Skip to content

EthenEthenEthen

Open Source Model Profile · farbodtavakkoli

OTel-LLM-7B-IT

OTel-LLM-7B-IT is a telecom-focused Olmo3 fine-tune from farbodtavakkoli. According to the model card, it fine-tunes allenai/OLMo-3-7B on OTel data for context-grounded RAG use.

Publisher
farbodtavakkoli
Task
text-generation
Model type
olmo3
License
apache-2.0
Library
Unknown
Publication status
Accepted · not indexed

Model overview

OTel-LLM-7B-IT is published by farbodtavakkoli as an Olmo3 text-generation model. The captured configuration identifies Olmo3ForCausalLM with model type olmo3, and card data records apache-2.0. According to the model card, it is a full-parameter fine-tune of allenai/OLMo-3-7B on OTel telecommunications data for context-grounded use.

Recorded capabilities

Telecom RAG fine-tune

Captured configuration records Olmo3ForCausalLM with model type olmo3, and the model card describes full-parameter fine-tuning on OTel telecommunications data for context-grounded use.

Publisher-reported correctness gain

According to the model card, OTel fine-tuning improves context-grounded correctness by 3.7 to 10.0 points, with a 57.4% to 63.4% example on the held-out split.

Documented telecom training recipe

According to the model card, training used 326,767 filtered examples from about 1.1M points, BF16 precision, 1500-token maximum sequence, Flash Attention 2, and 3 epochs.

Apache-2.0 release with dual compliance

Card data records apache-2.0, and the model card states users must comply with both OTel release and upstream base-model terms.

Use cases in the source record

  • Context-grounded telecom RAG workflows that pair retrieved context with the documented prompt and reference-completion pattern.
  • Abstention-aware telecom assistance where retrieved context is missing, using the card's Safety-variant guidance rather than unrestricted QA.

Limitations and unknowns

  • No Safetensors parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • Reported correctness gains and evaluation splits are publisher claims judged with GPT-4o mini and were not independently verified.
  • According to the model card, answer quality depends on the retriever, reranker, context, and prompt policy, and the model should not be treated as general-purpose.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

Source: farbodtavakkoli/OTel-LLM-7B-IT

Captured: Unknown. Processed: 2026-09-07T19:35:55.929825+00:00.

OTel-LLM-7B-IT OTel-LLM-7B-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 core OTel LLM baselines, OTel fine-tuning improves context-grounded correctness over the base checkpoints by +3.7 to +10.0 percentage points. Community Use As of June 23, 2026, the released OTel models had more than 18 million downloads, and the Open Telco AI project had received 157+ pieces of media coverage worldwide. Model Details Attribute Value B…

F001F002F003F004F005F006F007F008F009F010F012F013F014F016F017F018F019F020F021