Pinned Loading

1. llm-from-scratch-stack llm-from-scratch-stack Public

   A research-grade, reproducible end-to-end LLM training stack built from scratch in PyTorch. Includes tokenizer training, GPT-style pretraining, scaling experiments, SFT and DPO post-training, evalu…

   Jupyter Notebook

2. frontier-evals-harness frontier-evals-harness Public

   frontier-evals-harness is a lightweight framework for benchmarking frontier language models. It provides deterministic suite versioning, modular adapters, standardized scoring, and paired statistic…

   Python

3. microstructure-rnn-latent-diffusion-pbx microstructure-rnn-latent-diffusion-pbx Public

   Two-stage generative AI framework for topology-preserved synthetic PBX microstructures (GraphRNN + conditional latent diffusion).

4. vision-foundation-mae vision-foundation-mae Public

   Tutorial-grade, repo-grade reproducible MAE pretraining for ViT in PyTorch, with linear probe, fine-tune, and exported encoder checkpoints.

   Python