fix #2516

Former-commit-id: ce2340193e751c4212650b27f16c671261015047
2025-10-16 00:28:10 +08:00 · 2024-02-20 20:44:24 +08:00 · 2024-02-20 20:44:24 +08:00 · a3f30038a0
commit a3f30038a0
parent e237f618c2
2 changed files with 4 additions and 4 deletions
--- a/src/llmtuner/data/preprocess.py
+++ b/src/llmtuner/data/preprocess.py
@ -112,9 +112,9 @@ def preprocess_packed_supervised_dataset(
            input_ids += source_ids + target_ids
            labels += source_mask + target_ids

-    if template.efficient_eos:
-        input_ids += [tokenizer.eos_token_id]
-        labels += [tokenizer.eos_token_id]
+        if template.efficient_eos:
+            input_ids += [tokenizer.eos_token_id]
+            labels += [tokenizer.eos_token_id]

    total_length = len(input_ids)
    block_size = data_args.cutoff_len
--- a/src/llmtuner/webui/locales.py
+++ b/src/llmtuner/webui/locales.py
@ -477,7 +477,7 @@ LOCALES = {
        },
        "zh": {
            "label": "序列打包",
-            "info": "在指令监督微调阶段将序列打包为相同长度的样本。",
+            "info": "在指令监督微调时将序列打包为等长样本。",
        },
    },
    "upcast_layernorm": {