Large Language models(LLMs)
- Large Language Models: From Theory to Financial Applications
- Fundamentals of LLMs and the Transformer Architecture
- A Workflow for Fine-Tuning Transformers with Hugging Face
- The BPE Algorithm: A Detailed Breakdown of Tokenization
- Extending the LLaMA Tokenizer with a Custom Chinese Vocabulary
- An Introduction to Retrieval-Augmented Generation (RAG)
- Advanced RAG: Focusing on Recursive Chunking Strategies
- Core RAG Components: Embedding and Retrieval Techniques
- Retrieval-Augmented Generation: Advanced Techniques and Performance Metrics
- Principles of In-Context Learning and Retrieval Augmentation
- In-Context Retrieval-Augmented Language Models
- The Generate-then-Read Framework for Context Generation
- Generate Rather Than Retrieve: Large Language Models are Strong Context Generators
- Fine-Tuning a Language Model with Synthetically Generated Data Using QLoRA
- A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications
- System 2 Attention (is something you might need too)
- Thread of Thought: Unraveling Chaotic Contexts
- LLM Applications: Synthetic Data Generation and Financial Document Analysis
Stochastic Calculus for Finance