Directories
- gpt generations
- gpt-3 text generation
- Text Analysis
- 기본적인 텍스트 분석 기법
- Transformers
- pytorch Transformer 구조 모델 연구
- rlhl
- gpt 강화학습 연구
- LLM parallelism
- 병렬처리를 통한 LLM 서비스 연구
Reading Pappers
Read Pappers
CoMPM: Context Modeling with Speaker’s Pre-trained Memory Tracking for Emotion Recognition in Conversation
Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Few-Shot Parameter-Efficient Fine-Tuning is Betterand Cheaper than In-Context Learning
Few-shot Natural Language Generation for Task-Oriented Dialog
Towards a Human-like Open-Domain Chatbot
Implicit Unlikelihood Training: Improving Neural Text Generation withReinforcement Learning
Few-Shot Text Generation with Pattern-Exploiting Training
Making Pre-trained Language Models Better Few-shot Learners
Persona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Generative Language Models for Paragraph-Level Question Generation
Fine-Tuning Language Models from Human Preferences
GLM-130B: AN OPEN BILINGUAL PRE-TRAINED MODEL
Ankh �: Optimized Protein Language Model Unlocks General-Purpose Modelling
HuaTuo (华驼): Tuning LLaMA Model with Chinese Medical Knowledge