Skip to content

Commit 38335a3

Browse files
authored
Merge pull request #227212 from eric-urban/eur/openai-models
OpenAI models editorial pass
2 parents d72028d + 9d5a522 commit 38335a3

File tree

1 file changed

+38
-41
lines changed
  • articles/cognitive-services/openai/concepts

1 file changed

+38
-41
lines changed

articles/cognitive-services/openai/concepts/models.md

Lines changed: 38 additions & 41 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,10 @@
11
---
22
title: Azure OpenAI Service models
33
titleSuffix: Azure OpenAI
4-
description: Learn about the different models that are available in Azure OpenAI.
4+
description: Learn about the different model capabilities that are available with Azure OpenAI.
55
ms.service: cognitive-services
66
ms.topic: conceptual
7-
ms.date: 06/24/2022
7+
ms.date: 02/13/2023
88
ms.custom: event-tier1-build-2022, references_regions
99
manager: nitinme
1010
author: ChrisHMSFT
@@ -15,7 +15,7 @@ keywords:
1515

1616
# Azure OpenAI Service models
1717

18-
The service provides access to many different models, grouped by family and capability. A model family typically associates models by their intended task. The following table describes model families currently available in Azure OpenAI. Not all models are available in all regions currently. Please refer to the capability table at the bottom for a full breakdown.
18+
Azure OpenAI provides access to many different models, grouped by family and capability. A model family typically associates models by their intended task. The following table describes model families currently available in Azure OpenAI. Not all models are available in all regions currently. Refer to the [model capability table](#model-capabilities) in this article for a full breakdown.
1919

2020
| Model family | Description |
2121
|--|--|
@@ -25,14 +25,14 @@ The service provides access to many different models, grouped by family and capa
2525

2626
## Model capabilities
2727

28-
Each model family has a series of models that are further distinguished by capability. These capabilities are typically identified by names, and the alphabetical order of these names generally signifies the relative capability and cost of that model within a given model family. For example, GPT-3 models use names such as Ada, Babbage, Curie, and Davinci to indicate relative capability and cost. Davinci is more capable (at a higher cost) than Curie, which in turn is more capable (at a higher cost) than Babbage, and so on.
28+
Each model family has a series of models that are further distinguished by capability. These capabilities are typically identified by names, and the alphabetical order of these names generally signifies the relative capability and cost of that model within a given model family. For example, GPT-3 models use names such as Ada, Babbage, Curie, and Davinci to indicate relative capability and cost. Davinci is more capable and more expensive than Curie, which in turn is more capable and more expensive than Babbage, and so on.
2929

3030
> [!NOTE]
3131
> Any task that can be performed by a less capable model like Ada can be performed by a more capable model like Curie or Davinci.
3232
3333
## Naming convention
3434

35-
Azure OpenAI's model names typically correspond to the following standard naming convention:
35+
Azure OpenAI model names typically correspond to the following standard naming convention:
3636

3737
`{family}-{capability}[-{input-type}]-{identifier}`
3838

@@ -45,26 +45,26 @@ Azure OpenAI's model names typically correspond to the following standard naming
4545

4646
For example, our most powerful GPT-3 model is called `text-davinci-003`, while our most powerful Codex model is called `code-davinci-002`.
4747

48-
> Older versions of the GPT-3 models are available, named `ada`, `babbage`, `curie`, and `davinci`. These older models do not follow the standard naming conventions, and they are primarily intended for fine tuning. For more information, see [Learn how to customize a model for your application](../how-to/fine-tuning.md).
48+
> The older versions of GPT-3 models named `ada`, `babbage`, `curie`, and `davinci` that don't follow the standard naming convention are primarily intended for fine tuning. For more information, see [Learn how to customize a model for your application](../how-to/fine-tuning.md).
4949
5050
## Finding what models are available
5151

52-
You can easily see the models you have available for both inference and fine-tuning in your resource by using the [Models API](/rest/api/cognitiveservices/azureopenaistable/models/list).
52+
You can get a list of models that are available for both inference and fine-tuning by your Azure OpenAI resource by using the [Models List API](/rest/api/cognitiveservices/azureopenaistable/models/list).
5353

5454
## Finding the right model
5555

56-
We recommend starting with the most capable model in a model family because it's the best way to understand what the service is capable of. After you have an idea of what you want to accomplish, you can either stay with that model or move to a model with lower capability and cost, optimizing around that model's capabilities.
56+
We recommend starting with the most capable model in a model family to confirm whether the model capabilities meet your requirements. Then you can stay with that model or move to a model with lower capability and cost, optimizing around that model's capabilities.
5757

5858
## GPT-3 models
5959

60-
The GPT-3 models can understand and generate natural language. The service offers four model capabilities, each with different levels of power and speed suitable for different tasks. Davinci is the most capable model, while Ada is the fastest. The following list represents the latest versions of GPT-3 models, ordered by increasing capability.
60+
The GPT-3 models can understand and generate natural language. The service offers four model capabilities, each with different levels of power and speed suitable for different tasks. Davinci is the most capable model, while Ada is the fastest. In the order of greater to lesser capability, the models are:
6161

62-
- `text-ada-001`
63-
- `text-babbage-001`
64-
- `text-curie-001`
6562
- `text-davinci-003`
63+
- `text-curie-001`
64+
- `text-babbage-001`
65+
- `text-ada-001`
6666

67-
While Davinci is the most capable, the other models provide significant speed advantages. Our recommendation is for users to start with Davinci while experimenting, because it will produce the best results and validate the value our service can provide. Once you have a prototype working, you can then optimize your model choice with the best latency/performance balance for your application.
67+
While Davinci is the most capable, the other models provide significant speed advantages. Our recommendation is for users to start with Davinci while experimenting, because it produces the best results and validate the value that Azure OpenAI can provide. Once you have a prototype working, you can then optimize your model choice with the best latency/performance balance for your application.
6868

6969
### <a id="gpt-3-davinci"></a>Davinci
7070

@@ -96,14 +96,14 @@ Ada is usually the fastest model and can perform tasks like parsing text, addres
9696

9797
The Codex models are descendants of our base GPT-3 models that can understand and generate code. Their training data contains both natural language and billions of lines of public code from GitHub.
9898

99-
They’re most capable in Python and proficient in over a dozen languages, including C#, JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and even Shell. The following list represents the latest versions of Codex models, ordered by increasing capability.
99+
They’re most capable in Python and proficient in over a dozen languages, including C#, JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and Shell. In the order of greater to lesser capability, the Codex models are:
100100

101-
- `code-cushman-001`
102101
- `code-davinci-002`
102+
- `code-cushman-001`
103103

104104
### <a id="codex-davinci"></a>Davinci
105105

106-
Similar to GPT-3, Davinci is the most capable Codex model and can perform any task the other models can perform, often with less instruction. For applications requiring deep understanding of the content, Davinci produces the best results. These increased capabilities require more compute resources, so Davinci costs more and isn't as fast as other models.
106+
Similar to GPT-3, Davinci is the most capable Codex model and can perform any task the other models can perform, often with less instruction. For applications requiring deep understanding of the content, Davinci produces the best results. Greater capabilities require more compute resources, so Davinci costs more and isn't as fast as other models.
107107

108108
### Cushman
109109

@@ -150,40 +150,38 @@ Similar to text search embedding models, there are two input types supported by
150150
|---|---|
151151
| Code search and relevance | `code-search-ada-code-001` <br> `code-search-ada-text-001` <br> `code-search-babbage-code-001` <br> `code-search-babbage-text-001` |
152152

153-
When using our Embeddings models, keep in mind their limitations and risks.
153+
When using our embeddings models, keep in mind their limitations and risks.
154154

155155
## Model Summary table and region availability
156156

157157
### GPT-3 Models
158-
| Model | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
158+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
159159
| --- | --- | --- | --- | --- |
160-
| Ada | Yes | No | N/A | East US, South Central US, West Europe |
161-
| Text-Ada-001 | Yes | No | East US, South Central US, West Europe | N/A |
162-
| Babbage | Yes | No | N/A | East US, South Central US, West Europe |
163-
| Text-Babbage-001 | Yes | No | East US, South Central US, West Europe | N/A |
164-
| Curie | Yes | No | N/A | East US, South Central US, West Europe |
165-
| Text-curie-001 | Yes | No | East US, South Central US, West Europe | N/A |
166-
| Davinci* | Yes | No | N/A | East US, South Central US, West Europe |
167-
| Text-davinci-001 | Yes | No | South Central US, West Europe | N/A |
168-
| Text-davinci-002 | Yes | No | East US, South Central US, West Europe | N/A |
169-
| Text-davinci-003 | Yes | No | East US | N/A |
170-
| Text-davinci-fine-tune-002* | Yes | No | N/A | East US, West Europe |
171-
172-
\*Models available by request only. We are currently unable to onboard new customers at this time.
160+
| ada | Yes | No | N/A | East US, South Central US, West Europe |
161+
| text-ada-001 | Yes | No | East US, South Central US, West Europe | N/A |
162+
| babbage | Yes | No | N/A | East US, South Central US, West Europe |
163+
| text-babbage-001 | Yes | No | East US, South Central US, West Europe | N/A |
164+
| curie | Yes | No | N/A | East US, South Central US, West Europe |
165+
| text-curie-001 | Yes | No | East US, South Central US, West Europe | N/A |
166+
| davinci<sup>1</sup> | Yes | No | N/A | East US, South Central US, West Europe |
167+
| text-davinci-001 | Yes | No | South Central US, West Europe | N/A |
168+
| text-davinci-002 | Yes | No | East US, South Central US, West Europe | N/A |
169+
| text-davinci-003 | Yes | No | East US | N/A |
170+
| text-davinci-fine-tune-002<sup>1</sup> | Yes | No | N/A | East US, West Europe |
171+
172+
<sup>1</sup> The model is available by request only. Currently we aren't accepting new requests to use the model.
173173

174174
### Codex Models
175-
| Model | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
175+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
176176
| --- | --- | --- | --- | --- |
177-
| Code-Cushman-001* | Yes | No | South Central US, West Europe | East US, South Central US, West Europe |
178-
| Code-Davinci-002 | Yes | No | East US, West Europe | N/A |
179-
| Code-Davinci-Fine-tune-002* | Yes | No | N/A | East US, West Europe |
180-
181-
\*Models available for Fine-tuning by request only. We are currently unable to enable new cusetomers at this time.
182-
177+
| code-cushman-001<sup>2</sup> | Yes | No | South Central US, West Europe | East US, South Central US, West Europe |
178+
| code-davinci-002 | Yes | No | East US, West Europe | N/A |
179+
| code-davinci-fine-tune-002<sup>2</sup> | Yes | No | N/A | East US, West Europe |
183180

181+
<sup>2</sup> The model is available for fine-tuning by request only. Currently we aren't accepting new requests to fine-tune the model.
184182

185183
### Embeddings Models
186-
| Model | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
184+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
187185
| --- | --- | --- | --- | --- |
188186
| text-ada-embeddings-002 | No | Yes | East US, South Central US, West Europe | N/A |
189187
| text-similarity-ada-001 | No | Yes | East US, South Central US, West Europe | N/A |
@@ -203,7 +201,6 @@ When using our Embeddings models, keep in mind their limitations and risks.
203201
| code-search-babbage-code-001 | No | Yes | South Central US, West Europe | N/A |
204202
| code-search-babbage-text-001 | No | Yes | South Central US, West Europe | N/A |
205203

206-
207204
## Next steps
208205

209-
[Learn more about Azure OpenAI](../overview.md).
206+
[Learn more about Azure OpenAI](../overview.md)

0 commit comments

Comments
 (0)