Carlos García's picture
🤝 Open to Collab

Carlos García

cgarciams
·

AI & ML interests

Building a GPT-2 medium size (approx. 400 M parameters) model from scratch, using PyTorch, the OpenWebText dataset, Tiktoken, AdamW optimizer and FlashAttention. Just for fun.

Recent Activity

updated a model 5 days ago
cgarciams/gsp2_355m_sft
published a model 5 days ago
cgarciams/gsp2_355m_sft
updated a model 22 days ago
cgarciams/gpt_124m
View all activity

Organizations

Universidad de Zaragoza's profile picture