Papers with Code 아카이브

Multi-task Language Understanding

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크: 0
평가표: 5
보존된 평가 기록: 79

The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more. https://arxiv.org/pdf/2009.03300.pdf

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/NVIDIA/NeMo

공식 코드

Llama 3 Meets MoE: Efficient Upcycling

https://github.com/allenai/unifiedqa

공식 코드

UnifiedQA: Crossing Format Boundaries With a Single QA System

https://github.com/ceferisbarov/TUMLU

공식 코드

TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages

https://github.com/deepseek-ai/deepseek-r1

공식 코드

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

https://github.com/devichand579/HPT

공식 코드

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles

https://github.com/eleutherai/gpt-neox

공식 코드

GPT-NeoX-20B: An Open-Source Autoregressive Language Model

https://github.com/facebookresearch/atlas

공식 코드

Atlas: Few-shot Learning with Retrieval Augmented Language Models

https://github.com/facebookresearch/llama

공식 코드

LLaMA: Open and Efficient Foundation Language Models

https://github.com/fajri91/indommlu

공식 코드

Large Language Models Only Pass Primary School Exams in Indonesia: A Comprehensive Test on IndoMMLU

https://github.com/google-research/ALBERT

공식 코드

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

https://github.com/google-research/google-research

공식 코드

UL2: Unifying Language Learning Paradigms

https://github.com/hendrycks/test

공식 코드

Measuring Massive Multitask Language Understanding

https://github.com/leeroo-ai/leeroo_orchestrator

공식 코드

Routoo: Learning to Route to Large Language Models Effectively

https://github.com/liangzid/MERGE

공식 코드

MERGE: Fast Private Text Generation

https://github.com/mbzuai-nlp/arabicmmlu

공식 코드

ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic

https://github.com/microsoft/mmlu-cf

공식 코드

MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark

https://github.com/mistralai/mistral-src

공식 코드

Mistral 7B

https://github.com/mmatena/model_merging

공식 코드

Merging Models with Fisher-Weighted Averaging

https://github.com/openai/evals

공식 코드

GPT-4 Technical Report

https://github.com/openai/gpt-3

공식 코드

Language Models are Few-Shot Learners

https://github.com/openai/human-eval

공식 코드

Evaluating Large Language Models Trained on Code

https://github.com/paperswithcode/galai

공식 코드

Galactica: A Large Language Model for Science

https://github.com/pytorch/fairseq

공식 코드

RoBERTa: A Robustly Optimized BERT Pretraining Approach

https://github.com/ruili33/sec

공식 코드

Are Human-generated Demonstrations Necessary for In-context Learning?

https://github.com/suu990901/LLaMA-InfoEntropy-Loss

공식 코드

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models

https://github.com/thudm/glm-130b

공식 코드

GLM-130B: An Open Bilingual Pre-trained Model

https://github.com/wuhy68/parameter-efficient-moe

공식 코드

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

https://github.com/yaoching0/gac

공식 코드

Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.