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
webbrain-one-389594's profile picture
webbrain-one-177929's profile picture
jandrewq's profile picture·
AI & ML interests
Supervised and Unsupervised Learning, with a pinch of Large Language Models
Recent Activity
upvoted a collection 1 day ago
H-Net updated a model 3 months ago
ulmentflam/gpt2-774m-fineweb-nvfp4-mojo updated a model 3 months ago
ulmentflam/gpt2-774m-fineweb-fp8-mojoOrganizations
None yet