Enhance your LLM's performance through prompt engineering. Use system and chain-of-thought prompts for precise responses. Employ self-consistency by repeatedly consulting the model.
PROMPT ENGINEERING
-
Control AI Model Outputs: Temperature and Penalty Parameters
By
–
Identify shortcomings and adjust parameters like temperature, stop sequences, frequency and presence penalties to control outputs. Lower temperatures are perfect for summarizing or answering questions, higher ones foster creativity.
-
LLM Decoding Methods: Greedy, Top-K, Nucleus Sampling, Beam Search
By
–
Choosing the right decoding method is also key for LLM performance. Techniques like greedy decoding, top K sampling, nucleus sampling, and beam search each offer their unique advantages and you need to opt for the one that best suits your use case.
-
Preparing GPT-Based Applications for Commercial Deployment
By
–
How to make a GPT-based app ready for commercial use? Start by defining the model's desired responses, then test variations like GPT-4 or open-source ones to identify areas of refinement.
-
AI Photography Styles: Best Practices and Applications
By
–
They seem to work best on photography styles.
-
Designing LLM-Powered Systems with Real-World APIs
By
–
Learn practical methods for designing and implementing large language model (LLM)-powered systems on real-world data using popular, ready-to-go APIs. #llm #inference Register for free: https://
nvda.ws/400J2W4 -
Getting Started with RAG: Chroma and Mistral AI Guide
By
–
Retrieval augmented generation is all the rage, but getting started can be overwhelming. To help you get started and navigate all of the moving pieces, we wrote a blog post about how to do RAG with @trychroma and @MistralAI
's 7B-instruct. -
LLaMA-13B Model Classifies Text-to-Image Prompts for Safety
By
–
To go alongside sdxl-emoji I also trained a llama-13b fine-tune to classify text to image prompts as safe (0) or toxic (10). That model is also approaching 1M runs: https://
replicate.com/fofr/prompt-cl
assifier
… Trained on all the toxic prompts people tried after hitting #1 on Hacker News. -
Reverse Engineering ChatGPT Audio Conversation System Prompts
By
–
Has anyone dug out the system prompt/rules for the ChatGPT audio conversation mode?