Skip to content

Commit f0b6c7a

Browse files
v-stsavellv-stsavell
authored
Merge pull request #230122 from mrbullwinkle/mrb_03_09_2023_openai_models_update
[Cogntive Services] [Azure OpenAI] Update models
2 parents f675f5c + 44188d3 commit f0b6c7a

File tree

7 files changed

+52
-43
lines changed

7 files changed

+52
-43
lines changed

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

Lines changed: 41 additions & 40 deletions
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ titleSuffix: Azure OpenAI
44
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: 03/01/2023
7+
ms.date: 03/09/2023
88
ms.custom: event-tier1-build-2022, references_regions
99
manager: nitinme
1010
author: ChrisHMSFT
@@ -161,56 +161,57 @@ When using our embeddings models, keep in mind their limitations and risks.
161161
## Model Summary table and region availability
162162

163163
### GPT-3 Models
164-
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
165-
| --- | --- | --- | --- | --- |
166-
| ada | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe |
167-
| text-ada-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A |
168-
| babbage | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe |
169-
| text-babbage-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A |
170-
| curie | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe |
171-
| text-curie-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A |
172-
| davinci<sup>1</sup> | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe |
173-
| text-davinci-001 | Yes | No | South Central US, West Europe | N/A |
174-
| text-davinci-002 | Yes | No | East US, South Central US, West Europe | N/A |
175-
| text-davinci-003 | Yes | No | East US | N/A |
176-
| text-davinci-fine-tune-002<sup>1</sup> | Yes | No | N/A | East US, West Europe |
177-
| gpt-35-turbo<sup>3</sup> (ChatGPT) | Yes | No | N/A | East US, South Central US |
164+
165+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions | Max Request (tokens) | Training Data (up to) |
166+
| --------- | -------------------- | ------------------- | --------------------- | ------------------- | -------------------- | ---------------------- |
167+
| ada | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe | 2,049 | Oct 2019|
168+
| text-ada-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A | 2,049 | Oct 2019|
169+
| babbage | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe | 2,049 | Oct 2019 |
170+
| text-babbage-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A | 2,049 | Oct 2019 |
171+
| curie | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe | 2,049 | Oct 2019 |
172+
| text-curie-001 | Yes | No | East US<sup>2</sup>, South Central US, West Europe | N/A | 2,049 | Oct 2019 |
173+
| davinci<sup>1</sup> | Yes | No | N/A | East US<sup>2</sup>, South Central US, West Europe | 2,049 | Oct 2019|
174+
| text-davinci-001 | Yes | No | South Central US, West Europe | N/A | | |
175+
| text-davinci-002 | Yes | No | East US, South Central US, West Europe | N/A | 4,097 | Jun 2021 |
176+
| text-davinci-003 | Yes | No | East US | N/A | 4,097 | Jun 2021 |
177+
| text-davinci-fine-tune-002<sup>1</sup> | Yes | No | N/A | East US, West Europe | | |
178+
| gpt-35-turbo<sup>3</sup> (ChatGPT) | Yes | No | N/A | East US, South Central US | 4,096 | Sep 2021
178179

179180
<sup>1</sup> The model is available by request only. Currently we aren't accepting new requests to use the model.
180181
<br><sup>2</sup> East US is currently unavailable for new customers to fine-tune due to high demand. Please use US South Central region for US based training.
181182
<br><sup>3</sup> Currently, only version `"0301"` of this model is available. This version of the model will be deprecated on 8/1/2023 in favor of newer version of the gpt-35-model. See [ChatGPT model versioning](../how-to/chatgpt.md#model-versioning) for more details.
182183

183184
### Codex Models
184-
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
185-
| --- | --- | --- | --- | --- |
186-
| code-cushman-001<sup>1</sup> | Yes | No | South Central US, West Europe | East US<sup>2</sup> , South Central US, West Europe |
187-
| code-davinci-002 | Yes | No | East US, West Europe | N/A |
188-
| code-davinci-fine-tune-002<sup>1</sup> | Yes | No | N/A | East US<sup>2</sup> , West Europe |
185+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions | Max Request (tokens) | Training Data (up to) |
186+
| --- | --- | --- | --- | --- | --- | --- |
187+
| code-cushman-001<sup>1</sup> | Yes | No | South Central US, West Europe | East US<sup>2</sup> , South Central US, West Europe | 2,048 | |
188+
| code-davinci-002 | Yes | No | East US, West Europe | N/A | 8,001 | Jun 2021 |
189+
| code-davinci-fine-tune-002<sup>1</sup> | Yes | No | N/A | East US<sup>2</sup> , West Europe | | |
189190

190191
<sup>1</sup> The model is available for fine-tuning by request only. Currently we aren't accepting new requests to fine-tune the model.
191192
<br><sup>2</sup> East US is currently unavailable for new customers to fine-tune due to high demand. Please use US South Central region for US based training.
192193

193194
### Embeddings Models
194-
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions |
195-
| --- | --- | --- | --- | --- |
196-
| text-ada-embeddings-002 | No | Yes | East US, South Central US, West Europe | N/A |
197-
| text-similarity-ada-001 | No | Yes | East US, South Central US, West Europe | N/A |
198-
| text-similarity-babbage-001 | No | Yes | South Central US, West Europe | N/A |
199-
| text-similarity-curie-001 | No | Yes | East US, South Central US, West Europe | N/A |
200-
| text-similarity-davinci-001 | No | Yes | South Central US, West Europe | N/A |
201-
| text-search-ada-doc-001 | No | Yes | South Central US, West Europe | N/A |
202-
| text-search-ada-query-001 | No | Yes | South Central US, West Europe | N/A |
203-
| text-search-babbage-doc-001 | No | Yes | South Central US, West Europe | N/A |
204-
| text-search-babbage-query-001 | No | Yes | South Central US, West Europe | N/A |
205-
| text-search-curie-doc-001 | No | Yes | South Central US, West Europe | N/A |
206-
| text-search-curie-query-001 | No | Yes | South Central US, West Europe | N/A |
207-
| text-search-davinci-doc-001 | No | Yes | South Central US, West Europe | N/A |
208-
| text-search-davinci-query-001 | No | Yes | South Central US, West Europe | N/A |
209-
| code-search-ada-code-001 | No | Yes | South Central US, West Europe | N/A |
210-
| code-search-ada-text-001 | No | Yes | South Central US, West Europe | N/A |
211-
| code-search-babbage-code-001 | No | Yes | South Central US, West Europe | N/A |
212-
| code-search-babbage-text-001 | No | Yes | South Central US, West Europe | N/A |
213-
195+
| Model ID | Supports Completions | Supports Embeddings | Base model Regions | Fine-Tuning Regions | Max Request (tokens) | Training Data (up to) |
196+
| --- | --- | --- | --- | --- | --- | --- |
197+
| text-ada-embeddings-002 | No | Yes | East US, South Central US, West Europe | N/A | 8,191 | Sep 2021 |
198+
| text-similarity-ada-001 | No | Yes | East US, South Central US, West Europe | N/A | 2,046 | Aug 2020 |
199+
| text-similarity-babbage-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
200+
| text-similarity-curie-001 | No | Yes | East US, South Central US, West Europe | N/A | 2046 | Aug 2020 |
201+
| text-similarity-davinci-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
202+
| text-search-ada-doc-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
203+
| text-search-ada-query-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
204+
| text-search-babbage-doc-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
205+
| text-search-babbage-query-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
206+
| text-search-curie-doc-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
207+
| text-search-curie-query-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
208+
| text-search-davinci-doc-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
209+
| text-search-davinci-query-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
210+
| code-search-ada-code-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
211+
| code-search-ada-text-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
212+
| code-search-babbage-code-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
213+
| code-search-babbage-text-001 | No | Yes | South Central US, West Europe | N/A | 2,046 | Aug 2020 |
214+
214215
## Next steps
215216

216217
[Learn more about Azure OpenAI](../overview.md)

‎articles/cognitive-services/openai/how-to/chatgpt.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -294,3 +294,4 @@ assert tokens == [100264, 882, 198, 9906, 100265, 100264, 78191]
294294

295295
* [Learn more about Azure OpenAI](../overview.md).
296296
* Get started with the ChatGPT model with [the ChatGPT quickstart](../chatgpt-quickstart.md).
297+
* For more examples check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)

‎articles/cognitive-services/openai/includes/chatgpt-python.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -140,4 +140,5 @@ If you want to clean up and remove an OpenAI resource, you can delete the resour
140140

141141
## Next steps
142142

143-
Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model with the [ChatGPT how-to guide](../how-to/chatgpt.md).
143+
* Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model with the [ChatGPT how-to guide](../how-to/chatgpt.md).
144+
* For more examples check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)

‎articles/cognitive-services/openai/includes/chatgpt-rest.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -122,4 +122,5 @@ If you want to clean up and remove an OpenAI resource, you can delete the resour
122122

123123
## Next steps
124124

125-
Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model in the [how-to guide on ChatGPT](../how-to/chatgpt.md).
125+
* Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model in the [how-to guide on ChatGPT](../how-to/chatgpt.md).
126+
* For more examples check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)

‎articles/cognitive-services/openai/includes/chatgpt-studio.md

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -117,4 +117,5 @@ Once you're done testing out the ChatGPT playground, if you want to clean up and
117117

118118
## Next steps
119119

120-
Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model with the [ChatGPT how-to guide](../how-to/chatgpt.md).
120+
* Learn more about how to work with ChatGPT and the new `gpt-35-turbo` model with the [ChatGPT how-to guide](../how-to/chatgpt.md).
121+
* For more examples check out the [Azure OpenAI Samples GitHub repository](https://github.com/Azure/openai-samples)

‎articles/cognitive-services/openai/quotas-limits.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,8 @@ The following sections provide you with a quick guide to the quotas and limits t
3737

3838
*The limits are subject to change. We anticipate that you will need higher limits as you move toward production and your solution scales. When you know your solution requirements, please reach out to us by applying for a quota increase here: <https://aka.ms/oai/quotaincrease>
3939

40+
For information on max tokens for different models, consult the [models article](./concepts/models.md#model-summary-table-and-region-availability)
41+
4042
### General best practices to mitigate throttling during autoscaling
4143

4244
To minimize issues related to throttling, it's a good idea to use the following techniques:

‎articles/cognitive-services/openai/toc.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -88,6 +88,8 @@ items:
8888
href: ../cognitive-services-support-options.md?context=/azure/cognitive-services/openai/context/context
8989
- name: Intro to Azure OpenAI training
9090
href: /training/modules/explore-azure-openai/
91+
- name: Azure OpenAI Samples
92+
href: https://github.com/Azure/openai-samples
9193
- name: Region support
9294
href: https://azure.microsoft.com/global-infrastructure/services/?products=cognitive-services
9395
- name: Terms of use

0 commit comments

Comments
 (0)