Note: In case you come across this issue `TypeError: z_(): incompatible function arguments. The following argument types are supported: 1. (self: torch._C.Node, arg0: str, arg1: torch.Tensor) -> torch._C.Node Invoked with: %531 : Tensor = onnx::Constant(), scope: transformers_modules.pytorch.image_embedding_phi3_v_for_onnx.Phi3ImageEmbedding::/transformers.models.clip.modeling_clip.CLIPVisionModel::img_processor/transformers.models.clip.modeling_clip.CLIPVisionTransformer::vision_model/transformers.models.clip.modeling_clip.CLIPEncoder::encoder/transformers.models.clip.modeling_clip.CLIPEncoderLayer::layers.0/transformers.models.clip.modeling_clip.CLIPSdpaAttention::self_attn , 'value', 0.125 (Occurred when translating scaled_dot_product_attention).` please make sure that CLIP_VIT_LARGE_PATCH14_336_CONFIG is set up to use attn_implementation="eager" (if you can't use SDPA)
Note: In case you come across this issue `TypeError: z_(): incompatible function arguments. The following argument types are supported:
1. (self: torch._C.Node, arg0: str, arg1: torch.Tensor) -> torch._C.Node
Invoked with: %531 : Tensor = onnx::Constant(), scope: transformers_modules.pytorch.image_embedding_phi3_v_for_onnx.Phi3ImageEmbedding::/transformers.models.clip.modeling_clip.CLIPVisionModel::img_processor/transformers.models.clip.modeling_clip.CLIPVisionTransformer::vision_model/transformers.models.clip.modeling_clip.CLIPEncoder::encoder/transformers.models.clip.modeling_clip.CLIPEncoderLayer::layers.0/transformers.models.clip.modeling_clip.CLIPSdpaAttention::self_attn
, 'value', 0.125
(Occurred when translating scaled_dot_product_attention).` please make sure that CLIP_VIT_LARGE_PATCH14_336_CONFIG is set up to use attn_implementation="eager" (if you can't use SDPA)