- Transformer architecture overview
- Using LLMs
- API hosted
- Locally Hosted
- Ollama
- Huggingface
- Pytorch
- Evaluating LLMs
- Existing common evaluations
- MT-Bench
- AlpacaEval
- Creating your evaluation
- Existing common evaluations
- Deploying LLMs
- Deploy to the huggingface API
- OpenAI completions standard