| {"eval_library":{"additional_details":{"dataset":"mlqa-es","few_shot":"true","languages":"[\"es\"]","litellm_version":null,"raw_results":"[{\"f1\": 64.9489054055723, \"em\": 37.134052388289675}, {\"f1\": 68.53089471939273, \"em\": 40.184757505773675}, {\"f1\": 71.87668048949996, \"em\": 48.35423197492163}, {\"f1\": 68.71585593268158, \"em\": 41.8026418026418}, {\"f1\": 69.0294019126153, \"em\": 39.93660855784469}, {\"f1\": 67.52168352640737, \"em\": 41.217257318952235}, {\"f1\": 64.55716161715843, \"em\": 32.268121590023384}, {\"f1\": 70.12303977029893, \"em\": 47.62658227848101}, {\"f1\": 67.32753629498974, \"em\": 41.09263657957245}, {\"f1\": 66.3736839584804, \"em\": 40.061871616395976}]","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":"mlqa-es/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":67.90048436270968,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":66.50260909871406,"method":"bootstrap","upper":69.29835962670529},"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":40.96787616128965,"uncertainty":{"confidence_interval":{"confidence_level":0.95,"lower":38.10099488629552,"method":"bootstrap","upper":43.83475743628379},"num_samples":10}},"source_data":{"dataset_name":"mlqa-es","source_type":"hf_dataset"}}],"evaluation_timestamp":"2026-06-18T07:09:17.005050+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:
- 51a899a431728c9af5c74935b3c7910c4b8591ed23e661f53a6d0c9a1ed247e5
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.