dive-into-llms
《动手学大模型Dive into LLMs》系列编程实践教程
Discover how multi-modal LLMs process and generate text and images. Learn about modality-specific encoders, joint reasoning, and specialized decoders like Stable Diffusion.
Architecture of Multi-Modal Large Language Models: Encoder-LLM-Decoder vs Task Scheduler PatternsExplore multi-modal large language model architectures. Understand encoder-LLM-decoder and task scheduler patterns for processing diverse data inputs.
How to Evaluate the Success of Knowledge Editing in LLMs: The EasyEdit Metrics FrameworkLearn how to evaluate knowledge editing in LLMs with the EasyEdit metrics framework. Discover reliability, generality, locality, and portability measures for successful fact updates without compromising model capabilities.
ROME and MEMIT Methods for Knowledge Editing in LLMs: A Technical GuideExplore ROME and MEMIT knowledge editing methods for LLMs. Learn how rank-one updates and low-rank projections precisely modify model facts without full retraining. Dive into LLMs with this technical guide.
Knowledge Editing Techniques for Language Models: A Practical Guide with EasyEditLearn knowledge editing techniques for language models update factual information without full retraining. Explore practical methods with EasyEdit.
Deterministic vs Probabilistic Watermarking in LLMs: Implementation and Detection MethodsUnderstand deterministic vs probabilistic watermarking in LLMs. Learn about fixed token mappings and biased sampling distributions for effective watermark implementation and detection.
Designing Effective LLM Watermarks: Technical Considerations and Implementation GuideLearn to design effective LLM watermarks balancing detectability, fluency, and robustness. Implement LLM watermarking with our technical guide.
How to Implement Text Watermarks for LLM-Generated Content: A Complete GuideLearn how to implement text watermarks for LLM generated content with the Lordog/dive-into-llms repository. Discover a modular pipeline for embedding, detecting, and evaluating watermarks using KGW, X-SIR, and SIR algorithms.
How KL Divergence Prevents Mode Collapse in RLHF TrainingLearn how KL divergence prevents mode collapse in RLHF training. Discover how this regularization technique ensures policy diversity and optimizes rewards by penalizing deviations from a reference model.
The Three Stages of the RLHF Workflow with PPO: Implementation GuideMaster the three stages of RLHF with PPO: Rollout, Evaluation, and Optimization. This guide details implementing the RLHF workflow to fine-tune LLMs effectively.
How to Implement RLHF Alignment Using the TRL Library and PPO: A Complete GuideLearn to implement RLHF alignment with the TRL library and PPO. This guide details loading models, configuring PPO, and optimizing policy updates for better LLM control.
How the PAIR Method Works for Iterative Prompt Refinement in JailbreakingDiscover how the PAIR method iteratively refines jailbreak prompts to bypass LLM safety features. Learn this prompt engineering technique for advanced LLM analysis in Lordog dive-into-llms.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →