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
Copy file name to clipboardExpand all lines: articles/cognitive-services/openai/concepts/models.md
+10-4Lines changed: 10 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -86,7 +86,7 @@ Babbage can perform straightforward tasks like simple classification. It’s als
86
86
87
87
Ada is usually the fastest model and can perform tasks like parsing text, address correction and certain kinds of classification tasks that don’t require too much nuance. Ada’s performance can often be improved by providing more context.
@@ -103,16 +103,22 @@ Similar to GPT-3, Davinci is the most capable Codex model and can perform any ta
103
103
104
104
### Cushman
105
105
106
-
Cushman is powerful, yet fast. While Davinci is stronger when it comes to analyzing complicated tasks, Cushman is capable for many code generation tasks. Cushman typically runs faster and cheaper than Davinci, as well.
106
+
Cushman is powerful, yet fast. While Davinci is stronger when it comes to analyzing complicated tasks, Cushman is a capable model for many code generation tasks. Cushman typically runs faster and cheaper than Davinci, as well.
107
107
108
108
## Embeddings models
109
109
110
-
Currently, we offer three families of Embeddings models for different functionalities: text search, text similarity, and code search. Each family includes models across the following spectrum of capabilities:
110
+
Currently, we offer three families of Embeddings models for different functionalities:
111
+
112
+
-[Similarity](#similarity-embedding)
113
+
-[Text search](#text-search-embedding)
114
+
-[Code search](#code-search-embedding)
115
+
116
+
Each family includes models across the following spectrum of capability:
111
117
112
118
- Ada: 1024 dimensions
113
119
- Babbage: 2048 dimensions
114
120
- Curie: 4096 dimensions
115
-
- Davinci: 12,288 dimensions
121
+
- Davinci: 12288 dimensions
116
122
117
123
Davinci is the most capable, but is slower and more expensive than the other models. Ada is the least capable, but is both faster and cheaper.
0 commit comments