farbodtavakkoli/OTel-LLM-20B-IT
farbodtavakkoli/OTel-LLM-20B-IT is a 20 billion parameter, full-parameter fine-tuned language model developed by Farbod Tavakkoli, specifically optimized for telecommunications data. Built upon the openai/gpt-oss-20b base, it is part of the OTel Family of Models, an open-source initiative for the global telecom sector. This model excels at context-grounded telecom answer generation within Retrieval-Augmented Generation (RAG) pipelines, demonstrating a +4.5 percentage point improvement in correctness over its base model on OTel-LLM held-out evaluations.
Loading preview...
OTel-LLM-20B-IT: A Specialized Telecom Language Model
OTel-LLM-20B-IT is a 20 billion parameter language model, full-parameter fine-tuned by Farbod Tavakkoli on extensive telecommunications data. It is a key component of the OTel Family of Models, an open-source effort to provide AI resources for the global telecom industry. This model is built on the openai/gpt-oss-20b base and has been specifically optimized for telecom-related tasks.
Key Capabilities
- Context-Grounded Telecom Answer Generation: Designed for Retrieval-Augmented Generation (RAG) pipelines, it generates answers based on provided telecom context.
- Improved Correctness: Achieves a +4.5 percentage point increase in LLM-as-judge correctness over its base model on held-out OTel evaluation data.
- Specialized Training Data: Fine-tuned on a curated dataset of 326,767 high-confidence telecom examples, including arXiv papers, 3GPP standards, GSMA documents, IETF RFCs, and O-RAN specifications.
- High Context Length: Supports a context length of 131072 tokens, enabling processing of extensive telecom documentation.
Good For
- Telecom RAG Applications: Ideal for systems requiring precise, context-grounded answers to telecom-specific queries.
- Domain-Specific QA: Suitable for question-answering within the telecommunications sector where accuracy and relevance to retrieved context are critical.
- Research and Development in Telecom AI: Provides a strong foundation for further exploration and application of AI in telecommunications, leveraging its specialized training and performance improvements.