chrisociepa / allamo

Simple, hackable and fast implementation for training/finetuning medium-sized LLaMA-based models

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Import_llama_weights.py code bug

RDouglasSharp opened this issue · comments

line 137:
import_tokenizer(args.input_tokenizer_path, args.output_data_dir)
should be:
import_tokenizer(args.input_tokenizer_path, args.output_data_dir, args.max_block_size)

commented

right, thanks! fixed