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
In this article, you learn about Mistral Nemo chat model and how to use them.
22
-
Mistral AI offers two categories of models. Premium models including [Mistral Large and Mistral Small](deploy-models-mistral.md), available as serverless APIs with pay-as-you-go token-based billing. Open models including [Mistral Nemo](deploy-models-mistral-nemo.md), [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](deploy-models-mistral-open.md); available to also download and run on self-hosted managed endpoints.
21
+
In this article, you learn about Mistral Nemo chat model and how to use it.
22
+
Mistral AI offers two categories of models, namely:
23
+
24
+
-_Premium models_: These include [Mistral Large, Mistral Small, and Ministral 3B](deploy-models-mistral.md) models, and are available as serverless APIs with pay-as-you-go token-based billing.
25
+
-_Open models_: These include [Codestral](deploy-models-mistral-codestral.md) and Mistral Nemo (that are available as serverless APIs with pay-as-you-go token-based billing), and [Mixtral-8x7B-Instruct-v01, Mixtral-8x7B-v01, Mistral-7B-Instruct-v01, and Mistral-7B-v01](deploy-models-mistral-open.md)(that are available to download and run on self-hosted managed endpoints).
@@ -276,7 +280,7 @@ The following extra parameters can be passed to Mistral Nemo chat model:
276
280
277
281
### Safe mode
278
282
279
-
Mistral Nemo chat model support the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
283
+
Mistral Nemo chat model supports the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
280
284
281
285
> Always assist with care, respect, and truth. Respond with utmost utility yet securely. Avoid harmful, unethical, prejudiced, or negative content. Ensure replies promote fairness and positivity.
282
286
@@ -297,7 +301,7 @@ response = client.complete(
297
301
298
302
### Use tools
299
303
300
-
Mistral Nemo chat model support the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
304
+
Mistral Nemo chat model supports the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
301
305
302
306
The following code example creates a tool definition that is able to look from flight information from two different cities.
303
307
@@ -735,7 +739,7 @@ The following extra parameters can be passed to Mistral Nemo chat model:
735
739
736
740
### Safe mode
737
741
738
-
Mistral Nemo chat model support the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
742
+
Mistral Nemo chat model supports the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
739
743
740
744
> Always assist with care, respect, and truth. Respond with utmost utility yet securely. Avoid harmful, unethical, prejudiced, or negative content. Ensure replies promote fairness and positivity.
741
745
@@ -761,7 +765,7 @@ var response = await client.path("/chat/completions").post({
761
765
762
766
### Use tools
763
767
764
-
Mistral Nemo chat model support the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
768
+
Mistral Nemo chat model supports the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
765
769
766
770
The following code example creates a tool definition that is able to look from flight information from two different cities.
767
771
@@ -1214,7 +1218,7 @@ The following extra parameters can be passed to Mistral Nemo chat model:
1214
1218
1215
1219
### Safe mode
1216
1220
1217
-
Mistral Nemo chat model support the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
1221
+
Mistral Nemo chat model supports the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
1218
1222
1219
1223
> Always assist with care, respect, and truth. Respondwith utmost utility yet securely. Avoid harmful, unethical, prejudiced, or negative content. Ensure replies promote fairness and positivity.
Mistral Nemo chat model support the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
1244
+
Mistral Nemo chat model supports the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
1241
1245
1242
1246
The following code example creates a tool definition that is able to look from flight information from two different cities.
1243
1247
@@ -1752,7 +1756,7 @@ The following extra parameters can be passed to Mistral Nemo chat model:
1752
1756
1753
1757
### Safe mode
1754
1758
1755
-
Mistral Nemo chat model support the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
1759
+
Mistral Nemo chat model supports the parameter `safe_prompt`. You can toggle the safe prompt to prepend your messages with the following system prompt:
1756
1760
1757
1761
> Always assist with care, respect, and truth. Respond with utmost utility yet securely. Avoid harmful, unethical, prejudiced, or negative content. Ensure replies promote fairness and positivity.
Mistral Nemo chat model support the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
1792
+
Mistral Nemo chat model supports the use of tools, which can be an extraordinary resource when you need to offload specific tasks from the language model and instead rely on a more deterministic system or even a different language model. The Azure AI Model Inference API allows you to define tools in the following way.
1789
1793
1790
1794
The following code example creates a tool definition that is able to look from flight information from two different cities.
1791
1795
@@ -2030,11 +2034,11 @@ For more examples of how to use Mistral models, see the following examples and t
2030
2034
2031
2035
Quota is managed per deployment. Each deployment has a rate limit of200,000 tokens per minute and 1,000API requests per minute. However, we currently limit one deployment per model per project. Contact Microsoft Azure Support if the current rate limits aren't sufficient for your scenarios.
2032
2036
2033
-
Mistral models deployed as a serverless API are offered by MistralAI through the Azure Marketplace and integrated with Azure AI Foundry for use. You can find the Azure Marketplace pricing when deploying the model.
2037
+
Mistral models deployed as a serverless API are offered by MistralAI through Azure Marketplace and integrated with Azure AI Foundry for use. You can find Azure Marketplace pricing when deploying the model.
2034
2038
2035
-
Each time a project subscribes to a given offer from the Azure Marketplace, a new resource is created to track the costs associated with its consumption. The same resource is used to track costs associated with inference; however, multiple meters are available to track each scenario independently.
2039
+
Each time a project subscribes to a given offer from Azure Marketplace, a new resource is created to track the costs associated with its consumption. The same resource is used to track costs associated with inference; however, multiple meters are available to track each scenario independently.
2036
2040
2037
-
For more information on how to track costs, see [Monitor costs for models offered through the Azure Marketplace](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace).
2041
+
For more information on how to track costs, see [Monitor costs for models offered through Azure Marketplace](costs-plan-manage.md#monitor-costs-for-models-offered-through-the-azure-marketplace).
0 commit comments