Upload modeling_cogvlm.py

## Compatible with Transformers > 4.41.2

### Details:
The current implementation has an error with the line:
```python
if past_key_values is not None:
past_key_values_length = past_key_values[0][0].shape[2]
seq_length_with_past = seq_length_with_past + past_key_values_length
```
When the Transformers version is > 4.41.2.
The issue is caused by the change in the output of
`_extract_past_from_model_output` function defined in Transformers `src/transformers/generation/utils.py` since version v4.42.0.

Therefore, my pr includes checking the version of Transformers and modifying the process of the output of `_extract_past_from_model_output` to make sure cogvlm2 can work with newer version of Transformers

modeling_cogvlm.py

@@ -1,9 +1,11 @@
 """largely copy from llama and adapt for cogvlm"""
 import warnings
+import packaging.version
 from typing import TYPE_CHECKING, Optional, Tuple, List, Union, Literal, Dict, Any
 
 import math
 import torch
+import transformers
 from torch import nn
 from torch.nn import CrossEntropyLoss
 from torchvision import transforms
@@ -26,7 +28,12 @@ logger = get_logger(__name__)
 
 LANGUAGE_TOKEN_TYPE = 0
 VISION_TOKEN_TYPE = 1
-
+TRANSFORMERS_ABOVE_441 = (
+    True
+    if packaging.version.parse(transformers.__version__)
+    >= packaging.version.parse("4.42.0")
+    else False
+)
 
 # Copied from transformers.models.bart.modeling_bart._make_causal_mask
 def _make_causal_mask(
@@ -736,9 +743,13 @@ class CogVLMForCausalLM(CogVLMPreTrainedModel):
             standardize_cache_format: bool = False,
     ) -> Dict[str, Any]:
         # update past_key_values
-        model_kwargs["past_key_values"] = self._extract_past_from_model_output(
-            outputs, standardize_cache_format=standardize_cache_format
-        )
+        if TRANSFORMERS_ABOVE_441:
+            cache_name, cache = self._extract_past_from_model_output(outputs)
+            model_kwargs[cache_name] = cache
+        else:
+            model_kwargs["past_key_values"] = self._extract_past_from_model_output(
+                outputs, standardize_cache_format=standardize_cache_format
+            )
         if getattr(outputs, "state", None) is not None:
             model_kwargs["state"] = outputs.state