jprdonnelly/docs
1
0
Fork 0
mirror of synced 2025-12-22 19:34:15 -05:00
Code Issues Projects Releases Wiki Activity

[Remove Quotes] Removed quotes from copilot education and github-cli folders (#53589)

Browse Source 
Co-authored-by: Joe Clark <31087804+jc-clark@users.noreply.github.com>
This commit is contained in:
Ashley
2024-12-12 18:37:57 -05:00
committed by GitHub
parent 8e1ac36734
commit 7b3918e77b
123 changed files with 593 additions and 593 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
content/copilot/customizing-copilot/creating-a-custom-model-for-github-copilot.md
View File

@@ -22,7 +22,7 @@ The code on which you want to train a custom model must be hosted in repositorie
## Limitations
* For the {% data variables.release-phases.public_preview %}, an enterprise can deploy one custom model in a single organization.
* Code completion suggestions based on the custom model are only available to managed users who get a {% data variables.product.prodname_copilot_enterprise_short %} subscription from the organization in which the custom model is deployed. For more information, see "[AUTOTITLE](/enterprise-cloud@latest/admin/managing-iam/understanding-iam-for-enterprises/about-enterprise-managed-users)."
* Code completion suggestions based on the custom model are only available to managed users who get a {% data variables.product.prodname_copilot_enterprise_short %} subscription from the organization in which the custom model is deployed. For more information, see [AUTOTITLE](/enterprise-cloud@latest/admin/managing-iam/understanding-iam-for-enterprises/about-enterprise-managed-users).
* The custom model is not used for code suggested in responses by {% data variables.product.prodname_copilot_chat %}.
## About {% data variables.product.prodname_copilot_short %} custom models
@@ -47,7 +47,7 @@ Currently, in the {% data variables.release-phases.public_preview %}, only one o
As an owner of the organization that's permitted to create a custom model, you can choose which of your organization's repositories to use to train the model. You can train the model on one, several, or all of the repositories in the organization. The model is trained on the content of the default branches of the selected repositories. Optionally, you can specify that only code written in certain programming languages should be used for training. The custom model will be used for generating code completion suggestions in all file types, irrespective of whether that type of file was used for training.
You can also choose whether telemetry data (such as the prompts entered by users and the suggestions generated by {% data variables.product.prodname_copilot_short %}) should be used when training the model. For more information, see "[Telemetry data collection and usage for custom models](#telemetry-data-collection-and-usage-for-custom-models)," later in this article.
You can also choose whether telemetry data (such as the prompts entered by users and the suggestions generated by {% data variables.product.prodname_copilot_short %}) should be used when training the model. For more information, see [Telemetry data collection and usage for custom models](#telemetry-data-collection-and-usage-for-custom-models), later in this article.
Once initiated, custom model creation will take many hours to complete. You can check the progress of the training in your organization's settings. When model creation completes - or if it fails to complete - the person who initiated the model training will be notified by email.
@@ -71,7 +71,7 @@ However, even in standardized environments, fine-tuning offers an opportunity to
While some coding environments are more likely to benefit from fine-tuning, there is no guaranteed correlation between specific behaviors in a codebase and the quality of the results you get from a custom model. It is advisable to assess the use and satisfaction levels of {% data variables.product.prodname_copilot %} code completion suggestions before and after the implementation of a custom model.
* Use the {% data variables.product.prodname_dotcom %} API to assess the usage of {% data variables.product.prodname_copilot %}. See "[AUTOTITLE](/rest/copilot/copilot-usage?apiVersion=2022-11-28#get-a-summary-of-copilot-usage-for-an-enterprise-team)."
* Use the {% data variables.product.prodname_dotcom %} API to assess the usage of {% data variables.product.prodname_copilot %}. See [AUTOTITLE](/rest/copilot/copilot-usage?apiVersion=2022-11-28#get-a-summary-of-copilot-usage-for-an-enterprise-team).
* Survey developers to assess their level of satisfaction with {% data variables.product.prodname_copilot %} code completion suggestions.
Comparing results from the API and developer survey, from before and after the implementation of a custom model, will give you an indication of the effectiveness of the custom model.
@@ -91,11 +91,11 @@ You can use your organization settings to create a custom large language model.
1. To improve the performance of your model, select the checkbox labeled **Include data from prompts and suggestions**.
> [!NOTE]
> If the checkbox isn't available to select it indicates that the **Telemetry data collection** policy for custom models has been disabled in your organization's settings. For information on how to change policies for your organization, see "[AUTOTITLE](/copilot/managing-copilot/managing-github-copilot-in-your-organization/setting-policies-for-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization#enabling-copilot-features-in-your-organization)."
> If the checkbox isn't available to select it indicates that the **Telemetry data collection** policy for custom models has been disabled in your organization's settings. For information on how to change policies for your organization, see [AUTOTITLE](/copilot/managing-copilot/managing-github-copilot-in-your-organization/setting-policies-for-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization#enabling-copilot-features-in-your-organization).
By selecting this option you allow {% data variables.product.prodname_copilot_short %} to collect data for prompts that user submitted and the code completion suggestions that were generated. Once sufficient data has been collected, {% data variables.product.prodname_copilot_short %} will use this as part of the model training process, allowing it to produce a more effective model.
For more information, see "[Telemetry data collection and usage for custom models](#telemetry-data-collection-and-usage-for-custom-models)," later in this article.
For more information, see [Telemetry data collection and usage for custom models](#telemetry-data-collection-and-usage-for-custom-models), later in this article.
1. Click **Create new custom model**.
@@ -103,7 +103,7 @@ You can use your organization settings to create a custom large language model.
You can check in your organization settings for an indication of how model creation is progressing.
1. Go to your organization's settings for {% data variables.product.prodname_copilot_short %} custom models. See "[Creating a custom model](#creating-a-custom-model)" above.
1. Go to your organization's settings for {% data variables.product.prodname_copilot_short %} custom models. See [Creating a custom model](#creating-a-custom-model) above.
1. The first time you train a model, the page that's displayed shows the training results.
If this is not the first training, the current and previous training attempts are listed. To see details of the current training process, click the first ellipsis button (**...**), then click **Training details**.
@@ -122,7 +122,7 @@ As an organization owner, you can update or delete the custom model from your or
Retraining the model updates it to include any new code that has been added to the repositories you selected for training. You can retrain the model once a week.
1. Go to your organization's settings for {% data variables.product.prodname_copilot_short %} custom models. See "[Creating a custom model](#creating-a-custom-model)" above.
1. Go to your organization's settings for {% data variables.product.prodname_copilot_short %} custom models. See [Creating a custom model](#creating-a-custom-model) above.
1. On the model training page, click the first ellipsis button (**...**), then click either **Retrain model** or **Delete model**.
If you retrain the model, {% data variables.product.prodname_copilot_short %} will continue to use the current model to generate code completion suggestions until the new model is ready. Once the new model is ready, it will be automatically be used for code completion suggestions for all managed users who get a {% data variables.product.prodname_copilot_enterprise_short %} subscription from the organization.