Parlance
Services
Blog
Team
Education
Evals
Educational Resources
Evals
Inspect, An OSS framework for LLM evals
LLM Eval For Text2SQL
A Deep Dive on LLM Evaluation
RAG
Back to Basics for RAG
Beyond the Basics of RAG
Systematically improving RAG applications
Fine-Tuning
Should you fine-tune?
When and Why to Fine Tune an LLM
Fine-tuning when you’ve already deployed LLMs in prod
Why Fine Tuning is Dead
How to fine-tune
Creating, curating, and cleaning data for LLMs
Best Practices For Fine Tuning Mistral
Train (almost) any LLM using 🤗 autotrain
Fine Tuning OpenAI Models - Best Practices
Deploying Fine-Tuned Models
Advanced topics in fine-tuning
Napkin Math For Fine Tuning
Slaying OOMs with PyTorch FSDP and torchao
Fine Tuning LLMs for Function Calling
Applications
education/applications/**/*.qmd
Prompt Engineering
Evals
Measuring the performance of LLM products
Inspect, An OSS framework for LLM evals
This talk will cover using and extending Inspect, a new OSS Python…
LLM Eval For Text2SQL
Ankur from Braintrust discusses the systematic evaluation and enhancement…
A Deep Dive on LLM Evaluation
Doing LLM evaluation right is crucial, but very challenging! We’ll cover…
No matching items
Educational Resources
Inspect, An OSS framework for LLM evals
