https://github.com/nlpodyssey/verbaflow
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
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 They have superseded recurrent neural network-based models, which had previously superseded the purely statistical models, such as word n-gram language model.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.
The Pile: An 800GB Dataset of Diverse Text for Language Modeling
AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model
Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.