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 ↗ · 2026-11-12T02:17:05.818521413Z

123 indexed models

123 matching models

allenai/primera-multi_lexsum-source-short

azureFoundry/HuggingFace/allenai-primera-multi-lexsum-source-short@3

`allenai/primera-multi_lexsum-source-short` 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,

Input modalities
text
Output modalities
text

allenai/scirepeval_ctrl

vertexAI/publishers/hf-allenai/models/scirepeval_ctrl@001

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

allenai/scitulu-70b

vertexAI/publishers/hf-allenai/models/scitulu-70b@001

Input modalities
text
Output modalities
text

allenai/specter

azureFoundry/HuggingFace/allenai-specter@1

`allenai/specter` powered by Hugging Face Inference Toolkit - [Original Model Card](https://huggingface.co/allenai/specter) - [`feature-extraction` Task on Hugging Face](https://huggingface.co/tasks/feature-extraction) ### Send Request You can use cURL or any REST Client to se

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

allenai/specter2_aug2023refresh_base

azureFoundry/HuggingFace/allenai-specter2-aug2023refresh-base@1

`allenai/specter2_aug2023refresh_base` powered by Text Embeddings Inference (TEI) - [Original Model Card](https://huggingface.co/allenai/specter2_aug2023refresh_base) - [Text Embeddings Inference Documentation](https://huggingface.co/docs/text-embeddings-inference) ### Send Req

Input modalities
text
Output modalities
embeddings
Capabilities
embeddings

allenai/tk-instruct-3b-def

azureFoundry/HuggingFace/allenai-tk-instruct-3b-def@3

`allenai/tk-instruct-3b-def` 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, an

Input modalities
text
Output modalities
text

allenai/tk-instruct-3b-def-pos

azureFoundry/HuggingFace/allenai-tk-instruct-3b-def-pos@3

`allenai/tk-instruct-3b-def-pos` 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

allenai/tk-instruct-base-def-pos

azureFoundry/HuggingFace/allenai-tk-instruct-base-def-pos@3

`allenai/tk-instruct-base-def-pos` 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, limitatio

Input modalities
text
Output modalities
text

allenai/tulu-2-7b

vertexAI/publishers/hf-allenai/models/tulu-2-7b@001

Input modalities
text
Output modalities
text

allenai/tulu-2-dpo-70b

vertexAI/publishers/hf-allenai/models/tulu-2-dpo-70b@001

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 73.765%

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