Tag
A guide on using Kaggle's free dual Tesla T4 GPUs (32GB VRAM) to run large LLMs with massive context windows, covering multi-GPU parallelism strategies in llama.cpp.
This post demonstrates how to fine-tune a model for free using a single prompt, leveraging the new Google Colab CLI along with Hugging Face's TRL and trackio tools, all orchestrated by an AI agent.