improve handling for empty text on the tokenization step (#502)

src/axolotl/prompt_tokenizers.py

@@ -6,7 +6,7 @@ import functools
 import logging
 from typing import Dict, List, Tuple, Union
 
-from transformers import PreTrainedTokenizer
+from transformers import BatchEncoding, PreTrainedTokenizer
 
 from axolotl.prompters import IGNORE_TOKEN_ID
 
@@ -66,7 +66,14 @@ class PromptTokenizingStrategy(abc.ABC):
             pass
         return False
 
-    def _tokenize(self, prompt: str, add_eos_token=True, strip_bos_token=False):
+    def _tokenize(
+        self, prompt: str, add_eos_token: bool = True, strip_bos_token: bool = False
+    ) -> BatchEncoding:
+        result: BatchEncoding
+        if not prompt.strip():
+            LOG.warning("Empty text requested for tokenization.")
+            result = BatchEncoding(data={"input_ids": [], "attention_mask": []})
+        else:
             result = self.tokenizer(
                 prompt,
                 truncation=True,