| {"eval_library":{"additional_details":{"dataset":"foqa","few_shot":"true","languages":"[\"fo\"]","litellm_version":null,"raw_results":"[{\"f1\": 60.39210693640134, \"em\": 41.911764705882355}, {\"f1\": 61.63054260569709, \"em\": 44.47174447174447}, {\"f1\": 68.16279332956222, \"em\": 51.111111111111114}, {\"f1\": 64.89699633718296, \"em\": 47.57281553398058}, {\"f1\": 66.07892829896377, \"em\": 48.51485148514851}, {\"f1\": 62.49061806032827, \"em\": 45.4320987654321}, {\"f1\": 64.16742400733655, \"em\": 46.93396226415094}, {\"f1\": 67.91223227219236, \"em\": 48.600508905852415}, {\"f1\": 67.58933038993133, \"em\": 50.62344139650873}, {\"f1\": 65.75035486084305, \"em\": 46.19164619164619}]","task":"reading-comprehension","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":"foqa/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":64.90713270984389,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":63.22340033363734,"method":"bootstrap","upper":66.59086508605044},"num_samples":10}},"source_data":{"dataset_name":"foqa","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":47.136394483145736,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":45.402568264470595,"method":"bootstrap","upper":48.87022070182088},"num_samples":10}},"source_data":{"dataset_name":"foqa","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.004412+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"}} | |
Xet Storage Details
- Size:
- 2.65 kB
- Xet hash:
- add6827a89317aace0938ac2183da1905da044e132c5fe5c707e5cd872342e55
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.