Charles Packer on MemGPT - Weaviate Podcast #73!
Weaviate Podcast
Fine-tuning MemGBT for Long Conversations
The chapter discusses the process of fine-tuning a specific model for MemGBT, which involves long-running conversations with memory management injection. It explains that simulating real conversations is the best way to collect data and emphasizes the importance of manual correction and heuristics to improve parsing.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
