Questions tagged [large-language-model]

This tag is for topics related to large language models (LLMs). Remember to use more specific tags like GPT variants, PaLM, LLaMa, BLOOM, Claude, etc., whenever possible.

Ajax lm is causing parser error with sql agent

I'm having trouble getting the agent to generate an SQL query based on the prompt. Every time I try to execute the agent, it gives me an error message saying "This output parser only works with ChatGeneration output". The SQL is being generated properly us ...

What is the best way to transfer a PDF document to a Jupyter notebook, perform data processing within the notebook, and finally showcase the outcome on a web application?

I currently have a Jupyter notebook that is able to process a PDF file, execute an LLM model, and provide a summary of the content. I am considering creating a web application where users can upload their PDF files, send them to the Jupyter notebook for p ...

Introducing nanoGPT, a powerful text generation model trained on

I'm working on using nanoGPT from https://github.com/karpathy/nanoGPT with a customized input file. Although I've raised the issue on the repository itself (refer to issue 172), I haven't received any responses yet. Therefore, I'm seek ...