Joseph G JosephGabito

🔥

Grilling Chicken Inasal

AI systems engineer building production agent architectures and distributed backend infrastructure.

Achievements

JosephGabito/README.md

Engineering AI agents and automation systems. Currently spending too much time thinking about orchestration, memory, and context windows.

Meet Rimu ⚡ - my AI coding agent. Reincarnated as a slime, now writing code and shipping alongside me.

Single-file training script for a GP... Single-file training script for a GPT-style decoder trained on TinyStories using GPT-2 BPE (tiktoken). Implements a modern pre-norm stack (RMSNorm + causal SDPA + GELU MLP) with weight tying, bf16 mixed precision (when available), warmup + cosine LR decay, gradient clipping, checkpointing (best + periodic), and a built-in sample generation at the end.
1
"""
2
i16 — Train a GPT-style decoder on TinyStories (tiktoken GPT-2 BPE).
3
4
Usage:
5
python i16_train.py --data TinyStoriesV2-GPT4-train.txt --out checkpoints
visualmd visualmd Public

Your AI agents write piles of Markdown. Reading it shouldn't feel like work. Visual MD turns every README, note, and spec into a calm, searchable library—without uploading your files.

Dart 3
beautiful-cov beautiful-cov Public

Beautiful, local-first Python code coverage reports powered by Coverage.py. Explore project coverage, browse files and folders, see covered and missing lines, and discover which tests executed each…

Python 2

Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.

There was an error while loading. Please reload this page.