Merge branch 'main' into distillation-connection-changes

assets/models/system/TamGen/spec.yaml

@@ -11,7 +11,7 @@ properties:
 
 tags:
   task: protein-design
-  industry: health-and-life-sciences
+  disable-batch: "true"
   Preview: ""
   inference_supported_envs:
   license: mit

assets/models/system/mattersim/description.md

@@ -30,8 +30,8 @@ Please refer to the [MatterSim](https://arxiv.org/abs/2405.04967) manuscript for
 
 ### Model Sources
 
-- **Repository:** https://github.com/microsoft/mattersim
-- **Paper:** https://arxiv.org/abs/2405.04967
+- **Repository:** <https://github.com/microsoft/mattersim>
+- **Paper:** <https://arxiv.org/abs/2405.04967>
 
 ### Available Models
 
@@ -96,7 +96,6 @@ We evaluate the performance by computing the mean absolute errors (MAEs) of ener
 </p>
 where N is the number of structures in the same dataset, <img src="https://latex.codecogs.com/svg.image?\inline&space;&space;N_{at}^{(i)}"> is the number of atoms in the i-th structure and E, F and S represent ground-truth energy, forces and stress, respectively.
 
-
 ### Results
 
 | Dataset              | Dataset Size | MAE               | mattersim-v1.0.0-1M | mattersim-v1.0.0-5M |
@@ -120,7 +119,30 @@ where N is the number of structures in the same dataset, <img src="https://latex
 |                      |              | Forces [eV/<img src="https://latex.codecogs.com/svg.latex?\AA" alt="\AA">] | 0.933        | 0.824        |
 |                      |              | Stress [GPa]      | 2.065        | 1.999        |
 
-## Technical Specifications [optional]
+## Intended Uses
+
+The MatterSim model is intended for property predictions of materials.
+
+### Direct Use
+
+The model is used for materials simulation and property prediciton tasks. An interface to atomic simulation environment is provided. Examples of direct usages include but not limited to
+
+- Direct prediction of energy, forces and stress of a given materials
+- Phonon prediction using finite difference
+- Molecular dynamics
+
+### Out-of-Scope Use
+
+The model only supports atomistic simulations of materials and molecules. Any attempt and interpretation beyond that should be avoided.
+The model does not support generation of new materials as it is designed for materials simulation and property prediction only.
+The model is intended for research and experimental purposes. Further testing/development are needed before considering its application in real-world scenarios.
+
+## Contact Model Provider
+
+- Han Yang (<[email protected]>)
+- Ziheng Lu (<[email protected]>)
+
+## Technical Specifications
 
 ### Model Architecture and Objective
 
@@ -133,6 +155,7 @@ The checkpoints released in this repository are those trained on an internal imp
 ## Citation
 
 **BibTeX:**
+
 ```
 @article{yang2024mattersim,
       title={MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures},
@@ -146,20 +169,6 @@ The checkpoints released in this repository are those trained on an internal imp
 }
 ```
 
-## Model Card Contact
-
-- Han Yang ([email protected])
-- Ziheng Lu ([email protected])
-
-
-
-
-### Out-of-Scope Use
-
-The model only supports atomistic simulations of materials and molecules. Any attempt and interpretation beyond that should be avoided.
-The model does not support generation of new materials as it is designed for materials simulation and property prediction only.
-The model is intended for research and experimental purposes. Further testing/development are needed before considering its application in real-world scenarios.
-
 ## Bias, Risks, and Limitations
 
 The current model has relatively low accuracy for organic polymeric systems.

assets/models/system/mattersim/spec.yaml

@@ -11,7 +11,7 @@ properties:
 
 tags:
   task: materials-design
-  industry: health-and-life-sciences
+  disable-batch: "true"
   Preview: ""
   license: mit
   author: Microsoft

assets/training/finetune_acft_hf_nlp/components/pipeline_components/nlp_multiclass/spec.yaml

@@ -271,4 +271,13 @@ jobs:
       preprocess_output: ${{parent.jobs.preprocess.outputs.output_dir}}
     outputs:
       pytorch_model_folder: ${{parent.outputs.pytorch_model_folder_finetune}}
+  text_classification_model_converter:
+    type: command
+    component: azureml:ft_nlp_model_converter:0.0.66
+    compute: ${{parent.inputs.compute_finetune}}
+    resources:
+      instance_type: ${{parent.inputs.instance_type_finetune}}
+    inputs:
+      model_path: ${{parent.jobs.finetune.outputs.pytorch_model_folder}}
+    outputs:
       mlflow_model_folder: ${{parent.outputs.mlflow_model_folder_finetune}}

assets/training/finetune_acft_hf_nlp/components/pipeline_components/nlp_multilabel/spec.yaml

@@ -271,4 +271,13 @@ jobs:
       preprocess_output: ${{parent.jobs.preprocess.outputs.output_dir}}
     outputs:
       pytorch_model_folder: ${{parent.outputs.pytorch_model_folder_finetune}}
+  text_classification_model_converter:
+    type: command
+    component: azureml:ft_nlp_model_converter:0.0.66
+    compute: ${{parent.inputs.compute_finetune}}
+    resources:
+      instance_type: ${{parent.inputs.instance_type_finetune}}
+    inputs:
+      model_path: ${{parent.jobs.finetune.outputs.pytorch_model_folder}}
+    outputs:
       mlflow_model_folder: ${{parent.outputs.mlflow_model_folder_finetune}}

assets/training/finetune_acft_hf_nlp/components/preprocess/nlp_multiclass/spec.yaml

@@ -1,6 +1,6 @@
 $schema: https://azuremlschemas.azureedge.net/latest/commandComponent.schema.json
 name: nlp_multiclass_datapreprocessing
-version: 0.0.2
+version: 0.0.3
 type: command
 
 is_deterministic: True