| license: apache-2.0 | |
| pipeline_tag: text-classification | |
| basemodel: roberta-base | |
| datasets: | |
| - DevQuasar/llm_router_dataset-synth | |
| language: | |
| - en | |
| Intention of the model is to determine if the given user prompt's complexity, domain question requires a SOTA (very large) LLM | |
| or can be deescaleted to a smaller or local model. |