github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-06-28 16:27:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

Changing single to double quotes for quote consistency

Browse Source
This commit is contained in:
MalikMAlna 2023-04-06 20:07:08 -04:00
parent 334f36d844
commit 17fb6f668a
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
data.py
View File

@ -31,7 +31,7 @@ def tokenize_inputs(config, tokenizer, examples):
# add target tokens, remove bos
input_ids[i, newline_plus_inputs: newline_plus_inputs + len(target_tokens)] = target_tokens
# add eos token, enforce stopping if we don't truncate
# add eos token, enforce stopping if we don't truncate
# we don't want long code to stop generating if truncated during training
if newline_plus_inputs + len(target_tokens) < max_length:
input_ids[i, newline_plus_inputs + len(target_tokens)] = tokenizer.eos_token_id
@ -67,7 +67,7 @@ def load_data(config, tokenizer):
dataset = load_dataset("json", data_files=files, split="train")
else:
dataset = load_dataset(dataset_path, split='train')
dataset = load_dataset(dataset_path, split="train")
dataset = dataset.train_test_split(test_size=.05, seed=config["seed"])