No-Code LLM Fine-Tuning and Debugging in Real Time: Case Study

Read full article, here

Have you tried the xLLM web API? It allows you to fine-tune and debug an agentic multi-LLM in real time. The input data is part of the anonymized corporate corpus of a Fortune 100 company, dealing with AI policies, documentation, integration, best practices, references, onboarding, and so on. It features one sub-LLM. The full corpus is broken down into 15 sub-LLMs.

One of the goals is to return concise but exhaustive results, using acronyms (a specific table for each sub-LLM) to map multi-tokens found in prompts but not in the corpus, with multi-tokens in the corpus. Exhaustivity is the most overlooked metric when evaluating LLMs designed for search / retrieval. Using xLLM in combination with another LLMs is one of the best approaches, and both can be used to evaluate each other. Yet, thanks to fast in-memory processing, no weight, and no training, the xLLM web API is one of its kind, with capabilities not found in any competing product, free or not.

The document with full sample xLLM session (fine-tuning), illustrations, input sources, backend tables including embeddings, link to the web API, and full xLLM Python code with link to GitHub, is accessible here.

Announcement

If you are more interested in classic LLMs and what the big guys are up, I invite you to attend the Enterprise AI Conference in San Francisco. This is an opportunity to connect with top leaders in the field, such as the CEO of LlamaIndex. Use my code Vincent-25 to get a 75% discount, when registering here. If you cannot attend, feel free to share the code and link (https://mltblog.com/4dcYkf0) with your colleagues and connections.