OLMoE-1B-7B-0924 is an open language model hosted on Hugging Face. It is designed for text-generation tasks and follows a Mixture-of-Experts architecture under the OLMo family. The model carries the pipeline tag text-generation and the tags moe and olmoe along with the language code en.
It was created by allenai and made available as a public repository on 20 July 2024. The associated training dataset is allenai/OLMoE-mix-0924 and the work is referenced in arxiv:2409.02060. Model files use the safetensors format and the implementation relies on the transformers library. As of the latest update the repository has recorded more than 1.27 million lifetime downloads.
Access occurs through the standard Hugging Face model hub where users can download weights directly. No inference providers are listed as available within the repository metadata and the model is not gated. The page indicates compatibility with existing transformers-based workflows for loading and running the model on supported hardware.
OLMoE 1B 7B 0924 sits in PulseGate's Text generation category. It focuses on providing high-performance open-source language models for research and development. It is built as an open-source project for researchers and developers in natural language processing. OLMoE 1B 7B 0924 is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
It is developed by AllenAI (United States), and it first shipped in 2024. The project is developed in the open on GitHub with 1k stars. Key capabilities include Text Generation, mixture of Experts, and Open Weights. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do