/LLM_intro-workshop

Primary LanguageJupyter Notebook

Game Plan

  • Transformer architecture overview
  • Using LLMs
  • Evaluating LLMs
    • Existing common evaluations
      • MT-Bench
      • AlpacaEval
    • Creating your evaluation
  • Deploying LLMs
    • Deploy to the huggingface API
    • OpenAI completions standard