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

OTel-LLM-7B-IT, developed by farbodtavakkoli, is a 7 billion parameter language model built upon the allenai/OLMo-3-7B base. It is a key component of the OTel Family of Models, an initiative focused on creating open-source AI for the telecommunications industry. The model underwent full parameter fine-tuning using a high-quality, curated dataset.

Key Capabilities

• Domain-Specific Expertise: Trained on comprehensive telecommunications data, including GSMA Permanent Reference Documents, 3GPP Specifications, O-RAN Documentation, RFC Series, and various industry whitepapers.
• Data Curation: The training data was meticulously curated by over 200 domain experts from leading organizations like AT&T, GSMA, Purdue University, and Yale University.
• Training Infrastructure: Utilized a GPU-agnostic ScalarLM framework, leveraging both AMD and NVIDIA GPUs on TensorWave and Azure platforms.

Intended Use Cases

• RAG Applications: Optimized for Retrieval Augmented Generation (RAG) within the telecommunications domain.
• Question Answering: Excels at answering questions related to telecom specifications, standards, and technical documentation.

This model is designed to provide accurate and relevant information for complex telecom-related queries, making it a valuable tool for professionals and researchers in the sector.