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

ai-forever/ru-en-RoSBERTa

vertexAI/publishers/hf-ai-forever/models/ru-en-rosberta@001

Capabilities
embeddings

Benchmarks

  • MTEB: 62.577%

ai-forever/ruGPT-3.5-13B

azureFoundry/HuggingFace/ai-forever-rugpt-3.5-13b@1

`ai-forever/ruGPT-3.5-13B` 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/ruGPT-3.5-13B) - [Text Generation Inference Documentation](

Input modalities
text
Output modalities
text

ai-forever/rugpt3large_based_on_gpt2

vertexAI/publishers/hf-ai-forever/models/rugpt3large_based_on_gpt2@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 29.527%

ai-forever/ruRoberta-large

azureFoundry/HuggingFace/ai-forever-ruroberta-large@10

`ai-forever/ruRoberta-large` 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, y

ai-forever/ruT5-base

azureFoundry/HuggingFace/ai-forever-rut5-base@5

`ai-forever/ruT5-base` 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 bias

Input modalities
text
Output modalities
text

ai-forever/ruT5-large

azureFoundry/HuggingFace/ai-forever-rut5-large@5

`ai-forever/ruT5-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 bia

Input modalities
text
Output modalities
text

ai-forever/sage-fredt5-distilled-95m

azureFoundry/HuggingFace/ai-forever-sage-fredt5-distilled-95m@1

`ai-forever/sage-fredt5-distilled-95m` 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/sage-fredt5-distilled-95m) - [Text Generation I

Input modalities
text
Output modalities
text

ai-forever/sage-fredt5-large

azureFoundry/HuggingFace/ai-forever-sage-fredt5-large@1

`ai-forever/sage-fredt5-large` 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/sage-fredt5-large) - [Text Generation Inference Documen

Input modalities
text
Output modalities
text

ai-forever/sage-v1.1.0

azureFoundry/HuggingFace/ai-forever-sage-v1.1.0@1

`ai-forever/sage-v1.1.0` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/ai-forever/sage-v1.1.0) - [Text Generation Inference Documentation](http

Input modalities
text
Output modalities
text

ai-human-lab/EEVE-Korean-10.8B-DPO-v1.0

azureFoundry/HuggingFace/ai-human-lab-eeve-korean-10.8b-dpo-v1.0@1

`ai-human-lab/EEVE-Korean-10.8B-DPO-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/ai-human-lab/EEVE-Korean-10.8B-DPO-v1.0) - [Text Genera

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 30.303%

ai-human-lab/EEVE-Korean-10.8B-instruct-v4-sft

azureFoundry/HuggingFace/ai-human-lab-eeve-korean-10.8b-instruct-v4-sft@1

`ai-human-lab/EEVE-Korean-10.8B-instruct-v4-sft` 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-human-lab/EEVE-Korean-10.8B-instruct-v4-sft)

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 35.619%

ai-human-lab/EEVE-Korean-10.8B-SFT-v0.1

azureFoundry/HuggingFace/ai-human-lab-eeve-korean-10.8b-sft-v0.1@1

`ai-human-lab/EEVE-Korean-10.8B-SFT-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/ai-human-lab/EEVE-Korean-10.8B-SFT-v0.1) - [Text Genera

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

Benchmarks

  • Open Ko-LLM Leaderboard: 27.273%

ai-human-lab/EEVE-Korean_Instruct-10.8B-expo

azureFoundry/HuggingFace/ai-human-lab-eeve-korean-instruct-10.8b-expo@1

`ai-human-lab/EEVE-Korean_Instruct-10.8B-expo` 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-human-lab/EEVE-Korean_Instruct-10.8B-expo) - [T

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 53.588

AIJUUD/juud-Mistral-7B

azureFoundry/HuggingFace/aijuud-juud-mistral-7b@1

`AIJUUD/juud-Mistral-7B` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIJUUD/juud-Mistral-7B) - [Text Generation Inference Documentation](http

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 61.721%

AIJUUD/juud-Mistral-7B-dpo

azureFoundry/HuggingFace/aijuud-juud-mistral-7b-dpo@1

`AIJUUD/juud-Mistral-7B-dpo` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/AIJUUD/juud-Mistral-7B-dpo) - [Text Generation Inference Documentati

Input modalities
text
Output modalities
text

Benchmarks

  • Open Ko-LLM Leaderboard: 87.135%
  • Open LLM Leaderboard v1: 60.89%

aiknowyou/mt5-base-it-paraphraser

azureFoundry/HuggingFace/aiknowyou-mt5-base-it-paraphraser@3

`aiknowyou/mt5-base-it-paraphraser` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/aiknowyou/mt5-base-it-paraphraser) - [Text Generation Inferen

Input modalities
text
Output modalities
text

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