OTel-LLM-32B-IT

OTel-LLM-32B-IT is a context-grounded telecom language model full-parameter fine-tuned on OTel telecommunications data. It is part of the OTel Family of Models, an open-source initiative to build reference AI resources for the global telecommunications sector.

Across the 17 core OTel LLM baselines, OTel fine-tuning improves context-grounded correctness over the base checkpoints by +3.3 to +9.4 percentage points.

Community Use

As of May 3, 2026, the released OTel models had been downloaded over 16 million times, and the Open Telco AI project had received 157+ pieces of media coverage worldwide.

Model Details

Model Lineage

allenai/Olmo-3.1-32B-Instruct -> OTel-LLM full-parameter post-training -> farbodtavakkoli/OTel-LLM-32B-IT

OTel vs. Base Model

Standard errors are computed with bootstrap resampling (n=1000) over the held-out OTel evaluation partition. LLM correctness is the average score from two judge models, GPT-4o mini and Claude Sonnet 3.5, each judging the answer against the retrieved context and reference answer.

Evaluation Caveats

• LLM results measure context-grounded answer generation from retrieved context, not unrestricted context-free telecom QA.
• Reported standard errors come from bootstrap resampling over the held-out evaluation partitions.
• Answer quality depends on the retriever, reranker, context window, and prompt policy around the model.
• External benchmark transfer, multilingual performance, and per-subdomain performance should be evaluated separately for production settings.

Training Data

The model was trained on telecom-focused data curated by 100+ domain experts. The raw corpus contained roughly 1.1M training points and was filtered to 326,767 higher-confidence examples.

Released datasets: OTel-LLM, OTel-Embedding, OTel-Reranker, and OTel-Safety.

The OTel datasets release derived QA/retrieval/reranking examples rather than the raw source documents.

Each released dataset includes a dataset card and Croissant metadata with Responsible AI fields for data limitations, biases, sensitive-information considerations, use cases, social impact, synthetic-data status, and provenance.

Representative Training Row

OTel-LLM rows pair a context-grounded telecom RAG prompt with a reference completion.

{
  "anchor": "How can a cell be considered to be operating in MBSFN mode for 3.84/7.68 Mcps TDD?",
  "completion": "A cell shall be considered to be operating in MBSFN mode when individual scrambling codes are assigned to all timeslots via the IE \"TDD MBSFN Information\".",
  "abstention": false,
  "n_positive_chunks": 1,
  "n_negative_chunks": 4
}

Intended Use

This model is intended for context-grounded telecom answer generation in Retrieval-Augmented Generation (RAG) pipelines. It should receive retrieved telecom context and generate an answer grounded in that context.

The model is not optimized for unrestricted context-free question answering. For questions where the retrieved context is missing or insufficient, use an abstention-aware prompt or one of the dedicated -Safety variants.

Training Recipe

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "farbodtavakkoli/OTel-LLM-32B-IT"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

prompt = """You are a precise telecom assistant in a RAG pipeline.
Use only the retrieved context to answer.

User Question
What is the purpose of the F1 interface in O-RAN?

Retrieved Contexts
CONTEXT 1
The F1 interface connects the O-RAN Distributed Unit (O-DU) to the O-RAN Central Unit (O-CU).

Answer:"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations and Responsible Use

• OTel models are domain-specific to telecommunications and should not be treated as general-purpose models.
• The current release is English-only and primarily text-centric.
• The reported OTel performance results use held-out OTel evaluation partitions and should not be interpreted as results from a fully independent external benchmark suite.
• Aggregate scores can hide subdomain variation; collaborator stress tests suggest O-RAN retrieval is comparatively strong, while academic-paper and GSMA PRD examples need further curation.
• Generated telecom content should be verified before operational, customer-facing, regulatory, safety, or network-configuration use.
• Users must comply with both the OTel release license and the upstream base-model license or terms.
• For unrestricted telecom QA without retrieved context, use a separately evaluated context-free QnA model rather than assuming this RAG-oriented checkpoint will behave optimally.

Related Models

• OTel LLM Collection
• OTel Embedding Collection
• OTel Reranker Collection

Project Resources

• Project page: https://huggingface.co/farbodtavakkoli
• Code: https://github.com/farbodtavakkoli/OTel
• Media coverage list: https://github.com/farbodtavakkoli/OTel/blob/main/docs/OTel-1.0-media-coverage.md

Citation

@inproceedings{tavakkoli2026otel,
  title     = {OTel: Open Telco AI Datasets, Benchmarks, and Models},
  author    = {Tavakkoli, Farbod and Diamos, Gregory and Church, Kenneth and Kanter, David and Austin, Mark and Karim, Imtiaz and Rahman, Mirza Masfiqur and Debbah, Merouane Abdelkader and Nezami, Zeinab and Maatouk, Ali and Tassiulas, Leandros and Ying, Rex and Sorros, Nick and Powell, Louis and Vasiloglou, Nikolaos and Vaswani, Ashish and Singla, Somanshu and Chaluvaraju, Adarsh},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS), Evaluations and Datasets Track},
  year      = {2026},
  url       = {https://github.com/farbodtavakkoli/OTel}
}

Contact

For technical questions, contact farbod.tavakkoli@att.com or farbodtavakoli@gmail.com.