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/Llama2-7B-chat

Llama2-7B-chat

Reported on 13 benchmarks across 1 task · 1 paper · 12 SOTA

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

Natural Language Processing13 results

  • Question AnsweringonUniProtQA
    BLEU-2· 2023-07-18
    0.019
    best: 0.571 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonUniProtQA
    BLEU-4· 2023-07-18
    0.002
    best: 0.535 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonUniProtQA
    MEATOR· 2023-07-18
    0.052
    best: 0.754 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonUniProtQA
    ROUGE-1· 2023-07-18
    0.103
    best: 0.743 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonUniProtQA
    ROUGE-2· 2023-07-18
    0.06
    best: 0.759 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonUniProtQA
    ROUGE-L· 2023-07-18
    0.009
    best: 0.622 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    BLEU-2· 2023-07-18
    0.075
    best: 0.234 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    BLEU-4· 2023-07-18
    0.009
    best: 0.141 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    MEATOR· 2023-07-18
    0.149
    best: 0.308 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    ROUGE-1· 2023-07-18
    0.184
    best: 0.386 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    ROUGE-2· 2023-07-18
    0.043
    best: 0.206 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonPubChemQA
    ROUGE-L· 2023-07-18
    0.142
    best: 0.332 (BioMedGPT-10B)
    SOTA
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288
  • Question AnsweringonMMLU (Professional medicine)
    Accuracy· 2023-07-18
    40.07
    best: 95.2 (Med-PaLM 2 (5-shot))
    Llama 2: Open Foundation and Fine-Tuned Chat ModelsarXiv:2307.09288