4 @@ image:
     - conda_dependencies.yaml
   publish:
     location: mcr
-    visibility: unlisted
+    visibility: public

assets/training/automl/environments/ai-ml-automl-gpu/context/Dockerfile

@@ -17,7 +17,7 @@ ENV ENABLE_METADATA=true
 RUN mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
 RUN apt-get update && echo 'success updated apt-get!'
 RUN apt-get install -y --no-install-recommends cmake libboost-dev libboost-system-dev libboost-filesystem-dev
-RUN conda create -p $AZUREML_CONDA_ENVIRONMENT_PATH python=3.9 pip=22.1.2 -y
+RUN conda create -p $AZUREML_CONDA_ENVIRONMENT_PATH python=3.9 pip=22.1.2 conda-forge::tzdata -y
 
 RUN conda run -p $AZUREML_CONDA_ENVIRONMENT_PATH
 

assets/training/finetune_acft_hf_nlp/environments/acpt/context/Dockerfile

@@ -24,4 +24,4 @@ RUN MAX_JOBS=4 pip install flash-attn==2.5.5 --no-build-isolation
 # clean conda and pip caches
 RUN rm -rf ~/.cache/pip
 
-# dummy number to change when needing to force rebuild without changing the definition: 1
+# dummy number to change when needing to force rebuild without changing the definition: 2

assets/training/finetune_acft_image/components/finetune/mmd_od_is/spec.yaml

@@ -1,14 +1,14 @@
 $schema: https://azuremlschemas.azureedge.net/latest/commandComponent.schema.json
 type: command
 
-version: 0.0.19
+version: 0.0.20
 name: mmdetection_image_objectdetection_instancesegmentation_finetune
 display_name: Image Object Detection and Instance Segmentation MMDetection Model Finetune
 description: Component to finetune MMDetection models for image object detection and instance segmentation.
 
 is_deterministic: false
 
-environment: azureml://registries/azureml/environments/acft-mmdetection-image-gpu/versions/46
+environment: azureml://registries/azureml/environments/acft-mmdetection-image-gpu/versions/48
 
 code: ../../../src/finetune