LLM optimization beyond fine-tuning
Watch a February 2024 webinar on prompt optimization, evaluation, RAG techniques, model pruning, quantization, semantic caching, and edge deployment.
What's in this video
- This February 2024 SUPERWISE® webinar examines ways to optimize LLM applications without fine-tuning.
- It covers prompt optimization, test-driven development basics, evaluation paths, and synthetic data.
- It explores production insights, RLHF, self-querying, contextual compression, and parent and child chunking for RAG.
- It also discusses model pruning, quantization, semantic caching, and edge deployment.