anonym5035
/

gpt2_dense_50M_same_total_param

Model card Files Files and versions

gpt2_dense_50M_same_total_param / upload_project_hf.py

Commit History

Initial commit of GPT-2 46M SwiGLU Dense baseline model architecture and configs

fa2fdd8
verified

Soham Jain commited on 13 days ago