Back to Semantic Kernel

Models

dotnet/docs/MODELS.md

latest14.8 KB
Original Source

Models

This document describes the planned models to be supported by Semantic Kernel along with their current status. If you are interested in contributing to the development of a model, please use the attached links to the GitHub issues and comment that you're wanting to help.

Supported deployment types

In the core Semantic Kernel repo, we plan on supporting up to four deployment types of each model:

To support these different deployment types, we will follow a similar pattern to the Azure OpenAI and OpenAI connectors. Each connector uses the same underlying model and abstractions, but the connector constructors may take different parameters. For example, the Azure OpenAI connector expects an Azure endpoint and key, whereas the OpenAI connector expects an OpenAI organization ID and API key.

If there is another deployment type you'd like to see supported, please open an issue. We'll either work with you to add support for it or help you create a custom repository and NuGet package for your use case.

Planned models

The following models are currently prioritized for development. If you'd like to see a model added to this list, please open an issue. If you'd like to contribute to the development of a model, please comment on the issue that you're wanting to help.

Please note that not all of the model interfaces are defined yet. As part of contributing a new model, we'll work with you to define the interface and then implement it. As part of implementing the connector, you may also determine that the currently planned interface isn't the best fit for the model. If that's the case, we'll work with you to update the interface.

OpenAI

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P0GPT-3.5-turboCompleteIChatCompletionOpenAI APIN/AN/AN/A
P0GPT-3.5-turboCompleteIChatCompletionAzure AIN/AN/AN/A
P0GPT-4CompleteIChatCompletionOpenAI APIN/AN/AN/A
P0GPT-4CompleteIChatCompletionAzure AIN/AN/AN/A
P0GPT-4vCompleteIChatCompletionOpenAI APIN/AN/AN/A
P0GPT-4vCompleteIChatCompletionAzure AIN/AN/AN/A
P0text-embedding-ada-002PreviewIEmbeddingGenerationOpenAI APIN/AN/AN/A
P0text-embedding-ada-002PreviewIEmbeddingGenerationAzure AIN/AN/AN/A
P0DALL·E 3PreviewITextToImageOpenAI APIN/AN/AN/A
P0DALL·E 3PreviewITextToImageAzure AIN/AN/AN/A
P0Text-to-speechCompleteITextToSpeechOpenAI APITBDdmytrostrukTBD
P0Speech-to-textCompleteISpeechRecognitionOpenAI APITBDdmytrostrukTBD
P1openai-whisper-large-v3Not startedISpeechRecognitionAzure AITBDTBDTBD
P1openai-whisper-large-v3Not startedISpeechRecognitionHugging FaceTBDTBDTBD
P2ModerationIn ProgressITextClassificationOpenAI API#5062Krzysztof318MarkWallace
P2clip-vit-base-patch32Not startedIZeroShotImageClassificationAzure AITBDTBDTBD
P2clip-vit-base-patch32Not startedIZeroShotImageClassificationHugging FaceTBDTBDTBD

Microsoft

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P0microsoft-phi-1-5Not startedITextGenerationAzure AITBDTBDTBD
P0microsoft-phi-1-5Not startedITextGenerationHugging FaceTBDTBDTBD
P0microsoft-phi-2Not startedITextGenerationAzure AITBDTBDTBD
P0microsoft-phi-2Not startedITextGenerationHugging FaceTBDTBDTBD
P2resnet-50Not startedIImageClassificationAzure AITBDTBDTBD
P2resnet-50Not startedIImageClassificationHugging FaceTBDTBDTBD

Google

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P0gemini-proIn ProgressIChatCompletionGoogle APITBDKrzysztof318RogerBarreto
P0gemini-pro-visionIn ProgressIChatCompletionGoogle APITBDKrzysztof318RogerBarreto
P0gemini-ultraIn ProgressIChatCompletionGoogle APITBDKrzysztof318RogerBarreto
P0embedding-001In ProgressIEmbeddingGenerationGoogle APITBDKrzysztof318RogerBarreto

Facebook

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P0Llama-2-7b-chatNot startedIChatCompletionAzure AITBDTBDTBD
P0Llama-2-7b-chatNot startedIChatCompletionHugging FaceTBDTBDTBD
P0Llama-2-13b-chatNot startedIChatCompletionAzure AITBDTBDTBD
P0Llama-2-13b-chatNot startedIChatCompletionHugging FaceTBDTBDTBD
P0Llama-2-70b-chatNot startedIChatCompletionAzure AITBDTBDTBD
P0Llama-2-70b-chatNot startedIChatCompletionHugging FaceTBDTBDTBD
P0CodeLlama-7b-Instruct-hfNot startedITextGenerationAzure AITBDTBDTBD
P0CodeLlama-7b-Instruct-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P0CodeLlama-13b-Instruct-hfNot startedITextGenerationAzure AITBDTBDTBD
P0CodeLlama-13b-Instruct-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P0CodeLlama-34b-Instruct-hfNot startedITextGenerationAzure AITBDTBDTBD
P0CodeLlama-34b-Instruct-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P1Llama-2-7bNot startedITextGenerationAzure AITBDTBDTBD
P1Llama-2-7bNot startedITextGenerationOllamaTBDTBDTBD
P1Llama-2-7bNot startedITextGenerationHugging FaceTBDTBDTBD
P1Llama-2-13bNot startedITextGenerationAzure AITBDTBDTBD
P1Llama-2-13bNot startedITextGenerationOllamaTBDTBDTBD
P1Llama-2-13bNot startedITextGenerationHugging FaceTBDTBDTBD
P1Llama-2-70bNot startedITextGenerationAzure AITBDTBDTBD
P1Llama-2-70bNot startedITextGenerationOllamaTBDTBDTBD
P1Llama-2-70bNot startedITextGenerationHugging FaceTBDTBDTBD
P1CodeLlama-7b-hfNot startedITextGenerationAzure AITBDTBDTBD
P1CodeLlama-7b-hfNot startedITextGenerationOllamaTBDTBDTBD
P1CodeLlama-7b-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P1CodeLlama-13b-hfNot startedITextGenerationAzure AITBDTBDTBD
P1CodeLlama-13b-hfNot startedITextGenerationOllamaTBDTBDTBD
P1CodeLlama-13b-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P1CodeLlama-34b-hfNot startedITextGenerationAzure AITBDTBDTBD
P1CodeLlama-34b-hfNot startedITextGenerationOllamaTBDTBDTBD
P1CodeLlama-34b-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P1CodeLlama-7b-Python-hfNot startedITextGenerationAzure AITBDTBDTBD
P1CodeLlama-7b-Python-hfNot startedITextGenerationOllamaTBDTBDTBD
P2CodeLlama-7b-Python-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P2CodeLlama-13b-Python-hfNot startedITextGenerationAzure AITBDTBDTBD
P2CodeLlama-13b-Python-hfNot startedITextGenerationOllamaTBDTBDTBD
P2CodeLlama-13b-Python-hfNot startedITextGenerationHugging FaceTBDTBDTBD
P2CodeLlama-34b-Python-hfNot startedITextGenerationAzure AITBDTBDTBD
P2CodeLlama-34b-Python-hfNot startedITextGenerationOllamaTBDTBDTBD
P2CodeLlama-34b-Python-hfNot startedITextGenerationHugging FaceTBDTBDTBD

Mistral

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P2Mistral-7B-v0.2Not startedIChatCompletionMistral APITBDTBDTBD
P2Mistral-7B-v0.2Not startedIChatCompletionOllamaTBDTBDTBD
P2Mistral-7B-v0.1Not startedIChatCompletionAzure AITBDTBDTBD
P2Mistral-7B-v0.1Not startedIChatCompletionHugging FaceTBDTBDTBD
P2Mistral-7B-Instruct-v01Not startedIChatCompletionAzure AITBDTBDTBD
P2Mistral-7B-Instruct-v01Not startedIChatCompletionHugging FaceTBDTBDTBD
P2Mixtral-8X7B-v0.1Not startedIChatCompletionMistral APITBDTBDTBD
P2Mixtral-8X7B-v0.1Not startedIChatCompletionAzure AITBDTBDTBD
P2Mixtral-8X7B-v0.1Not startedIChatCompletionHugging FaceTBDTBDTBD
P2mistral-mediumNot startedIChatCompletionMistral APITBDTBDTBD
P2mistral-embedNot startedIChatCompletionMistral APITBDTBDTBD

Other

PriorityModelStatusInterfaceDeployment typeGitHub issueDeveloperReviewer
P0wav2vec2-large-xlsr-53-englishNot startedISpeechRecognitionAzure AITBDTBDTBD
P1wav2vec2-large-xlsr-53-englishNot startedISpeechRecognitionHugging FaceTBDTBDTBD
P2bert-base-uncasedNot startedIFillMaskAzure AITBDTBDTBD
P2bert-base-uncasedNot startedIFillMaskHugging FaceTBDTBDTBD
P2roberta-largeNot startedIFillMaskAzure AITBDTBDTBD
P2roberta-largeNot startedIFillMaskHugging FaceTBDTBDTBD
P1stable-diffusion-xl-base-1.0Not startedITextToImageAzure AITBDTBDTBD
P1stable-diffusion-xl-base-1.0Not startedITextToImageHugging FaceTBDTBDTBD