Microsoft Foundry

About Microsoft Foundry

Kickstart innovation with Microsoft Foundry, the AI app and agent factory designed to accelerate AI-driven, cloud-native development across industries.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T03:22:24.068797307Z

Service status

unknown

Current inference service status unverified

Official status page ↗

13,283 indexed models

13,283 matching models

AidenH20/DNABERT-500down

azureFoundry/HuggingFace/aidenh20-dnabert-500down@3

`AidenH20/DNABERT-500down` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text-classification` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and b

AIdenU/Mistral-7b-ko-Y24-DPO_v0.1

azureFoundry/HuggingFace/aidenu-mistral-7b-ko-y24-dpo-v0.1@1

`AIdenU/Mistral-7b-ko-Y24-DPO_v0.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIdenU/Mistral-7b-ko-Y24-DPO_v0.1) - [Text Generation Inferen

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 23.737%

AIdenU/Mistral-7B-v0.2-ko-Y24_v1.0

azureFoundry/HuggingFace/aidenu-mistral-7b-v0.2-ko-y24-v1.0@1

`AIdenU/Mistral-7B-v0.2-ko-Y24_v1.0` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIdenU/Mistral-7B-v0.2-ko-Y24_v1.0) - [Text Generation Infer

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 85.38%

AIdenU/Mistral-7B-v0.2-ko-Y24_v2.0

azureFoundry/HuggingFace/aidenu-mistral-7b-v0.2-ko-y24-v2.0@1

`AIdenU/Mistral-7B-v0.2-ko-Y24_v2.0` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIdenU/Mistral-7B-v0.2-ko-Y24_v2.0) - [Text Generation Infer

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 61.404%

AIdenU/SOLAR-10.7b-ko-Y24_v1.0

azureFoundry/HuggingFace/aidenu-solar-10.7b-ko-y24-v1.0@1

`AIdenU/SOLAR-10.7b-ko-Y24_v1.0` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIdenU/SOLAR-10.7b-ko-Y24_v1.0) - [Text Generation Inference Doc

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 89.474%

AIDX-ktds/ktdsbaseLM-v0.14-onbased-llama3.1

azureFoundry/HuggingFace/aidx-ktds-ktdsbaselm-v0.14-onbased-llama3.1@1

`AIDX-ktds/ktdsbaseLM-v0.14-onbased-llama3.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.14-onbased-llama3.1) - [Tex

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 65.027%

AIDX-ktds/ktdsbaseLM-v0.15-onbased-llama3.1

azureFoundry/HuggingFace/aidx-ktds-ktdsbaselm-v0.15-onbased-llama3.1@1

`AIDX-ktds/ktdsbaseLM-v0.15-onbased-llama3.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.15-onbased-llama3.1) - [Tex

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 57.619%

AIDX-ktds/ktdsbaseLM-v0.16-onbased-llama3.1

azureFoundry/HuggingFace/aidx-ktds-ktdsbaselm-v0.16-onbased-llama3.1@1

`AIDX-ktds/ktdsbaseLM-v0.16-onbased-llama3.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.16-onbased-llama3.1) - [Tex

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 57.619%

AIDX-ktds/ktdsbaseLM-v0.2-onbased-llama3.1

azureFoundry/HuggingFace/aidx-ktds-ktdsbaselm-v0.2-onbased-llama3.1@1

`AIDX-ktds/ktdsbaseLM-v0.2-onbased-llama3.1` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIDX-ktds/ktdsbaseLM-v0.2-onbased-llama3.1) - [Text

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 51.944%

ai-forever/FRED-T5-1.7B

azureFoundry/HuggingFace/ai-forever-fred-t5-1.7b@5

`ai-forever/FRED-T5-1.7B` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and b

Input modalities
text
Output modalities
text

ai-forever/FRED-T5-large

azureFoundry/HuggingFace/ai-forever-fred-t5-large@4

`ai-forever/FRED-T5-large` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `text2text-generation` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and

Input modalities
text
Output modalities
text

ai-forever/FRIDA

azureFoundry/HuggingFace/ai-forever-frida@1

`ai-forever/FRIDA` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/ai-forever/FRIDA) - [Text Generation Inference Documentation](https://huggingf

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • MTEB: 74.028%

ai-forever/mGPT

vertexAI/publishers/hf-ai-forever/models/mgpt@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 27.605%

ai-forever/mGPT-13B

vertexAI/publishers/hf-ai-forever/models/mgpt-13b@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 24.242%

ai-forever/ruBert-base

azureFoundry/HuggingFace/ai-forever-rubert-base@5

`ai-forever/ruBert-base` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `fill-mask` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparameters, limitations, and biases, you c

ai-forever/ruBert-large

azureFoundry/HuggingFace/ai-forever-rubert-large@6

`ai-forever/ruBert-large` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/ai-forever/ruBert-large) - [`fill-mask` Task on Hugging Face](https://huggingface.co/tasks/fill-mask) ### Send Request You can use cURL or any REST Client to send

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace