We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 8e7cdd2 commit 3cb4e20Copy full SHA for 3cb4e20
optimum/intel/openvino/modeling_visual_language.py
@@ -979,13 +979,6 @@ def preprocess_inputs(
979
Preprocess input instruction and an image.
980
"""
981
982
- # modified from https://github.com/huggingface/transformers/blob/v4.55.0/src/transformers/generation/utils.py#L1992
983
- def _prepare_cache_for_generation(self, *args, **kwargs):
984
- """
985
- This function is used to prepare the cache : when calling `generate` before the first inference, an instance of `DynamicCache` will be created.
986
- For OVModel, we don't want model_kwargs to be updated before generation.
987
988
- return
989
990
class _OVLlavaForCausalLM(OVModelForVisualCausalLM):
991
def __init__(
0 commit comments