423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 03:40:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

patch for gemma cpt

Browse Source
This commit is contained in:
hiyouga
2024-03-12 21:21:54 +08:00
parent 60cc17f3a8
commit 70a3052dd8
2 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/data/preprocess.py
View File

@@ -37,6 +37,10 @@ def preprocess_pretrain_dataset(
k: [t[i : i + block_size] for i in range(0, total_length, block_size)]
for k, t in concatenated_examples.items()
}
if data_args.template == "gemma":
for i in range(len(result["input_ids"])):
result["input_ids"][i][0] = tokenizer.bos_token_id
return result