You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Azure OpenAI Service offers a variety of models for different use cases. The following models are not available for new deployments beginning July 6, 2023. Deployments created prior to July 6, 2023 remain available to customers until July 5, 2024. We recommend customers migrate to the replacement models prior to the July 5, 2024 retirement.
17
+
Azure OpenAI Service offers a variety of models for different use cases. The following models were deprecated on July 6, 2023 and will be retired on July 5, 2024. These models are no longer available for new deployments. Deployments created prior to July 6, 2023 remain available to customers until July 5, 2024. We recommend customers migrate their applications to deployments of replacement models prior to the July 5, 2024 retirement.
18
+
19
+
At the time of retirement, deployments of these models will stop returning valid API responses.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/concepts/model-versions.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -23,7 +23,7 @@ We want to make it easy for customers to stay up to date as models improve. Cus
23
23
24
24
When a customer deploys GPT-3.5-Turbo and GPT-4 on Azure OpenAI Service, the standard behavior is to deploy the current default version – for example, GPT-4 version 0314. When the default version changes to say GPT-4 version 0613, the deployment is automatically updated to version 0613 so that customer deployments feature the latest capabilities of the model.
25
25
26
-
Customers can also deploy a specific version like GPT-4 0314 or GPT-4 0613 and choose an update policy, which can include the following options:
26
+
Customers can also deploy a specific version like GPT-4 0613 and choose an update policy, which can include the following options:
27
27
28
28
* Deployments set to **Auto-update to default** automatically update to use the new default version.
29
29
* Deployments set to **Upgrade when expired** automatically update when its current version is retired.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/concepts/models.md
+4-4Lines changed: 4 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -27,11 +27,12 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
27
27
28
28
## GPT-4 and GPT-4 Turbo Preview
29
29
30
-
GPT-4 can solve difficult problems with greater accuracy than any of OpenAI's previous models. Like GPT-3.5 Turbo, GPT-4 is optimized for chat and works well for traditional completions tasks. Use the Chat Completions API to use GPT-4. To learn more about how to interact with GPT-4 and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
30
+
GPT-4 is a large multimodal model (accepting text or image inputs and generating text) that can solve difficult problems with greater accuracy than any of OpenAI's previous models. Like GPT-3.5 Turbo, GPT-4 is optimized for chat and works well for traditional completions tasks. Use the Chat Completions API to use GPT-4. To learn more about how to interact with GPT-4 and the Chat Completions API check out our [in-depth how-to](../how-to/chatgpt.md).
31
+
32
+
GPT-4 Turbo with Vision is the version of GPT-4 that accepts image inputs. It is available as the `vision-preview` model of `gpt-4`.
31
33
32
34
-`gpt-4`
33
35
-`gpt-4-32k`
34
-
-`gpt-4-vision`
35
36
36
37
You can see the token context length supported by each model in the [model summary table](#model-summary-table-and-region-availability).
37
38
@@ -97,7 +98,6 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope
97
98
> [!NOTE]
98
99
> Version `0314` of `gpt-4` and `gpt-4-32k` will be retired no earlier than July 5, 2024. Version `0613` of `gpt-4` and `gpt-4-32k` will be retired no earlier than September 30, 2024. See [model updates](../how-to/working-with-models.md#model-updates) for model upgrade behavior.
99
100
100
-
101
101
GPT-4 version 0125-preview is an updated version of the GPT-4 Turbo preview previously released as version 1106-preview. GPT-4 version 0125-preview completes tasks such as code generation more completely compared to gpt-4-1106-preview. Because of this, depending on the task, customers may find that GPT-4-0125-preview generates more output compared to the gpt-4-1106-preview. We recommend customers compare the outputs of the new model. GPT-4-0125-preview also addresses bugs in gpt-4-1106-preview with UTF-8 handling for non-English languages.
102
102
103
103
> [!IMPORTANT]
@@ -205,7 +205,7 @@ The following Embeddings models are available with [Azure Government](/azure/azu
205
205
| Model ID | Feature Availability | Max Request (characters) |
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/working-with-models.md
+13-13Lines changed: 13 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,31 +20,31 @@ You can get a list of models that are available for both inference and fine-tuni
20
20
21
21
## Model updates
22
22
23
-
Azure OpenAI now supports automatic updates for select model deployments. On models where automatic update support is available, a model version drop-down will be visible in Azure OpenAI Studio under **Create new deployment** and **Edit deployment**:
23
+
Azure OpenAI now supports automatic updates for select model deployments. On models where automatic update support is available, a model version drop-down is visible in Azure OpenAI Studio under **Create new deployment** and **Edit deployment**:
24
24
25
25
:::image type="content" source="../media/models/auto-update.png" alt-text="Screenshot of the deploy model UI of Azure OpenAI Studio." lightbox="../media/models/auto-update.png":::
26
26
27
27
You can learn more about Azure OpenAI model versions and how they work in the [Azure OpenAI model versions](../concepts/model-versions.md) article.
28
28
29
29
### Auto update to default
30
30
31
-
When **Auto-update to default** is selected your model deployment will be automatically updated within two weeks of a change in the default version. For a preview version, it will update automatically when a new preview version is available starting two weeks after the new preview version is released.
31
+
When you set your deployment to **Auto-update to default**, your model deployment is automatically updated within two weeks of a change in the default version. For a preview version, it updates automatically when a new preview version is available starting two weeks after the new preview version is released.
32
32
33
33
If you're still in the early testing phases for inference models, we recommend deploying models with **auto-update to default** set whenever it's available.
34
34
35
35
### Specific model version
36
36
37
-
As your use of Azure OpenAI evolves, and you start to build and integrate with applications you might want to manually control model updates so that you can first test and validate that model performance is remaining consistent for your use case prior to upgrade.
37
+
As your use of Azure OpenAI evolves, and you start to build and integrate with applications you might want to manually control model updates. You can first test and validate that your application behavior is consistent for your use case before upgrading.
38
38
39
-
When you select a specific model version for a deployment this version will remain selected until you either choose to manually update yourself, or once you reach the retirement date for the model. When the retirement date is reached the model will automatically upgrade to the default version at the time of retirement.
39
+
When you select a specific model version for a deployment, this version remains selected until you either choose to manually update yourself, or once you reach the retirement date for the model. When the retirement date is reached the model will automatically upgrade to the default version at the time of retirement.
40
40
41
-
## Viewing deprecation dates
41
+
## Viewing retirement dates
42
42
43
43
For currently deployed models, from Azure OpenAI Studio select **Deployments**:
44
44
45
45
:::image type="content" source="../media/models/deployments.png" alt-text="Screenshot of the deployment UI of Azure OpenAI Studio." lightbox="../media/models/deployments.png":::
46
46
47
-
To view deprecation/expiration dates for all available models in a given region from Azure OpenAI Studio select **Models** > **Column options** > Select **Deprecation fine tune** and **Deprecation inference**:
47
+
To view retirement dates for all available models in a given region from Azure OpenAI Studio, select **Models** > **Column options** > Select **Deprecation fine tune** and **Deprecation inference**:
48
48
49
49
:::image type="content" source="../media/models/column-options.png" alt-text="Screenshot of the models UI of Azure OpenAI Studio." lightbox="../media/models/column-options.png":::
50
50
@@ -54,28 +54,28 @@ You can check what model upgrade options are set for previously deployed models
54
54
55
55
:::image type="content" source="../media/how-to/working-with-models/deployments.png" alt-text="Screenshot of the deployments pane with a deployment name highlighted." lightbox="../media/how-to/working-with-models/deployments.png":::
56
56
57
-
This will open the **Properties** for the model deployment. You can view what upgrade options are set for your deployment under **Version update policy**:
57
+
Selecting a deployment name opens the **Properties** for the model deployment. You can view what upgrade options are set for your deployment under **Version update policy**:
58
58
59
59
:::image type="content" source="../media/how-to/working-with-models/update-policy.png" alt-text="Screenshot of the model deployments property UI." lightbox="../media/how-to/working-with-models/update-policy.png":::
60
60
61
61
The corresponding property can also be accessed via [REST](../how-to/working-with-models.md#model-deployment-upgrade-configuration), [Azure PowerShell](/powershell/module/az.cognitiveservices/get-azcognitiveservicesaccountdeployment), and [Azure CLI](/cli/azure/cognitiveservices/account/deployment#az-cognitiveservices-account-deployment-show).
62
62
63
63
|Option| Read | Update |
64
64
|---|---|---|
65
-
|[REST](../how-to/working-with-models.md#model-deployment-upgrade-configuration)| Yes. If `versionUpgradeOption` is not returned it means it is `null`|Yes |
65
+
|[REST](../how-to/working-with-models.md#model-deployment-upgrade-configuration)| Yes. If `versionUpgradeOption` is not returned, it means it is `null`|Yes |
66
66
|[Azure PowerShell](/powershell/module/az.cognitiveservices/get-azcognitiveservicesaccountdeployment)| Yes.`VersionUpgradeOption` can be checked for `$null`| Yes |
67
67
|[Azure CLI](/cli/azure/cognitiveservices/account/deployment#az-cognitiveservices-account-deployment-show)| Yes. It shows `null` if `versionUpgradeOption` is not set.|*No.* It is currently not possible to update the version upgrade option.|
68
68
69
69
There are three distinct model deployment upgrade options:
70
70
71
71
| Name | Description |
72
72
|------|--------|
73
-
|`OnceNewDefaultVersionAvailable`| Once a new version is designated as the default, the model deployment will automatically upgrade to the default version within two weeks of that designation change being made. |
74
-
|`OnceCurrentVersionExpired`| Once the retirement date is reached the model deployment will automatically upgrade to the current default version. |
75
-
|`NoAutoUpgrade`| The model deployment will never automatically upgrade. Once the retirement date is reached the model deployment will stop working. You will need to update your code referencing that deployment to point to a nonexpired model deployment. |
73
+
|`OnceNewDefaultVersionAvailable`| Once a new version is designated as the default, the model deployment automatically upgrades to the default version within two weeks of that designation change being made. |
74
+
|`OnceCurrentVersionExpired`| Once the retirement date is reached the model deployment automatically upgrades to the current default version. |
75
+
|`NoAutoUpgrade`| The model deployment never automatically upgrades. Once the retirement date is reached the model deployment stops working. You need to update your code referencing that deployment to point to a nonexpired model deployment. |
76
76
77
77
> [!NOTE]
78
-
> `null` is equivalent to `AutoUpgradeWhenExpired`. If the **Version update policy** option is not present in the properties for a model that supports model upgrades this indicates the value is currently `null`. Once you explicitly modify this value the property will be visible in the studio properties page as well as via the REST API.
78
+
> `null` is equivalent to `AutoUpgradeWhenExpired`. If the **Version update policy** option is not present in the properties for a model that supports model upgrades this indicates the value is currently `null`. Once you explicitly modify this value, the property is visible in the studio properties page as well as via the REST API.
To query the current model deployment settings including the deployment upgrade configuration for a given resource use [`Deployments List`](/rest/api/cognitiveservices/accountmanagement/deployments/list?tabs=HTTP#code-try-0). If the value is null you won't see a `versionUpgradeOption` property.
125
+
To query the current model deployment settings including the deployment upgrade configuration for a given resource use [`Deployments List`](/rest/api/cognitiveservices/accountmanagement/deployments/list?tabs=HTTP#code-try-0). If the value is null, you won't see a `versionUpgradeOption` property.
126
126
127
127
```http
128
128
GET https://management.azure.com/subscriptions/{subscriptionId}/resourceGroups/{resourceGroupName}/providers/Microsoft.CognitiveServices/accounts/{accountName}/deployments?api-version=2023-05-01
![prmerger-automator[bot]](https://avatars.githubusercontent.com/u/22479449?v=4&size=40){kind=avatar}
0 commit comments