osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

Move enc to gloabal namespace

Browse Source
This commit is contained in:
vinjn 2024-01-12 12:47:42 -08:00
parent eba36e8464
commit dccf362c2b
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
data/openwebtext/prepare.py
View File

@ -16,6 +16,8 @@ num_proc = 8
# it is better than 1 usually though # it is better than 1 usually though
num_proc_load_dataset = num_proc num_proc_load_dataset = num_proc
enc = tiktoken.get_encoding("gpt2")
if __name__ == '__main__': if __name__ == '__main__':
# takes 54GB in huggingface .cache dir, about 8M documents (8,013,769) # takes 54GB in huggingface .cache dir, about 8M documents (8,013,769)
dataset = load_dataset("openwebtext", num_proc=num_proc_load_dataset) dataset = load_dataset("openwebtext", num_proc=num_proc_load_dataset)
@ -38,7 +40,6 @@ if __name__ == '__main__':
# }) # })
# we now want to tokenize the dataset. first define the encoding function (gpt2 bpe) # we now want to tokenize the dataset. first define the encoding function (gpt2 bpe)
enc = tiktoken.get_encoding("gpt2")
def process(example): def process(example):
ids = enc.encode_ordinary(example['text']) # encode_ordinary ignores any special tokens ids = enc.encode_ordinary(example['text']) # encode_ordinary ignores any special tokens
ids.append(enc.eot_token) # add the end of text token, e.g. 50256 for gpt2 bpe ids.append(enc.eot_token) # add the end of text token, e.g. 50256 for gpt2 bpe