SundayTheQuant Physicworld

## microgpt.py
"""
The most atomic way to train and inference a GPT LLM in pure, dependency-free Python.
Differences from GPT-2 are minor: layer norm -> rmsnorm, no biases, GeLU -> square ReLU, no weight tying.
The contents of this file is everything algorithmically needed to train a GPT. Everything else is just efficiency.
Art project by @karpathy.
"""

import os       # for os.path.exists
import time     # for time.perf_counter
import math     # for math.log, math.exp
	"""
	The most atomic way to train and inference a GPT LLM in pure, dependency-free Python.
	Differences from GPT-2 are minor: layer norm -> rmsnorm, no biases, GeLU -> square ReLU, no weight tying.
	The contents of this file is everything algorithmically needed to train a GPT. Everything else is just efficiency.
	Art project by @karpathy.
	"""

	import os # for os.path.exists
	import time # for time.perf_counter
	import math # for math.log, math.exp