|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "metadata": {}, |
| 6 | + "source": [ |
| 7 | + "# Orb Model Card\n", |
| 8 | + "\n", |
| 9 | + "## Details\n", |
| 10 | + "\n", |
| 11 | + "### Description\n", |
| 12 | + "\n", |
| 13 | + "Orb is a universal interatomic potential for atomistic modelling of materials. Orb models are 3-6 times faster than existing universal potentials, stable under simulation for a range of out of distribution materials and, upon release, represented a 31% reduction in error over other methods on the Matbench Discovery benchmark.\n", |
| 14 | + "\n", |
| 15 | + "\n", |
| 16 | + "### Repo\n", |
| 17 | + "\n", |
| 18 | + "Orb is an open source model, made available under the license conditions found in this model card. Miore details can be found in the [orb-models github repo](https://github.com/orbital-materials/orb-models)\n", |
| 19 | + "\n", |
| 20 | + "## Usage:\n", |
| 21 | + "\n", |
| 22 | + "\n", |
| 23 | + "### Capabities:\n", |
| 24 | + "\n", |
| 25 | + "Calculate energies, forces & stresses of atomic systems.\n", |
| 26 | + "\n", |
| 27 | + "### Intended Tasks\n", |
| 28 | + "\n", |
| 29 | + "Single point calculations, geometry optimisations, molecular dynamics simulations, and any other calculation involving energies, forces & stresses.\n", |
| 30 | + "\n", |
| 31 | + "### Inputs/outputs:\n", |
| 32 | + "\n", |
| 33 | + "#### Inputs\n", |
| 34 | + "Valid input mime types\n", |
| 35 | + "- `application/octet-stream`\n", |
| 36 | + "\n", |
| 37 | + "The input should be a binaryb stream from a valid CIF file.\n", |
| 38 | + "\n", |
| 39 | + "#### Outputs\n", |
| 40 | + "Valid output mime types\n", |
| 41 | + "- `application/json`\n", |
| 42 | + "\n", |
| 43 | + "The output is a json dictionary with the following keys:\n", |
| 44 | + "\n", |
| 45 | + "| Key | Description | Data Type |\n", |
| 46 | + "|------------|----------------------|-----------|\n", |
| 47 | + "| energy | Scalar. The final energy of the system. | Integer |\n", |
| 48 | + "| forces | Matrix. Dimensions of nx3 where n is number of atoms. Represents the force on each individual atom. | Continuous(float) |\n", |
| 49 | + "| stress | 6-dimensional vector in Voigt notation. Represents the stress of the system. | Continuous(float) |\n", |
| 50 | + "\n", |
| 51 | + "\n", |
| 52 | + "## Use Cases\n", |
| 53 | + "\n", |
| 54 | + "We have provided an example workflow based on the Zeolite 4A.\n", |
| 55 | + "\n", |
| 56 | + "The sample input data can be found in the [repo](https://github.com/orbital-materials/orb-models/blob/main/azure/examples/4A.cif)\n", |
| 57 | + "\n", |
| 58 | + "\n", |
| 59 | + "<span style=\"color:red\">The code for inference can be seen below.\n", |
| 60 | + "We need to finalizer how the model can be used from azure</span>\n", |
| 61 | + "\n", |
| 62 | + "The example output from the data can also be found in the [repo](https://github.com/orbital-materials/orb-models/blob/main/azure/examples/output.json)\n", |
| 63 | + "\n", |
| 64 | + "\n", |
| 65 | + "\n", |
| 66 | + "\n" |
| 67 | + ] |
| 68 | + }, |
| 69 | + { |
| 70 | + "cell_type": "code", |
| 71 | + "execution_count": null, |
| 72 | + "metadata": {}, |
| 73 | + "outputs": [], |
| 74 | + "source": [ |
| 75 | + "import requests\n", |
| 76 | + "import json\n", |
| 77 | + "\n", |
| 78 | + "file_name = \"4A.cif\"\n", |
| 79 | + "output_file_name = \"4A_output.json\"\n", |
| 80 | + "url = \"\"\n", |
| 81 | + "with open(file_name, 'rb') as file:\n", |
| 82 | + " # Read the file as binary\n", |
| 83 | + " body = file.read()\n", |
| 84 | + "# Create the signed request with the file body\n", |
| 85 | + "\n", |
| 86 | + "\n", |
| 87 | + "response = requests.request(\n", |
| 88 | + " method='POST',\n", |
| 89 | + " url=url,\n", |
| 90 | + " headers={'Content-Type': 'application/octet-stream'},\n", |
| 91 | + " data=body\n", |
| 92 | + " )\n", |
| 93 | + "with open(output_file_name, 'w') as file:\n", |
| 94 | + " json.dump(response.json(), file)\n" |
| 95 | + ] |
| 96 | + } |
| 97 | + ], |
| 98 | + "metadata": { |
| 99 | + "instance_type": "ml.t3.medium", |
| 100 | + "kernelspec": { |
| 101 | + "display_name": "core", |
| 102 | + "language": "python", |
| 103 | + "name": "python3" |
| 104 | + }, |
| 105 | + "language_info": { |
| 106 | + "codemirror_mode": { |
| 107 | + "name": "ipython", |
| 108 | + "version": 3 |
| 109 | + }, |
| 110 | + "file_extension": ".py", |
| 111 | + "mimetype": "text/x-python", |
| 112 | + "name": "python", |
| 113 | + "nbconvert_exporter": "python", |
| 114 | + "pygments_lexer": "ipython3", |
| 115 | + "version": "3.11.5" |
| 116 | + } |
| 117 | + }, |
| 118 | + "nbformat": 4, |
| 119 | + "nbformat_minor": 4 |
| 120 | +} |
0 commit comments