farbodtavakkoli/OTel-LLM-7B-IT

OTel-LLM-7B-IT: A Specialized Telecom Language Model

OTel-LLM-7B-IT is a 7 billion parameter language model developed by farbodtavakkoli, built upon the allenai/OLMo-3-7B base model. It is a key component of the OTel Family of Models, an open-source initiative focused on creating industry-standard AI for the global telecommunications sector.

Key Capabilities & Training

This model has undergone full parameter fine-tuning using an extensive, expert-curated dataset of telecom-focused information. The training data includes arXiv telecom papers, 3GPP standards, telecom Wikipedia, GSMA documents, IETF RFCs, industry whitepapers, and O-RAN specifications, contributed by institutions like Yale University, GSMA, NetoAI, Khalifa University, University of Leeds, and The University of Texas at Dallas.

Intended Use & Unique Features

OTel-LLM-7B-IT is designed to power end-to-end Retrieval-Augmented Generation (RAG) pipelines for telecommunications. It functions as the LLM component, generating accurate responses grounded in retrieved context. A notable feature is its abstention training: the model is optimized to decline to answer rather than hallucinate if it does not receive sufficient context. This makes it particularly suitable for applications requiring high factual accuracy within the telecom domain, rather than open-ended general question answering. It is licensed under Apache 2.0.