---
title: "TDM for ORCA VLMs"
slug: "tdm-for-orca-vlms"
description: "Learn to prepare and train specialized models in TDM for ORCA VLMs, enhancing document processing with effective training data management."
updated: 2026-10-14T19:43:03Z
published: 2026-10-14T19:43:03Z
canonical: "help.hyperscience.ai/tdm-for-orca-vlms"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://help.hyperscience.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# TDM for ORCA VLMs

Training Data Management (TDM) allows you to train and improve models by working directly with the training data, or Ground truth, obtained from each document in the Training Set.

For ORCA VLMs, use TDM to:

- prepare and annotate documents,
- train a specialized model on top of an ORCA base model,
- evaluate the resulting candidate,
- and manage the model versions associated with your use case.

TDM is where you add representative examples and confirm the correct field values that the specialized model should learn from. Training creates a candidate model without changing the base model; after you evaluate and deploy the candidate, it becomes the live specialized model used for document processing, depending on your flow settings. In this article, you’ll learn how to prepare and train a specialized model in TDM for ORCA VLMs.

## Prerequisites

Before you begin, make sure that:

- You have the **View Training Data** permission. Actions that add, annotate, or change training data also require the applicable edit permissions. See [Permission Groups](/v44/docs/permission-groups).
- A locked Semi-structured Layout with fields and notes is associated with the flow that uses ORCA.
  - ORCA VLM field extraction does not train on table fields. Learn how to configure the layout for ORCA in [Creating Semi-structured Layouts](/v44/docs/creating-semi-structured-layouts).
- A Model Definition exists for your scope, task, and model type. The model definition links the layout with its training data and model versions. See [Model Definitions](/v44/docs/model-definitions) for more information.

> [!NOTE]
> Base model requirement
> 
> - You can prepare and manage training data before installing a base model.
> - To train a specialized model, at least one compatible ORCA base model must be installed.
> - In v43.2 and later, the **ORCA 2** base model is available in addition to ORCA 1.0. Learn more in [ORCA Vision Language Models](/v44/docs/orca-vlms) and [Installing ORCA VLMs](/v44/docs/installing-orca-vlms).

## Access TDM for ORCA VLMs

To access TDM for ORCA VLMs:

1. Go to **Models**.
2. Open the **VLM Field Extraction** tab.
3. Select the model definition associated with your layout.

The model details page contains three tabs:

| Tab | Use it to |
| --- | --- |
| **Overview** | Check the live or candidate models, training readiness, latest base model, training data health, and Projected Automation. |
| **Training Data** | Add, find, annotate, tag, export, and manage the documents used as ground truth. |
| **History** | Review base models or specialized model versions, copy UUIDs, deploy compatible versions, and manage archived models. |

The page-level **Actions** menu contains model-definition actions such as **Deploy candidate model**, **Reject candidate model**, **Train model**, **Upload Documents**, **Export**, and **Import**. The available actions depend on the model state, your permissions, and whether training requirements are met.

![TDM for VLM Extraction tabs](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/vlm_tabs.png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

Do not confuse the page-level menu with the **Actions** menu in the Training Data table, which applies to selected training documents.

> [!NOTE]
> Opening a model definition for the first time
> 
> When you open a model definition, you land on the **Overview** tab. Before you add training data, it shows only the **Live** base model summary, labeled **Pre-trained**, and a Training summary of **Reqs not met**. This is expected — start in the **Training Data** tab to upload and annotate documents. The Overview tab fills in as your models training progress.
> 
> ![](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(285).png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

## Specialization process

Training a specialized model follows five stages:

- Prepare training data,
- Annotate training data,
- Train the model,
- Evaluate the candidate,
- and deploy the candidate.

The sections below describe where each stage happens in TDM. For the end-to-end process, including dataset guidance and validating a Deployed Model, see [Training a Specialized Model](/v44/docs/training-a-specialized-model).

## Training Data tab

The **Training Data** tab lists the documents associated with the model definition. Use this tab to build a representative dataset and maintain the training data for future training runs. Learn how to upload and manage training data by following the steps described in the next sections or see the interactive walkthrough below.

[Explore the Training Data tab](https://app.storylane.io/demo/vhjqeeyokupq?embed=inline)

### Upload documents

1. Open the page-level **Actions** menu.
2. Select **Upload Documents**.
3. Add the documents you want to use as training examples and complete the upload.
4. Wait for document loading to finish before annotating or exporting those documents.

![Page-level actions in TDM for VLM Extraction](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/page-level_actions.png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

For guidance on choosing representative documents and the dataset requirements (page limits, uniqueness, and minimum counts), see [Training a Specialized Model](/v44/docs/training-a-specialized-model).

### Training data table

#### Find and filter training data

Once uploaded, the training data can be filtered by **Usage Rule**, **Source**, **Sched. deletion**, or **Tags**.

![Training data table filters](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/training_data_table_filters.png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

The **Usage rule** indicates how the system uses each document for training:

| **Value** | Description |
| --- | --- |
| **Auto** | The system uses the document to train the model until it is scheduled for deletion, based on the PII Data Deletion settings for your instance. |
| **Always** | The system always uses the document to train the model. |
| **Never** | The system never uses the document in future model training, even if it has not been deleted as part of the PII Data Deletion. |
| **Loading** | The system is pre-processing the document and preparing it for annotation. |
| **Ready to annotate** | The document has been uploaded successfully, but has not been annotated yet. The system does not include it in training until you annotate it. |

Open the table-options menu next to **Filter** to manage tags or choose which columns appear.

![Additional options - manage tags and manage columns in the Training Data table](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/additional_options.png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

#### Tag training documents

Tags help you categorize, filter, and find training documents:

- To tag one document, hover over its **Tags** cell and select **+**.
- To tag multiple documents, select them and choose **Actions** > **Edit tags**.
- To create, rename, or delete available tags, open the table-options menu and select **Manage tags****...**.

The system automatically adds tags that are included in imported training data. Tag names cannot contain spaces or semicolons. The system replaces both with underscores. The system also automatically deletes unassigned tags. Tags are case-insensitive, and the system normalizes them to uppercase.

> [!NOTE]
> In v43.2 and later, the Tags column shortens long tag names with an ellipsis.
> 
> Hover over a shortened tag to see its full name.

![Tags](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/tags.png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

#### Export training data as CSV

1. To export a subset of the training data, select its rows in the Training Data table.
  - To export the entire table, do not select individual rows.
2. Open the Training Data table’s **Actions** menu.
3. Under **Export**, select **All training data as CSV** or **Selected rows as CSV**.
4. When the export is ready, use the download link in the **Notifications** menu.

An export option is unavailable if it would include documents that are still loading. Hover over an unavailable option to see why. Wait for loading to finish, or select only ready rows.

> [!NOTE]
> CSV contents
> 
> Training data CSV exports use status names, include layout names with layout-version identifiers, and contain the columns relevant to the model type.

### Annotate training documents

Annotation establishes the ground truth that the specialized model learns from. Review every supported field against the source document, even when the system has pre-populated a value.

1. In the **Training Data** tab, find a document that is ready to annotate.
2. Select **Annotate**, or **Edit annotations** for a document that has already been annotated.
  - You can also open the annotation view by selecting the document’s **Document ID** link.
3. Select a field and identify the text that represents its correct value.
4. Review the field’s location and transcription. Correct the transcription to match the document exactly.
5. Repeat for the remaining fields, and then click **Save**.

> [!NOTE]
> Text Segmentation
> 
> - For faster and easier annotation, use the dotted lines around each value.
> - These boxes represent the text segmentation in the document. To learn more, see [Text Segmentation](/v44/docs/text-segmentation).
> - Drag and drop your cursor to create a Bounding Box.
> 
> ![Text segmentation boxes shown as dotted lines around values in a document](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/segmentation(1).png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)

While annotating:

- Navigate between documents by selecting the left or right arrow (![Left and right navigation arrows](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/image(241).png?sv=2026-02-06&spr=https&st=2026-11-04T07%3A45%3A19Z&se=2026-11-04T08%3A45%3A19Z&sr=c&sp=r&sig=Hcc9LUU3lNPCURpVf1F9cKDP%2FjJZJ%2Bu5qlgv%2BZ3Mp8E%3D)).
- Documents appear in the order you’ve sorted them in the Training Data table.

To learn more about the annotation experience in TDM for ORCA VLMs, see the interactive walkthrough below.

[Annotate ORCA VLM training data](https://app.storylane.io/demo/gronggwcmzyx?embed=inline)

> [!NOTE]
> Automatically transcribed fields
> 
> - The application pre-populates some fields to reduce manual typing.
> - Treat these values as suggestions:
>   - review each one and correct it before completing the annotation.
> 
> In v43.2 and later, moving or resizing a field’s bounding box updates its transcription with the text segments inside the box. Review the updated value and correct it if necessary.

For guidelines on entering values so that they provide consistent ground truth (exact transcription, reading order, and multi-page fields), see [Training a Specialized Model](/v44/docs/training-a-specialized-model).

## Overview tab

### Check training readiness

After annotating, check the **Training summary** on the **Overview** tab to see whether the model is ready to train.

[Explore the ORCA VLM Overview tab](https://app.storylane.io/demo/pfq6c8orfgpx?embed=inline)

| Field or status | Description |
| --- | --- |
| **Ready to train** | At least one compatible base model is installed and has enough eligible annotated documents. |
| **Reqs not met** | No compatible base model is installed, or the training data requirement has not been met. Hover over the information icon to identify the unmet requirement. |
| **Training in progress** | Model training is running. |
| **Training failed** | The most recent training run failed. |
| **Required Documents** | Before the minimum is met, shows the number of eligible annotated documents available out of the 120 required for ORCA VLM training. |
| **Total Documents** | After the minimum is met, replaces Required Documents and shows the total number of eligible annotated documents. |
| **Base Model** | The base model used by the latest training (e.g., ORCA 1.0 or ORCA 2). Before a training run has selected a base model, the value is **N/A**. |

## Train a specialized model

Training uses annotated documents to create a specialized model on top of an installed ORCA base model. It does not modify the base model.

1. Confirm that the Training summary shows **Ready to train**.
2. Open the page-level **Actions** menu and select **Train model**.

- If one eligible base model is installed, the system schedules training with that model.
- If multiple base models are installed, select an eligible model in the **Select model** dialog, and then select **Train model**.
- You cannot select a base model that does not have enough eligible documents.

> [!NOTE]
> Different base models provide different capabilities
> 
> The specialized models inherit the capabilities of the base model selected for the training run. In v43.2 and later, you can train on the **ORCA 2** base model, which is available in addition to ORCA 1.0.

## Evaluate and deploy the candidate

After training completes, a candidate model appears on the **Overview** tab, alongside the live model’s summary card if one exists. Review the candidate’s summary and its Projected Automation. Decide whether you want to deploy or reject it from the page-level **Actions** menu or the **History** tab.

For the complete guidance on evaluating a candidate, deploying it, and validating the deployed model with test documents, see [Training a Specialized Model](/v44/docs/training-a-specialized-model).

> [!NOTE]
> Action notifications
> 
> The application displays success notifications when model actions are completed. These actions include deploying or undeploying a model, rejecting a candidate, scheduling or canceling training, and exporting a model.

## History tab

### Manage model versions

The **History** tab lists the base models and specialized model versions associated with the model definition. Available actions depend on each model’s source, state, compatibility, and your permissions.

[Explore ORCA VLM Model History](https://app.storylane.io/demo/3j5murpr0s59?embed=popup)

| Column | Description |
| --- | --- |
| **Name** | The model name. Specialized-model names can contain up to 128 characters. Hover over a shortened name to see it in full. |
| **UUID** | The model version’s unique identifier. This column is hidden by default and displays the first eight characters when enabled. |
| **State** | Live, Candidate, Inactive, or Not installed. Archived models appear in the Archive view. |
| **Compatibility** | The model’s compatibility with Hyperscience versions. Orange indicates the current version, green one version ahead, and blue two versions ahead. |
| **Layout version** | The layout version used to train a specialized model. Base-model rows show n/a. |
| **Source** | Internal, Uploaded, or Base. |
| **Base Model** | The base model used to create the specialized model. |
| **Proj auto** | The projected automation and margin of error at the selected Test Target Accuracy. Rows without projection data show n/a. |
| **Docs trained** | The number of documents used to train the specialized model. Base-model rows show n/a. |
| **Actions** | The actions available for the model version. A row can show an inline Deploy or Install action and additional actions in its three-dot menu. |

### Show and copy a model UUID

1. In the **History** tab, open the table-options menu next to **Filter**.
2. Select **Manage columns...**.
3. Select **UUID**, and then select **Save**.
4. Hover over a shortened UUID to see the full value, or select the UUID to copy it.

### Resolve a missing base model

If a specialized model depends on a base model that is not installed, the specialized model is unavailable for deployment, and its row is grayed out. You can still download or archive the specialized model.

1. In the **History** tab, find the required base-model row with the state **Not installed**.
2. Select **Install**. **Administration > Assets** opens in a new tab.
3. Install the base model, and then return to the model details page. To learn more, see [Installing ORCA VLMs](/v44/docs/installing-orca-vlms).

### Archive and unarchive specialized models

Archive specialized model versions that you no longer actively use. Base models cannot be archived from the History tab. Undeploy a Live model or reject a Candidate model before archiving it.

1. In the **History** tab, open the specialized model’s three-dot menu.
2. Select **Archive** and confirm the action.
3. To see archived models, open the table-options menu and select **View Archive**.
4. To restore a model, open its three-dot menu and select **Unarchive**.
5. Select **View Active** to return to active models.

## Next steps

For the end-to-end specialization workflow — dataset requirements, annotation guidelines, and validating a deployed model with held-out test documents — see [Training a Specialized Model](/v44/docs/training-a-specialized-model).

A tool used to annotate, manage, import, and export training documents. It is also used to train models by working directly with the training data (“ground truth”) obtained from each document in the training set.

Manually annotated data used to train our machine learning models. We use a subset of this data to assess the performance of your models

A dataset used to teach the system how to recognize and extract information. It includes documents with labeled fields so the system can learn from real examples.

A foundational model that provides core general-purpose capabilities and is not directly trained on customer-specific examples. Use-case specialization is achieved through additional training on top of the base model using customer-specific data.

A configuration within Hyperscience designed to process documents where fields and table cells are present, but their positions can vary among documents. Unlike Structured layouts, Semi-structured layouts do not rely on fixed field locations. Instead, a model is trained to find the fields and cells based on provided training examples.

A configuration object used to manage Vision Language Models (VLMs). Model definitions define a model's scope, task, compatibility, deployment status, and associated model versions. Learn more in [Model Definitions](https://help.hyperscience.ai/latest/docs/model-definitions).

The predicted automation based on the desired target accuracy. The projection is derived from the model’s training data. The system automatically ensures that the same data is not used for both projections and training.

A trained machine learning model that has been activated within Hyperscience to process documents in real time. Once deployed, the model is live and is used to process documents—classifying them, locating fields, and extracting data based on what it has learned.

A setting that allows you to remove PII from submissions to enhance security or comply with organizational policies. In Hyperscience, enabling this feature deletes all document image data, including extracted data and the original and processed images.

The process of partitioning an image into regions containing text. It is the first step of downstream processing tasks such as Classification and Transcription.

A rectangular subregion of a given page that specifies the location of text to be processed downstream or to be displayed to the user.