Model checkpoints trained from scratch with llm.mojo (Mojo/MAX port of Karpathy's llm.c). https://github.com/ulmentflam/llm.mojo
John Owen
ulmentflam
AI & ML interests
Supervised and Unsupervised Learning, with a pinch of Large Language Models
Recent Activity
updated a collection 2 days ago
llm.mojo GPT-2 releases updated a model 2 days ago
ulmentflam/gpt2-124m-fineweb-mojo published a model 2 days ago
ulmentflam/gpt2-124m-fineweb-mojoOrganizations
datasets 0
None public yet