LIBRA-Leaderboard / results /Saiga-LLaMA-3-8B.json
ai-forever's picture
Upload 19 files
1ddbee0 verified
raw
history blame
2.59 kB
{"passkey": {"4k": 1.0, "8k": 1.0, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.3333333333333333}, "matreshka_yes_no": {"4k": 0.8729096989966555, "8k": 0.81, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.28048494983277594}, "matreshka_names": {"4k": 0.5333333333333333, "8k": 0.4, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.15555555555555556}, "passkey_with_librusec": {"4k": 1.0, "8k": 0.995, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.3325}, "librusec_history": {"8k": 0.96875, "16k": 0, "32k": 0, "64k": 0, "dataset_total_score": 0.2421875}, "ru_gsm100": {"16k": 0, "dataset_total_score": 0.0}, "ru_sci_passage_count": {"4k": 0.195, "8k": 0.035, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.03833333333333334}, "ru_2wikimultihopqa": {"8k": 0.5306122448979592, "16k": 0, "32k": 0, "dataset_total_score": 0.17687074829931973}, "long_context_multiq": {"8k": 0.235, "4k": 0.055, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.04833333333333333}, "ru_sci_abstract_retrieval": {"4k": 0.9772222222222221, "8k": 0.9258564054992626, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.31717977128691416}, "ru_trec": {"4k": 0.5135135135135135, "8k": 0.54, "16k": 0, "32k": 0, "dataset_total_score": 0.2633783783783784}, "ru_sci_fi": {"32k": 0, "64k": 0, "dataset_total_score": 0.0}, "librusec_mhqa": {"8k": 0.4505208333333333, "dataset_total_score": 0.4505208333333333}, "ru_babilong_qa1": {"4k": 0.7629583333333333, "8k": 0.758125, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.25351388888888887}, "ru_babilong_qa2": {"4k": 0.195625, "8k": 0.06875, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.044062500000000004}, "ru_babilong_qa3": {"4k": 0.14733333333333334, "8k": 0.21585714285714286, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.06053174603174603}, "ru_babilong_qa4": {"4k": 0.6347142857142858, "8k": 0.5821428571428572, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.20280952380952386}, "ru_babilong_qa5": {"4k": 0.7466666666666667, "8k": 0.7633333333333334, "16k": 0, "32k": 0, "64k": 0, "128k": 0, "dataset_total_score": 0.2516666666666667}, "ru_quality": {"8k": 0.35772357723577236, "16k": 0, "dataset_total_score": 0.17886178861788618}, "ru_tpo": {"8k": 0.7569721115537849, "dataset_total_score": 0.7569721115537849}, "ru_qasper": {"8k": 0.07413702213069599, "16k": 0, "32k": 0, "dataset_total_score": 0.024712340710231998}, "total_score": 0.21008610966500027}