Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Dpo vocab size clarification (#628)
* Llama3 from scratch improvements * vocab size should be 50257 not 50256 * restore
S
Sebastian Raschka committed
adaf4faaae0edc90d5a01898336674677fddcb7b
Parent: 47c0360
Committed by GitHub <noreply@github.com>
on 4/18/2025, 10:20:56 PM