azureFoundry/HuggingFace/h2oai-danube2-singlish-finetuned@1
`h2oai/danube2-singlish-finetuned` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/danube2-singlish-finetuned) - [Text Generation Inference
- Input modalities
- text
- Output modalities
- text
huggingface/h2oai/h2o-danube-1.8b-base
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 39.12%
vertexAI/publishers/hf-h2oai/models/h2o-danube-1.8b-chat@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 44.491%
- Open LLM Leaderboard v2: 6.954%
huggingface/h2oai/h2o-danube-1.8b-sft
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 43.679%
huggingface/h2oai/h2o-danube2-1.8b-base
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 48.724%
huggingface/h2oai/h2o-danube2-1.8b-chat
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 49.258%
huggingface/h2oai/h2o-danube2-1.8b-sft
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 47.36%
azureFoundry/HuggingFace/h2oai-h2o-danube3.1-4b-chat@1
`h2oai/h2o-danube3.1-4b-chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/h2o-danube3.1-4b-chat) - [Text Generation Inference Documenta
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 16.412%
huggingface/h2oai/h2o-danube3-4b-base
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 10.091%
azureFoundry/HuggingFace/h2oai-h2o-danube3-4b-chat@1
`h2oai/h2o-danube3-4b-chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/h2o-danube3-4b-chat) - [Text Generation Inference Documentation
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 11.571%
vertexAI/publishers/hf-h2oai/models/h2o-danube3-500m-base@001
- Input modalities
- text
- Output modalities
- text
huggingface/h2oai/h2o-danube3-500m-chat
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 5.204%
azureFoundry/HuggingFace/h2oai-h2ogpt-4096-llama2-13b-chat@1
`h2oai/h2ogpt-4096-llama2-13b-chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/h2ogpt-4096-llama2-13b-chat) - [Text Generation Inferen
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/h2oai-h2ogpt-4096-llama2-70b-chat@1
`h2oai/h2ogpt-4096-llama2-70b-chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/h2ogpt-4096-llama2-70b-chat) - [Text Generation Inferen
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/h2oai-h2ogpt-4096-llama2-7b-chat@1
`h2oai/h2ogpt-4096-llama2-7b-chat` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/h2oai/h2ogpt-4096-llama2-7b-chat) - [Text Generation Inference
- Input modalities
- text
- Output modalities
- text
huggingface/h2oai/h2ogpt-gm-oasst1-en-1024-12b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 40.651%
huggingface/h2oai/h2ogpt-gm-oasst1-en-1024-20b
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 42.582%
huggingface/h2oai/h2ogpt-gm-oasst1-en-1024-open-llama-7b-preview-400bt
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v1: 39.895%