HyperAIHyperAI超神経
ホームプラットフォームドキュメントニュース論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAIHyperAI超神経

Command Palette

Search for a command to run...

Question Answering On Social Iqa

評価指標

Accuracy

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper TitleRepository
Unicorn 11B (fine-tuned)83.2UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
LLaMA-2 13B + MixLoRA82.5MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
CompassMTL 567M with Tailor82.2Task Compass: Scaling Multi-task Pre-training with Task Prefix
CompassMTL 567M81.7Task Compass: Scaling Multi-task Pre-training with Task Prefix
LLaMA-3 8B+MoSLoRA (fine-tuned)81.0Mixture-of-Subspaces in Low-Rank Adaptation
DeBERTa-Large 304M80.2Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering
DeBERTa-Large 304M (classification-based)79.9Two is Better than Many? Binary Classification as an Effective Approach to Multi-Choice Question Answering
UnifiedQA 3B79.8UnifiedQA: Crossing Format Boundaries With a Single QA System
ExDeBERTa 567M79.6Task Compass: Scaling Multi-task Pre-training with Task Prefix
LLaMA-3 8B + MixLoRA78.8MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
LLaMA-2 7B + MixLoRA78MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts
RoBERTa-Large 355M (fine-tuned)76.7RoBERTa: A Robustly Optimized BERT Pretraining Approach
BERT-large 340M (fine-tuned)64.5SocialIQA: Commonsense Reasoning about Social Interactions
BERT-base 110M (fine-tuned)63.1SocialIQA: Commonsense Reasoning about Social Interactions
GPT-1 117M (fine-tuned)63SocialIQA: Commonsense Reasoning about Social Interactions
phi-1.5-web 1.3B (zero-shot)53.0Textbooks Are All You Need II: phi-1.5 technical report
phi-1.5 1.3B (zero-shot)52.6Textbooks Are All You Need II: phi-1.5 technical report
LLaMA 65B (zero-shot)52.3LLaMA: Open and Efficient Foundation Language Models
Chinchilla (zero-shot)51.3Training Compute-Optimal Large Language Models
Gopher (zero-shot)50.6Scaling Language Models: Methods, Analysis & Insights from Training Gopher
0 of 24 row(s) selected.