Technova's Public Lair
  • Home
  • About

LLM

A collection of 2 posts
Rosenblatt's 1958 diagram comparing the organization of a biological brain with an artificial perceptron, the idea behind training neural networks.
LLM

Pre-Training, Post-Training & Alignment: How Language Models Are Actually Built

Language models don't get built in a single training run. They go through three distinct phases — pre-training, post-training (fine-tuning), and alignment — each with different goals, data sources, compute requirements, and techniques.
16 Nov 2026 8 min read
Common Visualization of Artificial Neural Network with Chip
AI

Bonsai 2 27B: The 5.9 GB Model That Retains 98.2% of Full-Precision Performance

PrismML's Bonsai 2 27B compresses a 27B multimodal model to 5.9 GB while retaining 98.2% of full-precision benchmark performance — a genuine engineering milestone for local-first AI deployment.
20 Sep 2026 7 min read
Page 1 of 1
Technova's Public Lair © 2026
  • Sign up
Powered by Ghost