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/LLaMA-2 7B + MixLoRA

LLaMA-2 7B + MixLoRA

Reported on 8 benchmarks across 3 tasks · 1 paper

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

Natural Language Processing8 results

  • Question AnsweringonSIQA
    Accuracy· 2024-04-22
    78
    best: 83.2 (Unicorn 11B (fine-tuned))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Question AnsweringonPIQA
    Accuracy· 2024-04-22
    83.2
    best: 90.1 (Unicorn 11B (fine-tuned))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Question AnsweringonBoolQ
    Accuracy· 2024-04-22
    72.7
    best: 99.87 (Mistral-Nemo 12B (HPT))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Question AnsweringonOpenBookQA
    Accuracy· 2024-04-22
    81.6
    best: 95.9 (GPT-4 + knowledge base)
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Common Sense ReasoningonWinoGrande
    Accuracy· 2024-04-22
    76.8
    best: 96.1 (ST-MoE-32B 269B (fine-tuned))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Common Sense ReasoningonARC (Challenge)
    Accuracy· 2024-04-22
    58.1
    best: 96.4 (GPT-4 (few-shot, k=25))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Common Sense ReasoningonARC (Easy)
    Accuracy· 2024-04-22
    77.7
    best: 95.2 (ST-MoE-32B 269B (fine-tuned))
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159
  • Sentence CompletiononHellaSwag
    Accuracy· 2024-04-22
    93.1
    best: 96.1 (CompassMTL 567M with Tailor)
    MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of ExpertsarXiv:2404.15159