Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

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

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

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

Models/LLaMA2-7b

LLaMA2-7b

Reported on 3 benchmarks across 1 task · 3 papers · 8 SOTA

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

Methodology10 results

parameter-efficient fine-tuningonHellaSwag
Accuracy (% )· uses extra data· 2024-08-27
76.68
SOTA
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs arXiv:2408.15300
parameter-efficient fine-tuningonBoolQ
Accuracy (% )· 2024-08-27
82.63
SOTA
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs arXiv:2408.15300
parameter-efficient fine-tuningonWinoGrande
Accuracy (% )· uses extra data· 2024-08-27
70.8
SOTA
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs arXiv:2408.15300
parameter-efficient fine-tuningonBoolQ
Accuracy (% )· 2024-02-14
81.93
best: 82.63
SOTA
DoRA: Weight-Decomposed Low-Rank Adaptation arXiv:2402.09353
parameter-efficient fine-tuningonWinoGrande
Accuracy (% )· uses extra data· 2024-02-14
70.09
best: 70.8
SOTA
DoRA: Weight-Decomposed Low-Rank Adaptation arXiv:2402.09353
parameter-efficient fine-tuningonHellaSwag
Accuracy (% )· uses extra data· 2021-06-17
76.67
best: 76.68
SOTA
LoRA: Low-Rank Adaptation of Large Language Models arXiv:2106.09685
parameter-efficient fine-tuningonBoolQ
Accuracy (% )· 2021-06-17
80.28
best: 82.63
SOTA
LoRA: Low-Rank Adaptation of Large Language Models arXiv:2106.09685
parameter-efficient fine-tuningonWinoGrande
Accuracy (% )· uses extra data· 2021-06-17
69.85
best: 70.8
SOTA
LoRA: Low-Rank Adaptation of Large Language Models arXiv:2106.09685
parameter-efficient fine-tuningonBoolQ
Accuracy (% )· 2024-08-27
82.63
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs arXiv:2408.15300
parameter-efficient fine-tuningonHellaSwag
Accuracy (% )· uses extra data· 2024-02-14
76.27
best: 76.68
DoRA: Weight-Decomposed Low-Rank Adaptation arXiv:2402.09353