Merge pull request #282 from mihainadas/master-1

Fixes https://github.com/karpathy/llama2.c/issues/280
This commit is contained in:
Andrej
2023-08-13 10:13:08 -07:00
committed by GitHub
+1 -1
View File
@@ -120,7 +120,7 @@ def train_vocab(vocab_size):
def process_shard(args, vocab_size):
shard_id, shard = args
tokenizer_model = get_tokenizer_model_path()
tokenizer_model = get_tokenizer_model_path(vocab_size)
enc = Tokenizer(tokenizer_model)
with open(shard, "r") as f:
data = json.load(f)