--- title: "Training a Specialized Model" slug: "training-a-specialized-model" description: "Train a specialized model on top of ORCA base models to enhance document extraction accuracy and automation tailored to your unique data needs." updated: 2026-10-14T19:52:48Z published: 2026-10-14T19:52:48Z canonical: "help.hyperscience.ai/training-a-specialized-model" --- > ## 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. # Training a Specialized Model ORCA is a Vision Language Model (VLM) that extracts information from documents. To learn more, see [ORCA Vision Language Models](/v44/docs/orca-vlms) While the base model works out of the box, you can improve its performance by training a specialized model on your specific data using annotated documents. ORCA VLMs can be managed and trained directly in Training Data Management (TDM). This article explains how to create a specialized model on top of an ORCA base model for your use case. ## ORCA VLM specialization The ORCA base model provides general-purpose extraction capabilities, but every customer’s documents are different. > [!NOTE] > ORCA 2 base model > > In v43.2 and later, the **ORCA 2** base model is available in addition to ORCA 1.0. ORCA 2 extends ORCA 1.0’s capabilities, and each specialized model inherits the capabilities of the base model selected for its training run. To learn more, see [ORCA Vision Language Models](/v44/docs/orca-vlms) and [TDM for ORCA VLMs](/v44/docs/tdm-for-orca-vlms). Training a specialized model on your documents allows you to: - Improve extraction accuracy for your specific layouts. To learn more, see [Accuracy](/v44/docs/accuracy). - Reduce the number of fields that require human review. To learn more, see [Automation](/v44/docs/automation). - Specialize the model to your organization’s document formats. Training creates a specialized model tailored to your use case while still using the capabilities of the ORCA base model. It does not modify the base model itself. > [!NOTE] > Accuracy and automation tradeoffs > > - Creating a specialized model on top of the ORCA base model allows you to define whether you need more accuracy or more automation for your specific use case. > - If you use an ORCA VLM without specialization, you will either fully automate the processing or send everything for human review. To learn more, see [Accuracy](/v44/docs/accuracy). To specialize an ORCA model: 1. Upload and annotate training documents in TDM for VLM Field Extraction. 2. Train the model to create a candidate. 3. Review the candidate model and its Projected Automation. 4. Deploy the candidate model. 5. Validate the model with test documents. 6. Retrain the model with additional data if needed, or keep the Deployed Model live. > [!NOTE] > Before specializing an ORCA model, make sure that: > > - An ORCA base model is installed. You can prepare and annotate training data without one, but training requires at least one compatible installed base model. To learn more, see [TDM for ORCA VLMs](/v44/docs/tdm-for-orca-vlms) and [Installing ORCA VLMs](/v44/docs/installing-orca-vlms). > - You’ve configured a Semi-structured layout with the fields you need for your use case. ORCA VLMs extract fields from Semi-structured layouts only. > - The latest Layout Version is locked. > - A Model Definition exists for the layout. To learn more, see [Model Definitions](/v44/docs/model-definitions). Follow the steps below to create a specialized model for your use case. ### Upload training documents Before training a specialized model, you must upload and annotate training documents for your layout. Doing so provides the ground truth values the model will learn from during training. > [!NOTE] > Dataset requirements > > - The uploaded documents should not exceed **5 pages.** > - Larger documents may lead to an Out-of-Memory (OOM) Error during specialized model training. > - **Supporting larger documents requires increasing GPU memory.** Contact your Hyperscience representative for more information. > - Make sure that all training documents are unique. > - The system excludes duplicate annotated documents from training. > - If the system excludes too many documents, training may fail because of insufficient data. > - Include documents that represent the different patterns in your dataset. > - Annotate enough documents to capture these patterns before training the model. Upload your documents through the **Training Data** tab in TDM. For the upload steps, see [Training Data Management for ORCA VLMs](/v44/docs/tdm-for-orca-vlms). Once the documents are loaded in the system, you can start the annotation process. ### Annotating training documents Open each document for annotation from the Training Data table. For the annotation steps and the annotation view’s controls, see [Training Data Management for ORCA VLMs](/v44/docs/tdm-for-orca-vlms). When annotating documents for a specialized ORCA model, follow these guidelines: - **Enter text exactly as it appears in the document.** Do not normalize dates, fix typos, or change the letter case unless specifically instructed. - **Avoid formatting or input validation.** - **Review pre-populated values carefully.** The application may automatically populate fields by detecting text inside a selected area. Always verify that the captured value matches the document exactly, and correct it if needed. - **Add missing text manually when necessary.** If the automated detection misses part of the value, manually enter the missing characters to complete the annotation. - **When a field appears multiple times in a document, annotate the values in natural reading order:** top to bottom, left to right, and first page to last page. - **If the same field appears across multiple pages, treat its values as a single continuous sequence for that document.** ### Train the model During training, the system uses the annotated document values as ground truth and trains a specialized model tailored to your document format. > [!NOTE] > Number of required documents > > - Make sure that you have **at least 120 annotated documents** to train the model. Only eligible annotated documents count toward this requirement. > - For more stable and reliable performance, **we recommend using 200+ annotated documents,** covering the variety of document patterns in your dataset. > - Using a larger and more diverse dataset generally improves model performance. To initiate training, click **Train Model** in the **Actions** drop-down menu. If multiple base models are installed, select an eligible base model when prompted. To learn more, see [Training Data Management for ORCA VLMs](/v44/docs/tdm-for-orca-vlms). ![Starting model training from the Actions drop-down menu](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/model_training.gif?sv=2026-02-06&spr=https&st=2026-11-09T19%3A58%3A08Z&se=2026-11-09T20%3A58%3A08Z&sr=c&sp=r&sig=QptuTGm%2F5g4he3T7i2N0jGp9OUC6EjzquJ09uYK8RoA%3D) ### Review the candidate model Training produces a candidate model. The candidate does not process documents until you deploy it, and you can review its projected performance first. The **Overview** tab can show **Live model summary**, **Last live model summary**, and **Candidate model summary** cards. A card appears only when the corresponding model exists. | Field | Meaning | | --- | --- | | **State** | The model’s current state, such as Live, Candidate, or Inactive. | | **Projected Automation** | The estimated automation at the selected Test Target Accuracy. It appears for a specialized model when projection data is available. | | **Machine Accuracy** | The measured model accuracy. It can appear when projected-automation data is unavailable. | | **Test Target Accuracy** | The accuracy value used to calculate Projected Automation. | | **Trained** | The specialized model’s training date. A base model is labeled Pre-trained. | | **Layout version** | The layout version used for specialized-model training. This field is not shown for a base model. | The Projected Automation card appears when the live or candidate specialized model has projection data. It shows projected automation and its margin of error at the selected **Test Target Accuracy**. To learn more, see [Accuracy and Automation](/v44-user-guide/docs/accuracy-and-automation). - Change Test Target Accuracy to see how the projection changes. - Expand the card to compare the live and candidate curves. A curve appears only when projection data is available for that model. - Use the margin of error to understand the uncertainty around the estimate. A smaller margin indicates a more precise projection. - If the candidate should not be used, you can reject it. You cannot undo the rejection of a candidate. To produce a new candidate, annotate additional documents and run training again. ### Deploy the candidate model To deploy the candidate: 1. On the **Model Details** page, open the **Actions** drop-down menu. 2. Select **Deploy candidate model** and confirm the action. You can also deploy the candidate from the **History** tab by finding the candidate model and clicking **Deploy**. ![Deploying the candidate model](https://cdn.us.document360.io/87894cef-4958-4f3f-be6f-b75a78c82548/Images/Documentation/deploy.jpg?sv=2026-02-06&spr=https&st=2026-11-09T19%3A58%3A08Z&se=2026-11-09T20%3A58%3A08Z&sr=c&sp=r&sig=QptuTGm%2F5g4he3T7i2N0jGp9OUC6EjzquJ09uYK8RoA%3D) After deployment, the candidate becomes **Live**, and documents submitted through the associated flow are processed by the specialized model. ### Validate the model with test documents After deploying the model, validate its performance on realistic data before relying on it in production. #### Using testing documents We recommend setting aside 50–100 representative documents for testing your model’s performance. Doing so allows you to evaluate how the model performs on realistic data. - These documents should reflect the variety of inputs you expect in production. - The model must not have seen them during training (i.e., do not include them in the training documents). #### Validating 1. Set the flow’s QA sample rate to 100%, so that each processed document is reviewed in a QA task. Follow the steps described in [Installing ORCA VLMs](/v44/docs/installing-orca-vlms) to set your sample rate. 2. Run your testing documents through the system. Learn how to perform the VLM QA task in our [Vision Language Model Quality Assurance](/v44/docs/vision-language-model-quality-assurance) article. 3. Use the QA results to assess whether: - the Accuracy rate indicates that the generated transcriptions correctly match the document content, and - the Automation rate indicates that documents can be processed without requiring manual transcription review. 4. Compare the metrics between the new model and the previous model. > [!NOTE] > ORCA VLM transcriptions > > Unlike traditional Identification models, ORCA VLMs directly generate transcriptions for each field. ### Decide next steps Based on the validation results, you can: - Keep the deployed model live if the results meet your requirements. - Retrain the model by adding more or higher-quality training data, and then review, deploy, and validate the new candidate as described above. Remember to return the flow’s QA sample rate to its regular value after you finish validating the model. 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 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. **Accuracy** measures the effectiveness of the models based on the proportion of correct predictions out of all predictions made. It helps you understand how often the system correctly predicts values compared to the actual values that reached consensus during QA. Accuracy can be influenced by factors like imbalanced datasets or inconsistent annotations. 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. The input used to teach machine learning models how to process documents accurately. Its structure depends on the model type: - For **Classification models**, training data consists of uploaded document pages grouped by layout. - For **Identification models**, training data includes manually annotated fields and tables to train the model to extract specific data points. 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. An iteration of a layout that reflects the state of a layout at a given point in time. You can create new versions and restore older ones based on your needs. 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). Manually annotated data used to train our machine learning models. We use a subset of this data to assess the performance of your models An out-of-memory error happens when a process in Hyperscience tries to use more memory than is available. It can interrupt processing and usually indicates that the job or document is too large or complex for the allocated resources. A group of documents used to help the system learn or improve. Datasets are used for training, testing, or evaluating how well the system reads and extracts information. **Annotation** refers to a user-provided input that defines the correct prediction for a given machine learning task. Annotations are used to train supervised machine learning models. **Quality Assurance (QA)** is a process that ensures the accuracy and reliability of system outputs. In Hyperscience, QA tasks allow users to review and correct errors in classification, identification, VLM extraction and transcription. Documents may enter QA after processing through Submissions, depending on the workflow configuration.