Papers with Code 아카이브

Language Modeling

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

0

보존된 평가 기록

0

코드

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

https://github.com/facebookresearch/CodeGen/blob/main/docs/dobf.md

공식 코드

DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

https://github.com/facebookresearch/ELI5

공식 코드

ELI5: Long Form Question Answering

https://github.com/facebookresearch/GPU-DPF

공식 코드

GPU-based Private Information Retrieval for On-Device Machine Learning Inference

https://github.com/facebookresearch/Mask-Predict

공식 코드

Mask-Predict: Parallel Decoding of Conditional Masked Language Models

https://github.com/facebookresearch/MemoryMosaics

공식 코드

Memory Mosaics

https://github.com/facebookresearch/XLM

공식 코드

Large Memory Layers with Product Keys

https://github.com/facebookresearch/adaptive-span

공식 코드

Adaptive Attention Span in Transformers

https://github.com/facebookresearch/alma

공식 코드

On Anytime Learning at Macroscale

https://github.com/facebookresearch/atlas

공식 코드

Atlas: Few-shot Learning with Retrieval Augmented Language Models

https://github.com/facebookresearch/bitsandbytes

공식 코드

8-bit Optimizers via Block-wise Quantization

https://github.com/facebookresearch/cc_net

공식 코드

Unsupervised Cross-lingual Representation Learning at Scale

https://github.com/facebookresearch/coder_reviewer_reranking

공식 코드

Coder Reviewer Reranking for Code Generation

https://github.com/facebookresearch/colorlessgreenRNNs

공식 코드

Colorless green recurrent networks dream hierarchically

https://github.com/facebookresearch/diffq

공식 코드

Differentiable Model Compression via Pseudo Quantization Noise

https://github.com/facebookresearch/dual-system-for-visual-language-reasoning

공식 코드

DOMINO: A Dual-System for Multi-step Visual Language Reasoning

https://github.com/facebookresearch/evaluation-of-nmt-bt

공식 코드

On The Evaluation of Machine Translation Systems Trained With Back-Translation

https://github.com/facebookresearch/large_concept_model

공식 코드

Large Concept Models: Language Modeling in a Sentence Representation Space

https://github.com/facebookresearch/lingua

공식 코드

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

https://github.com/facebookresearch/llama-hd-dataset

공식 코드

Multi-Task Learning for Front-End Text Processing in TTS

https://github.com/facebookresearch/maze_navigation_MLMU

공식 코드

Transformers Can Navigate Mazes With Multi-Step Prediction

https://github.com/facebookresearch/mega

공식 코드

Mega: Moving Average Equipped Gated Attention

https://github.com/facebookresearch/minif2f

공식 코드

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

https://github.com/facebookresearch/motif

공식 코드

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

https://github.com/facebookresearch/npm

공식 코드

Nonparametric Masked Language Modeling

https://github.com/facebookresearch/oni

공식 코드

Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback

https://github.com/facebookresearch/online-dt

공식 코드

Online Decision Transformer

https://github.com/facebookresearch/polymath

공식 코드

Logic.py: Bridging the Gap between LLMs and Constraint Solvers

https://github.com/facebookresearch/radioactive-watermark

공식 코드

Watermarking Makes Language Models Radioactive

https://github.com/facebookresearch/rlcd

공식 코드

RLCD: Reinforcement Learning from Contrastive Distillation for Language Model Alignment

https://github.com/facebookresearch/shepherd

공식 코드

Shepherd: A Critic for Language Model Generation

https://github.com/facebookresearch/simmc2

공식 코드

SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations

https://github.com/facebookresearch/spiritlm

공식 코드

Spirit LM: Interleaved Spoken and Written Language Model

https://github.com/facebookresearch/stepdiff

공식 코드

Step Differences in Instructional Video

https://github.com/facebookresearch/sweet_rl

공식 코드

SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

https://github.com/facebookresearch/synlm

공식 코드

Privately generating tabular data using language models

https://github.com/facebookresearch/task_bench

공식 코드

Quantifying Adaptability in Pre-trained Language Models with 500 Tasks

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