Telecom RAG specialization
According to the model card, rows pair a context-grounded telecom RAG prompt with a reference completion, including abstention and metadata fields.
Open Source Model Profile · farbodtavakkoli
OTel-LLM-0.6B-IT
OTel-LLM-0.6B-IT is a Qwen3-based telecom text-generation fine-tune from farbodtavakkoli. According to the model card, it is context-grounded on OTel data for RAG pipelines.
- Publisher
- farbodtavakkoli
- Task
- text-generation
- Model type
- qwen3
- License
- apache-2.0
- Library
- Unknown
- Publication status
- Approved for indexing
Model overview
OTel-LLM-0.6B-IT is published by farbodtavakkoli as a Qwen3 text-generation model. The captured configuration identifies Qwen3ForCausalLM with model type qwen3. According to the model card, it is a full-parameter fine-tune of Qwen/Qwen3-0.6B on OTel telecommunications data and part of the OTel family.
Recorded capabilities
Reported correctness gain
According to the model card, the 0.6B variant improves LLM-as-judge correctness from 49.0% to 59.0% on the OTel held-out split.
Documented training recipe
According to the model card, training uses full-parameter post-training with a ScalarLM recipe, BF16 precision, Flash Attention 2, and three epochs for LLM models.
Use cases in the source record
- Context-grounded telecom assistance inside a RAG pipeline using the card's precise telecom-assistant prompt pattern.
- Abstention-aware telecom question answering where retrieved context may be missing, including evaluation with the card's -Safety variants.
Limitations and unknowns
- According to the model card, answer quality depends on retriever, reranker, context, and prompt policy, and the model should not be treated as a general-purpose model.
- No Safetensors parameter count was extracted from this record; the 0.6B figure is a publisher-reported attribute.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: farbodtavakkoli/OTel-LLM-0.6B-IT
Captured: Unknown. Processed: 2026-09-07T19:35:55.881922+00:00.
OTel-LLM-0.6B-IT OTel-LLM-0.6B-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 Val…
F001F002F003F004F005F006F008F009F010F012F013F014F016F017F018F019F020