tiny fix

src/llamafactory/__init__.py

@@ -28,9 +28,9 @@ Dependency graph:
   attention:
     transformers>=4.42.4 (gemma+fa2)
   longlora:
-    transformers>=4.41.2,<=4.44.3
+    transformers>=4.41.2,<=4.45.0
   packing:
-    transformers>=4.41.2,<=4.44.3
+    transformers>=4.41.2,<=4.45.0
 
 Disable version checking: DISABLE_VERSION_CHECK=1
 Enable VRAM recording: RECORD_VRAM=1

src/llamafactory/data/collator.py

@@ -81,8 +81,8 @@ class MultiModalDataCollatorForSeq2Seq(DataCollatorForSeq2Seq):
     def __call__(self, features: Sequence[Dict[str, Any]]) -> Dict[str, "torch.Tensor"]:
         batch_images, batch_videos, batch_imglens, batch_vidlens, batch_seqlens = [], [], [], [], []
         for feature in features:
-            images = feature.pop("images") or []  # avoid NoneType
-            videos = feature.pop("videos") or []
+            images = feature.pop("images", None) or []
+            videos = feature.pop("videos", None) or []
             batch_images.extend(images)
             batch_videos.extend(videos)
             batch_imglens.append(len(images))

src/llamafactory/data/processors/pretrain.py

@@ -36,7 +36,7 @@ def preprocess_pretrain_dataset(
         if data_args.template == "gemma":
             text_examples = [tokenizer.bos_token + example for example in text_examples]
 
-        result = tokenizer(text_examples, add_special_tokens=False, max_length=data_args.cutoff_len, truncation=True)
+        result = tokenizer(text_examples, add_special_tokens=False, truncation=True, max_length=data_args.cutoff_len)
     else:
         tokenized_examples = tokenizer(text_examples, add_special_tokens=False)
         concatenated_examples = {k: list(chain(*tokenized_examples[k])) for k in tokenized_examples.keys()}

src/llamafactory/model/model_utils/longlora.py

@@ -353,7 +353,7 @@ def llama_sdpa_attention_forward(
 
 
 def _apply_llama_patch() -> None:
-    require_version("transformers>=4.41.2,<=4.44.3", "To fix: pip install transformers>=4.41.2,<=4.44.3")
+    require_version("transformers>=4.41.2,<=4.45.0", "To fix: pip install transformers>=4.41.2,<=4.45.0")
     LlamaAttention.forward = llama_attention_forward
     LlamaFlashAttention2.forward = llama_flash_attention_2_forward
     LlamaSdpaAttention.forward = llama_sdpa_attention_forward

src/llamafactory/model/model_utils/packing.py

@@ -114,7 +114,7 @@ def get_unpad_data(attention_mask: "torch.Tensor") -> Tuple["torch.Tensor", "tor
 
 
 def _patch_for_block_diag_attn(model_type: str) -> None:
-    require_version("transformers>=4.41.2,<=4.44.3", "To fix: pip install transformers>=4.41.2,<=4.44.3")
+    require_version("transformers>=4.41.2,<=4.45.0", "To fix: pip install transformers>=4.41.2,<=4.45.0")
     if is_transformers_version_greater_than_4_43():
         import transformers.modeling_flash_attention_utils