feat:New MARS8 model (#4429)

* feat:New MARS8 model

* feat:New MARS8 model

notebooks/official/generative_ai/cambai_intro_mars8.ipynb

@@ -0,0 +1,686 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "cellView": "form",
+        "id": "9A9NkTRTfo2I"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2026 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "IPprg6Oz0QDs"
+      },
+      "source": [
+        "# Getting Started with Camb AI's Models"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8fK_rdvvx1iZ"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "### Camb AI on Vertex AI\n",
+        "\n",
+        "You can deploy the Camb AI models in your own endpoint.\n",
+        "\n",
+        "### Available Camb AI models\n",
+        "\n",
+        "#### MARS8\n",
+        "\n",
+        "MARS8 is CAMB.AI's latest speech synthesis model. It's aimed towards high quality, multilingual, low latency TTS outputs.\n",
+        "It features voicecloning and fine-grained pronunciation control in over 30 languages.\n",
+        "Deployed on Google Cloud’s Vertex AI Launchpad, it brings latencies of less than 400ms with Blackwell 6000 GPUs, with an architectural focus on speed and voice cloning capabilites.\n",
+        "\n",
+        "#### MARS7\n",
+        "(Multilingual AutoRegressive Speech 7) is the prior generation in CAMB.AI’s MARS series of speech synthesis models. MARS7 creates hyper-realistic, prosodic, multilingual text-to-speech (TTS) outputs, featuring optional voice cloning and fine-grained emotional control. Deployed on Google Cloud’s Vertex AI Launchpad, it brings near real-time latency, with an architectural focus on parameter efficiency and global context understanding.\n",
+        "\n",
+        "## Objective\n",
+        "This notebook shows how to use **Vertex AI API** to deploy the Camb AI models.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "lNZFf33uusH9"
+      },
+      "source": [
+        "## Vertex AI API"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "nwYvaaW25jYS"
+      },
+      "source": [
+        "## Get Started\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0660e339bf3f"
+      },
+      "source": [
+        "### Install required packages\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "754611260f53"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U -q httpx soundfile\n",
+        "! command -v jq >/dev/null 2>&1 || { echo >&2 \"jq is not installed. Installing jq...\"; sudo apt-get update -y && sudo apt-get install -y jq; }"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b9f4c57a43f6"
+      },
+      "source": [
+        "### Restart runtime (Colab only)\n",
+        "\n",
+        "To use the newly installed packages, you must restart the runtime on Google Colab."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "3b9119a60525"
+      },
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "\n",
+        "if \"google.colab\" in sys.modules:\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {
+        "id": "u8Mn7YGTfgpc"
+      },
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "import tempfile\n",
+        "\n",
+        "import IPython.display as ipd\n",
+        "import soundfile as sf\n",
+        "from IPython.display import Audio\n",
+        "\n",
+        "\n",
+        "def display_flac_in_notebook(path_to_flac):\n",
+        "    data, samplerate = sf.read(path_to_flac)\n",
+        "    with tempfile.NamedTemporaryFile(suffix=\".wav\", delete=False) as tmp:\n",
+        "        sf.write(tmp.name, data, samplerate, format=\"WAV\")\n",
+        "        return Audio(filename=tmp.name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e767418763cd"
+      },
+      "source": [
+        "<div class=\"alert alert-block alert-warning\">\n",
+        "<b>⚠️ The kernel is going to restart. Wait until it's finished before continuing to the next step. ⚠️</b>\n",
+        "</div>\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6a5bea26f60f"
+      },
+      "source": [
+        "### Authenticate your notebook environment (Colab only)\n",
+        "\n",
+        "Authenticate your environment on Google Colab.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "c97be6a73155"
+      },
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "\n",
+        "if \"google.colab\" in sys.modules:\n",
+        "\n",
+        "    from google.colab import auth\n",
+        "\n",
+        "    auth.authenticate_user()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2fxZn4SAbxdl"
+      },
+      "source": [
+        "#### Select one of Camb AI models"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "Y8X70FTSbx7U"
+      },
+      "outputs": [],
+      "source": [
+        "PUBLISHER_NAME = \"cambai\"  # @param {type:\"string\"}\n",
+        "PUBLISHER_MODEL_NAME = \"mars8\"\n",
+        "available_regions = [\"us-central1\"]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bpuX3sKtexlK"
+      },
+      "source": [
+        "#### Select a location and a version from the dropdown"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dHl8xW45ex_O"
+      },
+      "outputs": [],
+      "source": [
+        "import ipywidgets as widgets\n",
+        "from IPython.display import display\n",
+        "\n",
+        "dropdown_loc = widgets.Dropdown(\n",
+        "    options=available_regions,\n",
+        "    description=\"Select a location:\",\n",
+        "    font_weight=\"bold\",\n",
+        "    style={\"description_width\": \"initial\"},\n",
+        ")\n",
+        "\n",
+        "\n",
+        "def dropdown_loc_eventhandler(change):\n",
+        "    global LOCATION\n",
+        "    if change[\"type\"] == \"change\" and change[\"name\"] == \"value\":\n",
+        "        LOCATION = change.new\n",
+        "        print(\"Selected:\", change.new)\n",
+        "\n",
+        "\n",
+        "LOCATION = dropdown_loc.value\n",
+        "dropdown_loc.observe(dropdown_loc_eventhandler, names=\"value\")\n",
+        "display(dropdown_loc)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3q58icinBjoK"
+      },
+      "source": [
+        "#### Set Google Cloud project and model information\n",
+        "\n",
+        "To get started using Vertex AI, you must have an existing Google Cloud project and [enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). Learn more about [setting up a project and a development environment](https://cloud.google.com/vertex-ai/docs/start/cloud-environment)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "hltNx33t6cSZ"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "ENDPOINT = f\"https://{LOCATION}-aiplatform.googleapis.com\"\n",
+        "\n",
+        "if not PROJECT_ID or PROJECT_ID == \"[your-project-id]\":\n",
+        "    raise ValueError(\"Please set your PROJECT_ID\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4NAstKRFBt4N"
+      },
+      "source": [
+        "#### Import required libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "QZEFLE6a6bqy"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "import time"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "qjsDpa8jlTRu"
+      },
+      "source": [
+        "### Upload Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "y1R2BRsBlu-k"
+      },
+      "outputs": [],
+      "source": [
+        "UPLOAD_MODEL_PAYLOAD = {\n",
+        "    \"model\": {\n",
+        "        \"displayName\": \"ModelGarden_LaunchPad_Model_\" + time.strftime(\"%Y%m%d-%H%M%S\"),\n",
+        "        \"baseModelSource\": {\n",
+        "            \"modelGardenSource\": {\n",
+        "                \"publicModelName\": f\"publishers/{PUBLISHER_NAME}/models/{PUBLISHER_MODEL_NAME}\",\n",
+        "            }\n",
+        "        },\n",
+        "    }\n",
+        "}\n",
+        "\n",
+        "request = json.dumps(UPLOAD_MODEL_PAYLOAD)\n",
+        "\n",
+        "! curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" {ENDPOINT}/v1beta1/projects/{PROJECT_ID}/locations/{LOCATION}/models:upload -d '{request}'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "V2j0nVGwlf9b"
+      },
+      "source": [
+        "#### Get Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bxwM0GXTmQhh"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_ID = -1  # @param {type: \"number\"}\n",
+        "# copy the model id from the upload in the previous cell into the model id above\n",
+        "! curl -X GET -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" {ENDPOINT}/v1/projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3q3ygq8VlZAp"
+      },
+      "source": [
+        "### Create the endpoint"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "O1ChDOt7mPBQ"
+      },
+      "outputs": [],
+      "source": [
+        "CREATE_ENDPOINT_PAYLOAD = {\n",
+        "    \"displayName\": \"ModelGarden_LaunchPad_Endpoint_\" + time.strftime(\"%Y%m%d-%H%M%S\"),\n",
+        "}\n",
+        "\n",
+        "request = json.dumps(CREATE_ENDPOINT_PAYLOAD)\n",
+        "\n",
+        "! curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" {ENDPOINT}/v1/projects/{PROJECT_ID}/locations/{LOCATION}/endpoints -d '{request}'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "GuMZCdhmlpCE"
+      },
+      "source": [
+        "#### Get Endpoint"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "tHq_cLT6mPp_"
+      },
+      "outputs": [],
+      "source": [
+        "ENDPOINT_ID = -1  # @param {type: \"number\"}\n",
+        "# copy the endpoint id from the create endpoint in the previous cell into the endpoint id above\n",
+        "! curl -X GET -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" {ENDPOINT}/v1/projects/{PROJECT_ID}/locations/{LOCATION}/endpoints/{ENDPOINT_ID}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "G0amEPXolbP7"
+      },
+      "source": [
+        "### Deploy Model"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {
+        "id": "Ucj-Xa-fpGrg"
+      },
+      "outputs": [],
+      "source": [
+        "MACHINE_TYPE = \"g4-standard-48\"  # @param {type: \"string\"}\n",
+        "ACCELERATOR_TYPE = \"NVIDIA_RTX_PRO_6000\"  # @param {type: \"string\"}\n",
+        "ACCELERATOR_COUNT = 1  # @param {type: \"number\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "VGTyCQQhlrAR"
+      },
+      "outputs": [],
+      "source": [
+        "# Try CURL, if it fails, use stubby command in the next cell.\n",
+        "DEPLOY_PAYLOAD = {\n",
+        "    \"deployedModel\": {\n",
+        "        \"model\": f\"projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}\",\n",
+        "        \"displayName\": \"ModelGarden_LaunchPad_DeployedModel_\"\n",
+        "        + time.strftime(\"%Y%m%d-%H%M%S\"),\n",
+        "        \"dedicatedResources\": {\n",
+        "            \"machineSpec\": {\n",
+        "                \"machineType\": MACHINE_TYPE,\n",
+        "                \"acceleratorType\": ACCELERATOR_TYPE,\n",
+        "                \"acceleratorCount\": ACCELERATOR_COUNT,\n",
+        "            },\n",
+        "            \"minReplicaCount\": 1,\n",
+        "            \"maxReplicaCount\": 1,\n",
+        "        },\n",
+        "    },\n",
+        "    \"trafficSplit\": {\"0\": 100},\n",
+        "}\n",
+        "\n",
+        "request = json.dumps(DEPLOY_PAYLOAD)\n",
+        "print(\"Request payload to Deploy Model:\")\n",
+        "print(json.dumps(DEPLOY_PAYLOAD, indent=2))\n",
+        "print(\"\\nResult:\")\n",
+        "! curl -X POST -H \"Authorization: Bearer $(gcloud auth print-access-token)\" -H \"Content-Type: application/json\" {ENDPOINT}/v1/projects/{PROJECT_ID}/locations/{LOCATION}/endpoints/{ENDPOINT_ID}:deployModel -d '{request}'"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5ahw-uFjCAbo"
+      },
+      "source": [
+        "### Audio generation"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "61107099357a"
+      },
+      "source": [
+        "#### Unary call\n",
+        "\n",
+        "Sends a POST request to the specified API endpoint to get a response from the model for a joke using the provided payload."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "id": "fqq3G6fnDxzR"
+      },
+      "outputs": [],
+      "source": [
+        "# load in env variables\n",
+        "import os\n",
+        "\n",
+        "os.environ[\"ENDPOINT\"] = ENDPOINT\n",
+        "os.environ[\"PROJECT_ID\"] = PROJECT_ID\n",
+        "os.environ[\"LOCATION\"] = LOCATION\n",
+        "os.environ[\"ENDPOINT_ID\"] = str(ENDPOINT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "_I8EU083e1jy"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash\n",
+        "# download the ref file\n",
+        "curl -o ref.flac \"https://storage.googleapis.com/cambai-prod-public/public/ref.flac\"\n",
+        "# base64 encode the ref and save the payload:\n",
+        "b64=$(base64 -i ref.flac | tr -d '\\n')\n",
+        "cat > body.json <<EOF\n",
+        "{\n",
+        "  \"text\": \"The quick brown fox jumps over the lazy dog.\",\n",
+        "  \"reference_audio\": \"$b64\",\n",
+        "  \"reference_language\": \"en-us\",\n",
+        "  \"output_duration\": null,\n",
+        "  \"language\": \"en-us\"\n",
+        "}\n",
+        "EOF\n",
+        "\n",
+        "# send the request, saving the output to a .flac file:\n",
+        "curl -X POST ${ENDPOINT}/v1/projects/${PROJECT_ID}/locations/${LOCATION}/endpoints/${ENDPOINT_ID}:rawPredict \\\n",
+        "    -H \"Content-Type: application/json\" \\\n",
+        "    -H \"Authorization: Bearer $(gcloud auth print-access-token)\" \\\n",
+        "    -d @body.json > output.flac\n",
+        "# NOTE: the first request to a model endpoint pod might be slow as the model compiles kernels"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "XBMjtnUjflpz"
+      },
+      "outputs": [],
+      "source": [
+        "# play the output audio\n",
+        "ipd.Audio(\"output.flac\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "GhUFddWsDxzR"
+      },
+      "source": [
+        "#### Unary Call with Vertex SDK"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 22,
+      "metadata": {
+        "id": "FJuOQuS1DxzS"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "from pathlib import Path\n",
+        "\n",
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "aiplatform.init(project=PROJECT_ID, location=LOCATION)\n",
+        "endpoint = aiplatform.Endpoint(endpoint_name=str(ENDPOINT_ID))\n",
+        "\n",
+        "# encode reference audio as base64 string:\n",
+        "file_path = \"ref.flac\"\n",
+        "encoded_str = base64.b64encode(Path(file_path).read_bytes()).decode(\"utf-8\")\n",
+        "\n",
+        "# define payload:\n",
+        "data = {\n",
+        "    \"text\": \"The quick brown fox jumps over the lazy dog.\",\n",
+        "    \"language\": \"en-us\",\n",
+        "    \"output_duration\": None,\n",
+        "    \"reference_language\": \"en-us\",\n",
+        "    \"reference_audio\": encoded_str,\n",
+        "}\n",
+        "\n",
+        "prediction = []\n",
+        "for chunk in endpoint.raw_predict(\n",
+        "    body=json.dumps(data).encode(\"utf-8\"),\n",
+        "    headers={\"Content-Type\": \"application/json\"},\n",
+        "    use_dedicated_endpoint=True,\n",
+        "):\n",
+        "    if chunk:\n",
+        "        prediction.append(chunk)\n",
+        "full_audio_bytes = b\"\".join(prediction)\n",
+        "# save output to a local file\n",
+        "with open(\"output.flac\", \"wb\") as file:\n",
+        "    file.write(full_audio_bytes)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Oo_NeG4LgJsg"
+      },
+      "outputs": [],
+      "source": [
+        "# play the output audio\n",
+        "ipd.Audio(\"output.flac\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WmQ-CJs4gbPI"
+      },
+      "source": [
+        "#### Unary call with streaming"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gGfJjOlWgYsZ"
+      },
+      "outputs": [],
+      "source": [
+        "import base64\n",
+        "import subprocess\n",
+        "import time\n",
+        "from pathlib import Path\n",
+        "\n",
+        "import httpx\n",
+        "\n",
+        "url = f\"https://{LOCATION}-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/{LOCATION}/endpoints/{ENDPOINT_ID}:rawPredict\"\n",
+        "# authenticate\n",
+        "res = subprocess.run([\"gcloud\", \"auth\", \"print-access-token\"], capture_output=True)\n",
+        "access_token = res.stdout.decode(\"utf-8\").strip()\n",
+        "headers = {\"Authorization\": f\"Bearer {access_token}\", \"Accept\": \"text/event-stream\"}\n",
+        "# Define reference audio to use for cloning (base64 encoded)\n",
+        "file_path = \"ref.flac\"\n",
+        "encoded_str = base64.b64encode(Path(file_path).read_bytes()).decode(\"utf-8\")\n",
+        "\n",
+        "data = {\n",
+        "    \"text\": \"そしてカールソンは、あの軽やかなスケーティングで、まるで幽霊のようにニュートラルゾーンを縫うように駆け抜ける.\",  # text to synthesize\n",
+        "    \"language\": \"ja-jp\",\n",
+        "    \"output_duration\": None,\n",
+        "    \"reference_language\": \"en-us\",\n",
+        "    \"reference_audio\": encoded_str,\n",
+        "}\n",
+        "\n",
+        "st = time.time()\n",
+        "\n",
+        "prediction = []\n",
+        "wavs = []\n",
+        "with httpx.stream(\"POST\", url, headers=headers, json=data, timeout=300) as r:\n",
+        "    print(r.status_code, r.headers)\n",
+        "    dt = time.time()\n",
+        "    for chunk in r.iter_bytes(4096 * 16):\n",
+        "        if chunk:\n",
+        "            # each chunk is a bytes object of the next audio chunk.\n",
+        "            # If you want you can render the output piece by piece, or use an async receiver.\n",
+        "            print(\n",
+        "                f\"Received chunk of size {len(chunk)} at {time.time() - st:.2f}s. w/o network delay: {time.time() - dt:.2f}s\"\n",
+        "            )\n",
+        "            prediction.append(chunk)\n",
+        "et = time.time()\n",
+        "full_audio_bytes = b\"\".join(prediction)\n",
+        "# Check the response status code\n",
+        "if r.status_code == 200:\n",
+        "    print(f\"Request successful! Took {et-st:.2f}s\")\n",
+        "else:\n",
+        "    print(\"Request failed with status code\", r.status_code)\n",
+        "# display or save full output\n",
+        "with open(\"output.flac\", \"wb\") as file:\n",
+        "    file.write(full_audio_bytes)\n",
+        "ipd.Audio(full_audio_bytes)"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "cambai_intro_mars8.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}