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
# How to use Cohere Command chat models with Azure AI studio
16
+
# How to use Cohere Command chat models
17
17
18
-
In this article, you learn about Cohere Command chat models and how to use them with Azure AI studio.
18
+
In this article, you learn about Cohere Command chat models and how to use them.
19
19
The Cohere family of models includes various models optimized for different use cases, including chat completions, embeddings, and rerank. Cohere models are optimized for various use cases that include reasoning, summarization, and question answering.
20
20
21
21
@@ -62,6 +62,9 @@ The following models are available:
62
62
63
63
---
64
64
65
+
> [!TIP]
66
+
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
67
+
65
68
## Prerequisites
66
69
67
70
To use Cohere Command chat models with Azure AI studio, you need the following prerequisites:
@@ -93,9 +96,6 @@ pip install azure-ai-inference
93
96
94
97
Read more about the [Azure AI inference package and reference](https://aka.ms/azsdk/azure-ai-inference/python/reference).
95
98
96
-
> [!TIP]
97
-
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
98
-
99
99
## Work with chat completions
100
100
101
101
In this section, you use the [Azure AI model inference API](https://aka.ms/azureai/modelinference) with a chat completions model for chat.
Cohere Command chat models 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.
290
290
@@ -497,6 +497,9 @@ The following models are available:
497
497
498
498
---
499
499
500
+
> [!TIP]
501
+
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
502
+
500
503
## Prerequisites
501
504
502
505
To use Cohere Command chat models with Azure AI studio, you need the following prerequisites:
@@ -526,9 +529,6 @@ Once you have these prerequisites, install the Azure Inference library for JavaS
526
529
npm install @azure-rest/ai-inference
527
530
```
528
531
529
-
> [!TIP]
530
-
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
531
-
532
532
## Work with chat completions
533
533
534
534
In this section, you use the [Azure AI model inference API](https://aka.ms/azureai/modelinference) with a chat completions model for chat.
@@ -738,7 +738,7 @@ var response = await client.path("/chat/completions").post({
738
738
});
739
739
```
740
740
741
-
### Define tools
741
+
### Use tools
742
742
743
743
Cohere Command chat models 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.
744
744
@@ -946,6 +946,9 @@ The following models are available:
946
946
947
947
---
948
948
949
+
> [!TIP]
950
+
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
951
+
949
952
## Prerequisites
950
953
951
954
To use Cohere Command chat models with Azure AI studio, you need the following prerequisites:
@@ -998,9 +1001,6 @@ using System.Text.Json.Serialization;
998
1001
using System.Reflection;
999
1002
```
1000
1003
1001
-
> [!TIP]
1002
-
> Additionally, Cohere supports the use of a tailored APIfor use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
1003
-
1004
1004
## Work with chat completions
1005
1005
1006
1006
In this section, you use the [Azure AI model inference API](https://aka.ms/azureai/modelinference) with a chat completions model for chat.
Cohere Command chat models 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.
1213
1213
@@ -1420,6 +1420,9 @@ The following models are available:
1420
1420
1421
1421
---
1422
1422
1423
+
> [!TIP]
1424
+
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
1425
+
1423
1426
## Prerequisites
1424
1427
1425
1428
To use Cohere Command chat models with Azure AI studio, you need the following prerequisites:
@@ -1442,9 +1445,6 @@ Models deployed with the [Azure AI model inference API](https://aka.ms/azureai/m
1442
1445
* To construct the requests, you need to pass in the endpoint URL. The endpoint URL has the form `https://your-host-name.your-azure-region.inference.ai.azure.com`, where `your-host-name`` is your unique model deployment host name and `your-azure-region`` is the Azure region where the model is deployed (for example, eastus2).
1443
1446
* Depending on your model deployment and authentication preference, you need either a key to authenticate against the service, or Microsoft Entra ID credentials. The key is a 32-character string.
1444
1447
1445
-
> [!TIP]
1446
-
> Additionally, Cohere supports the use of a tailored API for use with specific features of the model. To use the model-provider specific API, check [Cohere documentation](https://docs.cohere.com/reference/about) or see the [inference examples](#more-inference-examples) section to code examples.
1447
-
1448
1448
## Work with chat completions
1449
1449
1450
1450
In this section, you use the [Azure AI model inference API](https://aka.ms/azureai/modelinference) with a chat completions model for chat.
Cohere Command chat models 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.
# How to use Jais chat models with Azure AI studio
16
+
# How to use Jais chat models
17
17
18
-
In this article, you learn about Jais chat models and how to use them with Azure AI studio.
18
+
In this article, you learn about Jais chat models and how to use them.
19
19
JAIS 30b Chat is an autoregressive bi-lingual LLM for **Arabic** & **English**. The tuned versions use supervised fine-tuning (SFT). The model is fine-tuned with both Arabic and English prompt-response pairs. The fine-tuning datasets included a wide range of instructional data across various domains. The model covers a wide range of common tasks including question answering, code generation, and reasoning over textual content. To enhance performance in Arabic, the Core42 team developed an in-house Arabic dataset and translated some open-source English instructions into Arabic.
20
20
21
21
***Context length:** JAIS supports a context length of 8K.
# How to use Jamba-Instruct chat models with Azure AI studio
16
+
# How to use Jamba-Instruct chat models
17
17
18
-
In this article, you learn about Jamba-Instruct chat models and how to use them with Azure AI studio.
18
+
In this article, you learn about Jamba-Instruct chat models and how to use them.
19
19
The Jamba-Instruct model is AI21's production-grade Mamba-based large language model (LLM) which uses AI21's hybrid Mamba-Transformer architecture. It's an instruction-tuned version of AI21's hybrid structured state space model (SSM) transformer Jamba model. The Jamba-Instruct model is built for reliable commercial use with respect to quality and performance.
# How to use Meta Llama chat models with Azure AI studio
16
+
# How to use Meta Llama chat models
17
17
18
-
In this article, you learn about Meta Llama chat models and how to use them with Azure AI studio.
18
+
In this article, you learn about Meta Llama chat models and how to use them.
19
19
Meta Llama 2 and 3 models and tools are a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. The model family also includes fine-tuned versions optimized for dialogue use cases with reinforcement learning from human feedback (RLHF).
0 commit comments