LIBRA-Leaderboard / results /Mistral-7B-v0.1.json
ai-forever's picture
Upload 19 files
1ddbee0 verified
raw
history blame
2.73 kB
{"passkey": {"4k": 1.0, "8k": 0.975, "16k": 0.125, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.35000000000000003}, "matreshka_yes_no": {"4k": 0.5016722408026756, "8k": 0.5, "16k": 0.0033333333333333335, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.1675009290226682}, "matreshka_names": {"4k": 0.32666666666666666, "8k": 0.16, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.08111111111111112}, "passkey_with_librusec": {"4k": 1.0, "8k": 1.0, "16k": 0.3, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.3833333333333333}, "librusec_history": {"8k": 0.78125, "16k": 0.15625, "32k": 0.0, "64k": 0, "dataset_total_score": 0.234375}, "ru_gsm100": {"16k": 0.13, "dataset_total_score": 0.13}, "ru_sci_passage_count": {"4k": 0.04, "8k": 0.04, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.013333333333333334}, "ru_2wikimultihopqa": {"8k": 0.42857142857142855, "16k": 0.1796875, "32k": 0.08130081300813008, "dataset_total_score": 0.22985324719318623}, "long_context_multiq": {"8k": 0.22, "16k": 0.005, "4k": 0.04, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.04416666666666667}, "ru_sci_abstract_retrieval": {"4k": 0.9484126984126985, "8k": 0.7607802118516404, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.28486548504405645}, "ru_trec": {"4k": 0.02702702702702703, "8k": 0.1, "16k": 0.03296703296703297, "32k": 0.0, "dataset_total_score": 0.039998514998515}, "ru_sci_fi": {"32k": 0.027777777777777776, "64k": 0, "dataset_total_score": 0.013888888888888888}, "librusec_mhqa": {"8k": 0.3411458333333333, "dataset_total_score": 0.3411458333333333}, "ru_babilong_qa1": {"4k": 0.63, "8k": 0.63, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.21}, "ru_babilong_qa2": {"4k": 0.21, "8k": 0.25, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.07666666666666666}, "ru_babilong_qa3": {"4k": 0.29, "8k": 0.25, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.09000000000000001}, "ru_babilong_qa4": {"4k": 0.4292857142857143, "8k": 0.3157142857142857, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.12416666666666669}, "ru_babilong_qa5": {"4k": 0.7, "8k": 0.6933333333333335, "16k": 0.0, "32k": 0.0, "64k": 0, "128k": 0, "dataset_total_score": 0.23222222222222225}, "ru_quality": {"16k": 0.11801242236024845, "8k": 0.22764227642276424, "dataset_total_score": 0.17282734939150635}, "ru_tpo": {"8k": 0.3957503320053121, "dataset_total_score": 0.3957503320053121}, "ru_qasper": {"16k": 0.011042882576489372, "8k": 0.0625419691096683, "32k": 0.0008322260797508323, "dataset_total_score": 0.024805692588636172}, "total_score": 0.17333387011743345}