farbodtavakkoli/OTel-LLM-1.7B-IT

OTel-LLM-1.7B-IT: A Telecom-Specialized Language Model

OTel-LLM-1.7B-IT is a 1.7 billion parameter language model, part of the OTel Family of Models, an open-source initiative by farbodtavakkoli to develop AI for the global telecommunications sector. Fine-tuned from the Qwen/Qwen3-1.7B base model, it is specifically trained on extensive telecom-focused data curated by over 100 domain experts from institutions like Yale University, GSMA, NetoAI, Khalifa University, and the University of Leeds.

Key Capabilities

• Domain Specialization: Highly proficient in understanding and generating content related to telecommunications, including arXiv papers, 3GPP standards, GSMA documents, IETF RFCs, and O-RAN specifications.
• RAG Pipeline Integration: Designed to function as the LLM component in end-to-end Retrieval-Augmented Generation (RAG) pipelines, working alongside OTel embedding and reranker models.
• Context-Grounded Generation: Features abstention training, meaning it will decline to answer if insufficient context is provided, minimizing hallucinations and ensuring responses are grounded in retrieved information.

Good For

• Telecommunications RAG Systems: Ideal for building robust RAG applications that require accurate, domain-specific responses from telecom documentation and standards.
• Technical Information Retrieval: Generating summaries or answers based on complex telecom specifications and industry whitepapers.
• Specialized Q&A: Answering questions within the telecommunications domain where context-grounded accuracy is critical.