farbodtavakkoli/OTel-LLM-24B-IT

Hugging Face
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Mar 10, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

OTel-LLM-24B-IT is a 24 billion parameter language model developed by farbodtavakkoli, fine-tuned specifically for the telecommunications domain. Built upon the LiquidAI/LFM2-24B-A2B base model, it excels at generating accurate responses grounded in telecom-specific contexts. This model is designed as part of an end-to-end Retrieval-Augmented Generation (RAG) pipeline for telecommunications, optimized to decline answers if context is insufficient, preventing hallucination.

Loading preview...

OTel-LLM-24B-IT: A Specialized Telecom Language Model

OTel-LLM-24B-IT is a 24 billion parameter language model developed by farbodtavakkoli, specifically fine-tuned for the telecommunications sector. It is built on the LiquidAI/LFM2-24B-A2B base model and represents a key component of the OTel Family of Models, an open-source initiative aimed at establishing industry-standard AI for global telecommunications.

Key Capabilities

  • Telecom Domain Expertise: Fine-tuned on extensive telecommunications data, including arXiv papers, 3GPP standards, GSMA documents, IETF RFCs, and O-RAN specifications, curated by over 100 domain experts from institutions like Yale University and Khalifa University.
  • RAG Pipeline Integration: Designed to function as the generative component within an end-to-end Retrieval-Augmented Generation (RAG) pipeline, working alongside OTel Embedding and Reranker models.
  • Context-Grounded Generation: Features abstention training, meaning the model is optimized to decline answering if it does not receive sufficient context, thereby minimizing hallucination and ensuring factual accuracy.
  • Open-Source Initiative: Part of a broader open-source effort providing datasets and models for the telecom industry.

Good For

  • Telecommunications RAG Systems: Ideal for building robust RAG applications that require accurate, context-grounded responses within the telecom domain.
  • Information Retrieval: Generating summaries or answers from technical telecom documentation, standards, and research papers.
  • Specialized AI Development: Developers working on AI solutions for the telecommunications industry who need a model with deep domain understanding and hallucination control.