| {"eval_library":{"additional_details":{"dataset":"multi-wiki-qa-pt","few_shot":"true","languages":"[\"pt\"]","litellm_version":null,"raw_results":"[{\"f1\": 75.33755106045882, \"em\": 57.82881002087683}, {\"f1\": 78.94360065397315, \"em\": 59.32203389830509}, {\"f1\": 78.89313297495352, \"em\": 60.788381742738586}, {\"f1\": 77.65778497265296, \"em\": 59.47046843177189}, {\"f1\": 75.43989163064356, \"em\": 57.31958762886598}, {\"f1\": 74.02233416358881, \"em\": 56.46817248459959}, {\"f1\": 78.68103321678173, \"em\": 60.37735849056604}, {\"f1\": 79.72358968807286, \"em\": 62.34309623430963}, {\"f1\": 76.31066814510795, \"em\": 58.09128630705394}, {\"f1\": 76.77142185718908, \"em\": 59.50413223140496}]","task":"reading-comprehension","torch_version":"2.7.1","transformers_version":"4.55.2","validation_split":"false","vllm_version":"0.10.0","xgrammar_version":"0.1.21"},"name":"euroeval","version":"15.16.0"},"evaluation_id":"multi-wiki-qa-pt/CohereForAI/aya-23-35B/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":77.17810083634224,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":76.00369121353721,"method":"bootstrap","upper":78.35251045914727},"num_samples":10}},"source_data":{"dataset_name":"multi-wiki-qa-pt","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":59.15133274704925,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":58.05705732536352,"method":"bootstrap","upper":60.24560816873498},"num_samples":10}},"source_data":{"dataset_name":"multi-wiki-qa-pt","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.005314+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":"0.10.0"},"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"}} | |
Xet Storage Details
- Size:
- 2.69 kB
- Xet hash:
- aa8c9736e68226abf049105e9f45eb44cb39e0948dae308a1249b7cae4bb9887
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.