Allenai
About Allenai
Ai2 was founded in 2014 with the mission of conducting high-impact AI research and engineering in service of the common good.
We are a Seattle based non-profit AI research institute founded in 2014 by the late Paul Allen. We develop foundational AI research and innovation to deliver real-world impact through large-scale open models, data, robotics, conservation, and beyond.
We unite the best and brightest scientific and engineering minds to explore the potential of truly open AI. Through close collaboration, we rapidly identify, define, and act on the most exciting and promising new ideas in our industry.
To us, a variety of skills, experiences, and backgrounds is key to building the safest, most effective open AI technology. We invest in research into accessibility and inclusive user experiences, intentional hiring practices, and community building.
Website ↗Documentation ↗GitHub ↗Hugging Face ↗
Source ↗ · 2026-11-12T02:17:05.818521413Z123 indexed models
123 matching models
azureFoundry/HuggingFace/allenai-hvila-row-layoutlm-finetuned-grotoap2@2
`allenai/hvila-row-layoutlm-finetuned-grotoap2` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/allenai/hvila-row-layoutlm-finetuned-grotoap2) - [`token-classification` Task on Hugging Face](https://huggingface.co/tasks/token-classificati
azureFoundry/HuggingFace/allenai-ivila-block-layoutlm-finetuned-docbank@3
`allenai/ivila-block-layoutlm-finetuned-docbank` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/allenai/ivila-block-layoutlm-finetuned-docbank) - [`token-classification` Task on Hugging Face](https://huggingface.co/tasks/token-classifica
azureFoundry/HuggingFace/allenai-ivila-block-layoutlm-finetuned-grotoap2@3
`allenai/ivila-block-layoutlm-finetuned-grotoap2` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/allenai/ivila-block-layoutlm-finetuned-grotoap2) - [`token-classification` Task on Hugging Face](https://huggingface.co/tasks/token-classifi
azureFoundry/HuggingFace/allenai-ivila-row-layoutlm-finetuned-s2vl-v2@6
`allenai/ivila-row-layoutlm-finetuned-s2vl-v2` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/allenai/ivila-row-layoutlm-finetuned-s2vl-v2) - [`token-classification` Task on Hugging Face](https://huggingface.co/tasks/token-classification
azureFoundry/HuggingFace/allenai-led-base-16384@7
`allenai/led-base-16384` 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 bi
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/allenai-led-large-16384@7
`allenai/led-large-16384` 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
azureFoundry/HuggingFace/allenai-led-large-16384-arxiv@4
`allenai/led-large-16384-arxiv` 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,
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-allenai/models/llama-3.1-tulu-3.1-8b@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-allenai/models/llama-3.1-tulu-3-405b@001
- Input modalities
- text
- Output modalities
- text
huggingface/allenai/Llama-3.1-Tulu-3-70B-DPO
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 42.224%
vertexAI/publishers/hf-allenai/models/llama-3.1-tulu-3-70b-sft@001
Benchmarks
- Open LLM Leaderboard v2: 38.848%
vertexAI/publishers/hf-allenai/models/llama-3.1-tulu-3-8b-dpo@001
Benchmarks
- Open LLM Leaderboard v2: 26.464%
azureFoundry/HuggingFace/allenai-llama-3.1-tulu-3-8b-rm@1
`allenai/Llama-3.1-Tulu-3-8B-RM` powered by Text Generation Inference (TGI) - [Example Notebook](https://aka.ms/hugging-face-text-generation-streaming-online-endpoint) - [Original Model Card](https://huggingface.co/allenai/Llama-3.1-Tulu-3-8B-RM) - [Text Generation Inference Doc
Benchmarks
- Open LLM Leaderboard v2: 4.235%
vertexAI/publishers/hf-allenai/models/llama-3.1-tulu-3-8b-sft@001
- Input modalities
- text
- Output modalities
- text
Benchmarks
- Open LLM Leaderboard v2: 22.597%
huggingface/allenai/longformer-base-4096
azureFoundry/HuggingFace/allenai-longformer-large-4096-finetuned-triviaqa@4
`allenai/longformer-large-4096-finetuned-triviaqa` is a pre-trained language model available on the Hugging Face Hub. It's specifically designed for the `question-answering` task in the `transformers` library. If you want to learn more about the model's architecture, hyperparamet
- Input modalities
- text
- Output modalities
- text
azureFoundry/HuggingFace/allenai-macaw-large@5
`allenai/macaw-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 biase
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-allenai/models/molmo2-4b@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput