TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Shakti-LLM (2.5B)

Shakti-LLM (2.5B)

Reported on 7 benchmarks across 1 task · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing7 results

  • Question AnsweringonHellaSwag
    Accuracy· 2024-10-15
    52.4
    SOTA
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonBBH
    Accuracy· 2024-10-15
    58.2
    SOTA
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonTruthfulQA
    Accuracy· 2024-10-15
    68.4
    SOTA
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonMedQA
    Accuracy· 2024-10-15
    60.3
    best: 91.1 (Med-Gemini)
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonPIQA
    Accuracy· 2024-10-15
    86.2
    best: 90.1 (Unicorn 11B (fine-tuned))
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonBoolQ
    Accuracy· 2024-10-15
    61.1
    best: 99.87 (Mistral-Nemo 12B (HPT))
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331
  • Question AnsweringonTriviaQA
    EM· 2024-10-15
    58.2
    best: 87.5 (Claude 2 (few-shot, k=5))
    SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource EnvironmentsarXiv:2410.11331