The Fine-Tuning Index / Quantize & Merge / #61

pochenai/nano-llm-posttraining

by pochenai · Quantize & Merge · updated 1mo ago

Minimal, readable LLM post-training experiments on one 8GB GPU. Measures forgetting, seed variance, and RL emergence.

48
momentum
26
stars
5
forks
#61
rank
View on GitHub →