{"eval_library":{"additional_details":{"dataset":"fone","few_shot":"true","languages":"[\"fo\"]","litellm_version":null,"raw_results":"[{\"micro_f1_no_misc\": 0.6526939769238912, \"micro_f1\": 0.5027606878056476}, {\"micro_f1_no_misc\": 0.6392188443728609, \"micro_f1\": 0.627735831023607}, {\"micro_f1_no_misc\": 0.6398941698951147, \"micro_f1\": 0.5145560407569142}, {\"micro_f1_no_misc\": 0.6052631578947368, \"micro_f1\": 0.5515896566341669}, {\"micro_f1_no_misc\": 0.6435298935298935, \"micro_f1\": 0.4843525043570508}, {\"micro_f1_no_misc\": 0.6948919449901768, \"micro_f1\": 0.6088360237892948}, {\"micro_f1_no_misc\": 0.6771621345328154, \"micro_f1\": 0.6408375089477452}, {\"micro_f1_no_misc\": 0.6793862305673328, \"micro_f1\": 0.5986240529478359}, {\"micro_f1_no_misc\": 0.642666118082699, \"micro_f1\": 0.5670217298679164}, {\"micro_f1_no_misc\": 0.6654830287206266, \"micro_f1\": 0.5681975138121548}]","task":"named-entity-recognition","torch_version":"2.7.0","transformers_version":"4.52.4","validation_split":"false","vllm_version":"0.9.1","xgrammar_version":"0.2.0"},"name":"euroeval","version":"15.10.0.dev0"},"evaluation_id":"fone/CohereForAI/aya-23-35B/1781766557","evaluation_results":[{"evaluation_name":"test_micro_f1_no_misc","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":65.40189499510147,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":63.799232880325576,"method":"bootstrap","upper":67.00455710987737},"num_samples":10}},"source_data":{"dataset_name":"fone","source_type":"hf_dataset"}},{"evaluation_name":"test_micro_f1","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":56.64511549942335,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":53.3243615615836,"method":"bootstrap","upper":59.965869437263095},"num_samples":10}},"source_data":{"dataset_name":"fone","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.004381+00:00","model_info":{"additional_details":{"commercially_licensed":false,"generative":"true","generative_type":"instruction_tuned","max_sequence_length":"8192","merge":"false","model_url":"https://hf.co/CohereForAI/aya-23-35B","num_model_parameters":"34980831232","open":true,"release_date":"2024-05-23","trained_from_scratch":false,"vocabulary_size":"256000"},"id":"CohereForAI/aya-23-35B","inference_engine":{"name":"vllm","version":"0.9.1"},"name":"CohereForAI/aya-23-35B"},"retrieved_timestamp":"1781766557","schema_version":"0.2.1","source_metadata":{"evaluator_relationship":"third_party","source_name":"EuroEval","source_organization_name":"EuroEval","source_organization_url":"https://euroeval.com","source_type":"evaluation_run"}}