wandbot
Members
This team has no public members. You must be a member to see who's a part of this team.
Projects
Runs
Name
Project
State
Created
User
No rows found
Loading...
Reports
RAGs To Riches: Bringing Wandbot into Production
Lessons we learned bringing our LLM-powered documentation bot into production
3358 views
Last edit 5 months agoHow to Evaluate an LLM, Part 1: Building an Evaluation Dataset for our LLM System
Building gold standard questions for evaluating our QA bot based on production data.
5894 views Last edit 3 months agoHow to Evaluate an LLM, Part 2: Manual Evaluation of Wandbot, our LLM-Powered Docs Assistant
How we used manual annotation from subject matter experts to generate a baseline correctness score and what we learned about how to improve our system and our annotation process
2855 views Last edit 1 year agoHow to evaluate an LLM Part 3: LLMs evaluating LLMs
Employing auto-evaluation strategies to evaluate different component of our Wandbot RAG-based support system.
3886 views Last edit 1 year agoImplementing RLHF: Learning to Summarize with trlX
Implementation of Reinforcement Learning with Human Feedback for text summarization task using CarperAI's trlX framework.
31207 views Last edit 2 years agoWandBot: GPT-4 Powered Chat Support
This article explores how we built a support bot, enriched with documentation, code, and blogs, to answer user questions with GPT-4, Langchain, and Weights & Biases.
4666 views Last edit 2 years agoRLHF: Hyperparameter Optimization for trlX
In this article, we follow a step-by-step guide for performing hyperparameter optimization using Ray Tune and Weights & Biases, looking at how trlX can help.
3090 views Last edit 2 years ago