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-studio/concepts/fine-tuning-overview.md
+15-3Lines changed: 15 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -99,6 +99,7 @@ There isn't a single right answer to this question, but you should have clearly
99
99
100
100
Now that you know when to leverage fine-tuning for your use-case, you can go to Azure AI Studio to find several models available to fine-tune including:
101
101
- Azure OpenAI models
102
+
- Phi-3 family of models
102
103
- Meta Llama 2 family models
103
104
- Meta Llama 3.1 family of models
104
105
@@ -119,22 +120,33 @@ The following Azure OpenAI models are supported in Azure AI Studio for fine-tuni
119
120
120
121
Please note for fine-tuning Azure OpenAI models, you must add a connection to an Azure OpenAI resource with a supported region to your project.
121
122
123
+
### Phi-3 family models
124
+
The following Phi-3 family models are supported in Azure AI Studio for fine-tuning:
125
+
-`Phi-3-mini-4k-instruct`
126
+
-`Phi-3-mini-128k-instruct`
127
+
-`Phi-3-medium-4k-instruct`
128
+
-`Phi-3-medium-128k-instruct`
129
+
130
+
Fine-tuning of Phi-3 models is currently supported in projects located in East US2.
131
+
122
132
### Llama 2 family models
123
133
The following Llama 2 family models are supported in Azure AI Studio for fine-tuning:
124
134
-`Meta-Llama-2-70b`
125
135
-`Meta-Llama-2-7b`
126
136
-`Meta-Llama-2-13b`
127
137
128
-
Fine-tuning of Llama 2 models is currently supported in projects located in West US 3.
138
+
Fine-tuning of Llama 2 models is currently supported in projects located in West US3.
129
139
130
140
### Llama 3.1 family models
131
141
The following Llama 3.1 family models are supported in Azure AI Studio for fine-tuning:
132
142
-`Meta-Llama-3.1-70b-Instruct`
133
-
-`Meta-Llama-3.1-7b-Instruct`
143
+
-`Meta-Llama-3.1-8b-Instruct`
134
144
135
-
Fine-tuning of Llama 3.1 models is currently supported in projects located in West US 3.
145
+
Fine-tuning of Llama 3.1 models is currently supported in projects located in West US3.
136
146
137
147
## Related content
138
148
139
149
-[Learn how to fine-tune an Azure OpenAI model in Azure AI Studio](../../ai-services/openai/how-to/fine-tuning.md?context=/azure/ai-studio/context/context)
140
150
-[Learn how to fine-tune a Llama 2 model in Azure AI Studio](../how-to/fine-tune-model-llama.md)
151
+
-[Learn how to fine-tune a Phi-3 model in Azure AI Studio](../how-to/fine-tune-phi-3.md)
152
+
-[How to deploy Phi-3 family of small language models with Azure AI Studio](../how-to/deploy-models-phi-3.md)
0 commit comments