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/ai-services/openai/concepts/model-retirements.md
+20-1Lines changed: 20 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -87,7 +87,7 @@ For more information on how to manage model upgrades and migrations for provisio
87
87
> [!NOTE]
88
88
> Not all models go through a deprecation period prior to retirement. Some models/versions only have a retirement date.
89
89
>
90
-
> **Fine-tuned models** are subject to the same deprecation and retirement schedule as their equivalent base model.
90
+
> **Fine-tuned models** are subject to a [different](#fine-tuned-models) deprecation and retirement schedule from their equivalent base model.
91
91
92
92
These models are currently available for use in Azure OpenAI.
93
93
@@ -135,6 +135,25 @@ We'll notify all customers with these preview deployments at least 30 days befor
135
135
> [!IMPORTANT]
136
136
> Vision enhancements preview features including Optical Character Recognition (OCR), object grounding, video prompts will be retired and no longer available once `gpt-4` Version: `vision-preview` is upgraded to `turbo-2024-04-09`. If you're currently relying on any of these preview features, this automatic model upgrade will be a breaking change.
137
137
138
+
## Fine-tuned models
139
+
140
+
Fine-tuned models retire in two phases: training and deployment.
141
+
142
+
All fine-tuned models follow their equivalent base model for **training** retirement. Once retired, a given model is no longer available for fine tuning.
143
+
144
+
For fine-tuned models made generally available since `gpt-4o-2024-08-06`, **deployment** retirement occurs 1 year after **training** retirement. At deployment retirement, inference and deployment returns error responses.
145
+
146
+
| Model | Version | Training retirement date | Deployment retirement date |
0 commit comments