https://github.com/koustuvsinha/clutrr-workshop
Compositional Language Understanding with Text-based Relational Reasoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A language model is a model of natural language. Language models are useful for a variety of tasks, including speech recognition, machine translation, natural language generation (generating more human-like text), optical character recognition, route optimization, handwriting recognition, grammar induction, and information retrieval.
Large language models (LLMs), currently their most advanced form, are predominantly based on transformers trained on larger datasets (frequently using words scraped from the public internet). They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model.
Source: Wikipedia
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Compositional Language Understanding with Text-based Relational Reasoning
General-purpose, long-context autoregressive modeling with Perceiver AR
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention
PaLI-X: On Scaling up a Multilingual Vision and Language Model
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Moshi: a speech-text foundation model for real-time dialogue
Moshi: a speech-text foundation model for real-time dialogue
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
VisualBERT: A Simple and Performant Baseline for Vision and Language
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.