| {"eval_library":{"additional_details":{"dataset":"mlqa-es","few_shot":"true","languages":"[\"es\"]","litellm_version":null,"raw_results":"[{\"f1\": 58.455986368518765, \"em\": 28.043143297380585}, {\"f1\": 60.5834216106254, \"em\": 32.10161662817552}, {\"f1\": 64.75600788077128, \"em\": 38.793103448275865}, {\"f1\": 59.307329566365404, \"em\": 31.235431235431236}, {\"f1\": 62.717516579974465, \"em\": 34.54833597464342}, {\"f1\": 60.326692711121765, \"em\": 32.973805855161785}, {\"f1\": 57.505852898534364, \"em\": 26.188620420888544}, {\"f1\": 62.12978024824503, \"em\": 36.70886075949367}, {\"f1\": 61.21312106897404, \"em\": 34.045922406967534}, {\"f1\": 61.880720715694224, \"em\": 35.80819798917247}]","task":"reading-comprehension","torch_version":"2.7.0","transformers_version":"4.51.3","validation_split":"false","vllm_version":"0.9.1","xgrammar_version":"0.2.0"},"name":"euroeval","version":"15.10.0"},"evaluation_id":"mlqa-es/CohereForAI/aya-23-8B/1781766557","evaluation_results":[{"evaluation_name":"test_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":60.88764296488247,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":59.56149227593299,"method":"bootstrap","upper":62.21379365383194},"num_samples":10}},"source_data":{"dataset_name":"mlqa-es","source_type":"hf_dataset"}},{"evaluation_name":"test_em","metric_config":{"lower_is_better":false,"max_score":100,"min_score":0,"score_type":"continuous"},"score_details":{"details":{"num_failed_instances":"0.0"},"score":33.044703801559066,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":30.6570427459178,"method":"bootstrap","upper":35.432364857200334},"num_samples":10}},"source_data":{"dataset_name":"mlqa-es","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.050424+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-23-8B","num_model_parameters":"8028033024","open":true,"release_date":"2024-05-23","trained_from_scratch":false,"vocabulary_size":"256000"},"id":"CohereForAI/aya-23-8B","inference_engine":{"name":"vllm","version":"0.9.1"},"name":"CohereForAI/aya-23-8B"},"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"}} | |
Xet Storage Details
- Size:
- 2.66 kB
- Xet hash:
- d9b3ebf7909e5530e9674c35a312509c598054b510f1a9670184ecc791292268
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.