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
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.
19
19
20
20
| Model family | Description |
21
21
|--|--|
@@ -25,14 +25,14 @@ The service provides access to many different models, grouped by family and capa
25
25
26
26
## Model capabilities
27
27
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.
29
29
30
30
> [!NOTE]
31
31
> 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.
32
32
33
33
## Naming convention
34
34
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:
@@ -45,26 +45,26 @@ Azure OpenAI's model names typically correspond to the following standard naming
45
45
46
46
For example, our most powerful GPT-3 model is called `text-davinci-003`, while our most powerful Codex model is called `code-davinci-002`.
47
47
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).
49
49
50
50
## Finding what models are available
51
51
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).
53
53
54
54
## Finding the right model
55
55
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.
57
57
58
58
## GPT-3 models
59
59
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:
61
61
62
-
-`text-ada-001`
63
-
-`text-babbage-001`
64
-
-`text-curie-001`
65
62
-`text-davinci-003`
63
+
-`text-curie-001`
64
+
-`text-babbage-001`
65
+
-`text-ada-001`
66
66
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.
68
68
69
69
### <aid="gpt-3-davinci"></a>Davinci
70
70
@@ -96,14 +96,14 @@ Ada is usually the fastest model and can perform tasks like parsing text, addres
96
96
97
97
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.
98
98
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:
100
100
101
-
-`code-cushman-001`
102
101
-`code-davinci-002`
102
+
-`code-cushman-001`
103
103
104
104
### <aid="codex-davinci"></a>Davinci
105
105
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.
107
107
108
108
### Cushman
109
109
@@ -150,40 +150,38 @@ Similar to text search embedding models, there are two input types supported by
0 commit comments