Buckets:

EuroEval/results / ChocoLlama_ChocoLlama-2-7B-instruct.jsonl
saattrupdan's picture
download
raw
24.6 kB
{"schema_version": "0.2.1", "evaluation_id": "conll-nl/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132383+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "conll-nl", "languages": "[\"nl\"]", "task": "named-entity-recognition", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"micro_f1_no_misc\": 0.30173228346456693, \"micro_f1\": 0.31960188001105894}, {\"micro_f1_no_misc\": 0.36644242184408393, \"micro_f1\": 0.3841015364061457}, {\"micro_f1_no_misc\": 0.3650674662668666, \"micro_f1\": 0.3608043047295384}, {\"micro_f1_no_misc\": 0.24885095206828628, \"micro_f1\": 0.2370927318295739}, {\"micro_f1_no_misc\": 0.2704207920792079, \"micro_f1\": 0.280306905370844}, {\"micro_f1_no_misc\": 0.3625377643504532, \"micro_f1\": 0.32341156267887805}, {\"micro_f1_no_misc\": 0.3074324324324324, \"micro_f1\": 0.2980769230769231}, {\"micro_f1_no_misc\": 0.2200895713371721, \"micro_f1\": 0.22765598650927488}, {\"micro_f1_no_misc\": 0.2839093273875883, \"micro_f1\": 0.263579697239537}, {\"micro_f1_no_misc\": 0.2767162066525124, \"micro_f1\": 0.2859598853868195}]"}}, "evaluation_results": [{"evaluation_name": "test_micro_f1_no_misc", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 30.0319921788317, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.878723874747443, "upper": 33.18526048291596, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_micro_f1", "source_data": {"dataset_name": "conll-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 29.805914132385936, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.688277722325033, "upper": 32.92355054244684, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "dbrd/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132421+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": "instruction_tuned", "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.8.3"}}, "eval_library": {"name": "euroeval", "version": "15.7.1.dev0", "additional_details": {"dataset": "dbrd", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "4.51.2", "torch_version": "2.6.0", "vllm_version": "0.8.3", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.713642513383768, \"macro_f1\": 0.8439998187300108}, {\"mcc\": 0.844373052413836, \"macro_f1\": 0.9182811946348142}, {\"mcc\": 0.6008261178812255, \"macro_f1\": 0.7533368759106323}, {\"mcc\": 0.8349230043149101, \"macro_f1\": 0.9129238104960995}, {\"mcc\": 0.5266823316559863, \"macro_f1\": 0.6939350301688891}, {\"mcc\": 0.5303984219822114, \"macro_f1\": 0.695991361912092}, {\"mcc\": 0.6745007073204907, \"macro_f1\": 0.8072622149817124}, {\"mcc\": 0.7105125270050826, \"macro_f1\": 0.8327778781644759}, {\"mcc\": 0.7345688158650783, \"macro_f1\": 0.8507129210692714}, {\"mcc\": 0.5169686839970424, \"macro_f1\": 0.6860856355377357}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 66.87396175819632, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 59.3235888149528, "upper": 74.42433470143983, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dbrd", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 79.95306741605732, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 74.5026678853746, "upper": 85.40346694674004, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "dutch-social/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132455+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "dutch-social", "languages": "[\"nl\"]", "task": "sentiment-classification", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.0466875949385833, \"macro_f1\": 0.24687570948297755}, {\"mcc\": 0.07346743560236603, \"macro_f1\": 0.33129075234338395}, {\"mcc\": 0.03181771026017717, \"macro_f1\": 0.23258876470570403}, {\"mcc\": 0.09309105617708886, \"macro_f1\": 0.2980516662260173}, {\"mcc\": 0.08867523393284844, \"macro_f1\": 0.28816035187303674}, {\"mcc\": 0.045812520115590755, \"macro_f1\": 0.23396927344659793}, {\"mcc\": 0.10485622906937381, \"macro_f1\": 0.2596309732812601}, {\"mcc\": 0.10519569074782645, \"macro_f1\": 0.3304294998194645}, {\"mcc\": 0.08448845263268706, \"macro_f1\": 0.3580524107918413}, {\"mcc\": 0.12820500361313975, \"macro_f1\": 0.3252604502638943}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 8.022969270896816, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 6.119835070403431, "upper": 9.926103471390201, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "dutch-social", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 29.043098522341783, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.23317791312209, "upper": 31.853019131561474, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "hellaswag-nl/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132487+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "hellaswag-nl", "languages": "[\"nl\"]", "task": "common-sense-reasoning", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.06489085273883627, \"accuracy\": 0.28466796875}, {\"mcc\": 0.027133752966827417, \"accuracy\": 0.27490234375}, {\"mcc\": 0.04723398650487947, \"accuracy\": 0.27978515625}, {\"mcc\": 0.04255320221244003, \"accuracy\": 0.2783203125}, {\"mcc\": 0.022220900358971358, \"accuracy\": 0.267578125}, {\"mcc\": 0.029625669742401228, \"accuracy\": 0.24951171875}, {\"mcc\": 0.03115697477664815, \"accuracy\": 0.26611328125}, {\"mcc\": 0.0520737366652633, \"accuracy\": 0.28564453125}, {\"mcc\": 0.01508107796511291, \"accuracy\": 0.2626953125}, {\"mcc\": 0.045893814754266016, \"accuracy\": 0.25341796875}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 3.7786396868564616, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 2.832246058557838, "upper": 4.725033315155085, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "hellaswag-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 27.0263671875, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 26.24857687430417, "upper": 27.80415750069583, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "mmlu-nl/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132518+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "mmlu-nl", "languages": "[\"nl\"]", "task": "knowledge", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.07676056304269241, \"accuracy\": 0.30810546875}, {\"mcc\": 0.07586696761989686, \"accuracy\": 0.2998046875}, {\"mcc\": 0.07464474241826503, \"accuracy\": 0.3017578125}, {\"mcc\": 0.06587885235494932, \"accuracy\": 0.29296875}, {\"mcc\": 0.09024031390926342, \"accuracy\": 0.2890625}, {\"mcc\": 0.08174649728397579, \"accuracy\": 0.3037109375}, {\"mcc\": 0.050687391582231296, \"accuracy\": 0.279296875}, {\"mcc\": 0.0413369067357243, \"accuracy\": 0.271484375}, {\"mcc\": 0.060287571309153624, \"accuracy\": 0.28759765625}, {\"mcc\": 0.050323030620777684, \"accuracy\": 0.28662109375}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 6.677728368769298, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 5.700227360730523, "upper": 7.655229376808073, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_accuracy", "source_data": {"dataset_name": "mmlu-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 29.2041015625, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 28.4905657498862, "upper": 29.9176373751138, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "scala-nl/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132550+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "scala-nl", "languages": "[\"nl\"]", "task": "linguistic-acceptability", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"mcc\": 0.08811854054017172, \"macro_f1\": 0.3815754591758841}, {\"mcc\": 0.09240043387681658, \"macro_f1\": 0.3750984833787382}, {\"mcc\": 0.11155764940496603, \"macro_f1\": 0.3776120516071295}, {\"mcc\": 0.06321802448280575, \"macro_f1\": 0.3387953281727916}, {\"mcc\": 0.06380675638982074, \"macro_f1\": 0.35245097776515416}, {\"mcc\": 0.1076431205125005, \"macro_f1\": 0.4389008248496947}, {\"mcc\": 0.09948187734894068, \"macro_f1\": 0.4045357627447179}, {\"mcc\": 0.04304118148569285, \"macro_f1\": 0.3442426031326399}, {\"mcc\": 0.09442760108736287, \"macro_f1\": 0.35477456298730126}, {\"mcc\": 0.12043692052762701, \"macro_f1\": 0.4452455262835103}]"}}, "evaluation_results": [{"evaluation_name": "test_mcc", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 8.841321056567047, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 7.32247329015501, "upper": 10.360168822979084, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_macro_f1", "source_data": {"dataset_name": "scala-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 38.13231580097561, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 35.80268276300438, "upper": 40.461948838946846, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "speed/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132588+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "speed", "languages": "[\"ab\", \"aa\", \"af\", \"sq\", \"am\", \"ar\", \"an\", \"hy\", \"as\", \"av\", \"ae\", \"ay\", \"az\", \"bm\", \"ba\", \"eu\", \"be\", \"bn\", \"bi\", \"bs\", \"br\", \"bg\", \"my\", \"ca\", \"ch\", \"ce\", \"ny\", \"zh\", \"cu\", \"cv\", \"kw\", \"co\", \"cr\", \"hr\", \"cs\", \"da\", \"dv\", \"nl\", \"dz\", \"en\", \"eo\", \"et\", \"ee\", \"fo\", \"fj\", \"fi\", \"fr\", \"fy\", \"ff\", \"gd\", \"gl\", \"lg\", \"ka\", \"de\", \"el\", \"kl\", \"gn\", \"gu\", \"ht\", \"ha\", \"he\", \"hz\", \"hi\", \"ho\", \"hu\", \"is\", \"io\", \"ig\", \"id\", \"ia\", \"ie\", \"iu\", \"ik\", \"ga\", \"it\", \"ja\", \"kn\", \"kr\", \"ks\", \"kk\", \"km\", \"ki\", \"rw\", \"ky\", \"kv\", \"kg\", \"ko\", \"kj\", \"ku\", \"lo\", \"la\", \"lv\", \"li\", \"ln\", \"lt\", \"lu\", \"lb\", \"mk\", \"mg\", \"ms\", \"ml\", \"mt\", \"gv\", \"mi\", \"mr\", \"mh\", \"mn\", \"na\", \"nv\", \"nd\", \"nr\", \"ng\", \"ne\", \"no\", \"nb\", \"nn\", \"ii\", \"oc\", \"oj\", \"or\", \"om\", \"os\", \"pi\", \"ps\", \"fa\", \"pl\", \"pt\", \"pa\", \"qu\", \"ro\", \"rm\", \"rn\", \"ru\", \"se\", \"sm\", \"sg\", \"sa\", \"sc\", \"sr\", \"sn\", \"sd\", \"si\", \"sk\", \"sl\", \"so\", \"st\", \"es\", \"su\", \"sw\", \"ss\", \"sv\", \"tl\", \"ty\", \"tg\", \"ta\", \"tt\", \"te\", \"th\", \"bo\", \"ti\", \"to\", \"ts\", \"tn\", \"tr\", \"tk\", \"tw\", \"ug\", \"uk\", \"ur\", \"uz\", \"ve\", \"vi\", \"vo\", \"wa\", \"cy\", \"wo\", \"xh\", \"yi\", \"yo\", \"za\", \"zu\"]", "task": "speed", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"test_speed\": 2016.3999999999999, \"test_speed_short\": 98.8}, {\"test_speed\": 3663.18, \"test_speed_short\": 444.3}, {\"test_speed\": 4137.71, \"test_speed_short\": 353.21999999999997}, {\"test_speed\": 2779.09, \"test_speed_short\": 437.40000000000003}, {\"test_speed\": 3159.0, \"test_speed_short\": 1230.23}, {\"test_speed\": 5877.160000000001, \"test_speed_short\": 1630.77}, {\"test_speed\": 6392.82, \"test_speed_short\": 1825.92}, {\"test_speed\": 6507.599999999999, \"test_speed_short\": 2017.8200000000002}, {\"test_speed\": 6625.5, \"test_speed_short\": 2195.7}, {\"test_speed\": 6645.4800000000005, \"test_speed_short\": 2356.2}]"}}, "evaluation_results": [{"evaluation_name": "test_speed", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 4780.394, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 3656.2804178686365, "upper": 5904.507582131364, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_speed_short", "source_data": {"dataset_name": "speed", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false}, "score_details": {"score": 1259.036, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 727.3508791225972, "upper": 1790.7211208774029, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}
{"schema_version": "0.2.1", "evaluation_id": "squad-nl/ChocoLlama/ChocoLlama-2-7B-instruct/1781766557", "evaluation_timestamp": "2026-06-18T07:09:17.132628+00:00", "retrieved_timestamp": "1781766557", "source_metadata": {"source_name": "EuroEval", "source_type": "evaluation_run", "source_organization_name": "EuroEval", "source_organization_url": "https://euroeval.com", "evaluator_relationship": "third_party"}, "model_info": {"name": "ChocoLlama/ChocoLlama-2-7B-instruct", "id": "ChocoLlama/ChocoLlama-2-7B-instruct", "additional_details": {"num_model_parameters": "6738415616", "max_sequence_length": "4096", "vocabulary_size": "32000", "merge": "false", "generative": "true", "generative_type": null, "commercially_licensed": false, "open": true, "trained_from_scratch": false, "model_url": "https://hf.co/ChocoLlama/ChocoLlama-2-7B-instruct"}, "inference_engine": {"name": "vllm", "version": "0.22.0+cpu"}}, "eval_library": {"name": "euroeval", "version": "17.4.0.dev0", "additional_details": {"dataset": "squad-nl", "languages": "[\"nl\"]", "task": "reading-comprehension", "few_shot": "true", "validation_split": "false", "transformers_version": "5.10.2", "torch_version": "2.11.0", "vllm_version": "0.22.0+cpu", "xgrammar_version": "0.2.0", "litellm_version": null, "raw_results": "[{\"f1\": 67.05820792912814, \"em\": 48.18181818181818}, {\"f1\": 68.7669522055499, \"em\": 51.93328278999242}, {\"f1\": 67.0329951771842, \"em\": 48.717948717948715}, {\"f1\": 67.70215218578916, \"em\": 51.2937595129376}, {\"f1\": 69.15876199778553, \"em\": 53.81649961449499}, {\"f1\": 68.53125204173641, \"em\": 47.786259541984734}, {\"f1\": 66.71715724263862, \"em\": 50.546021840873635}, {\"f1\": 66.76575135497302, \"em\": 47.484276729559745}, {\"f1\": 69.44626215835429, \"em\": 54.4891640866873}, {\"f1\": 68.04741064561006, \"em\": 50.0}]"}}, "evaluation_results": [{"evaluation_name": "test_f1", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 67.92269029387492, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 67.29171886391634, "upper": 68.5536617238335, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}, {"evaluation_name": "test_em", "source_data": {"dataset_name": "squad-nl", "source_type": "hf_dataset"}, "metric_config": {"lower_is_better": false, "score_type": "continuous", "min_score": 0, "max_score": 100}, "score_details": {"score": 50.42490310162973, "details": {"num_failed_instances": "0.0"}, "uncertainty": {"confidence_interval": {"lower": 48.89547050536995, "upper": 51.95433569788951, "confidence_level": 0.95, "method": "bootstrap"}, "num_samples": 10}}}]}

Xet Storage Details

Size:
24.6 kB
·
Xet hash:
33db3f0df056c223dc5e2f3ac1b726d9439aac81dbc8e21633c29d31d6d6d91f

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.