irt24

↗ HN profile [ 32.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. "GGUF quantization" is the most popular tech stack for quantizing Llama-like models for CPU. But the documentation is very sparse, and the maintainers made it clear that writing a paper is not their priority. So I spent…

  2. To build this model, we scraped 4 weeks' worth of user-issued text prompts from Midjourney's public Discord server. We released the dataset on Kaggle: https://www.kaggle.com/datasets/succinctlyai/midjourney-text....