tiny-random-llava-ov / openvino_vision_embeddings_model.xml
katuni4ka's picture
Upload 15 files
50e8eb3 verified
<?xml version="1.0"?>
<net name="Model3" version="11">
<layers>
<layer id="0" name="pixel_values" type="Parameter" version="opset1">
<data shape="?,3,?,?" element_type="f32" />
<output>
<port id="0" precision="FP32" names="pixel_values">
<dim>-1</dim>
<dim>3</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="1" name="self.vision_tower.vision_model.embeddings.class_embedding" type="Const" version="opset1">
<data element_type="f32" shape="32" offset="0" size="128" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.embeddings.class_embedding">
<dim>32</dim>
</port>
</output>
</layer>
<layer id="2" name="self.vision_tower.vision_model.embeddings.patch_embedding.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 3, 2, 2" offset="128" size="1536" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.embeddings.patch_embedding.weight">
<dim>32</dim>
<dim>3</dim>
<dim>2</dim>
<dim>2</dim>
</port>
</output>
</layer>
<layer id="3" name="__module.vision_tower.vision_model.embeddings.patch_embedding/aten::_convolution/Convolution" type="Convolution" version="opset1">
<data strides="2, 2" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>3</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>3</dim>
<dim>2</dim>
<dim>2</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="49,patch_embeds">
<dim>-1</dim>
<dim>32</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="4" name="ShapeOf_13579" type="ShapeOf" version="opset3">
<data output_type="i64" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>32</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
</input>
<output>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="5" name="Constant_13580" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1664" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="6" name="Constant_13581" type="Const" version="opset1">
<data element_type="i64" shape="" offset="1664" size="8" />
<output>
<port id="0" precision="I64" />
</output>
</layer>
<layer id="7" name="Gather_13582" type="Gather" version="opset8">
<data batch_dims="0" />
<input>
<port id="0" precision="I64">
<dim>4</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64" />
</input>
<output>
<port id="3" precision="I64" names="42,79">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="8" name="Constant_13467" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1672" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="9" name="Constant_13469" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1672" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="10" name="__module.vision_tower.vision_model.embeddings/prim::ListConstruct" type="Concat" version="opset1">
<data axis="0" />
<input>
<port id="0" precision="I64">
<dim>1</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="3" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="11" name="__module.vision_tower.vision_model.embeddings/aten::expand/Broadcast" type="Broadcast" version="opset3">
<data mode="bidirectional" />
<input>
<port id="0" precision="FP32">
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="53">
<dim>-1</dim>
<dim>1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="12" name="Constant_13591" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="1680" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="13" name="__module.vision_tower.vision_model.embeddings/aten::flatten/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>32</dim>
<dim>-1</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="50">
<dim>-1</dim>
<dim>32</dim>
<dim>-1</dim>
</port>
</output>
</layer>
<layer id="14" name="__module.vision_tower.vision_model.embeddings/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="3" offset="1704" size="12" />
<output>
<port id="0" precision="I32">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="15" name="__module.vision_tower.vision_model.embeddings/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>32</dim>
<dim>-1</dim>
</port>
<port id="1" precision="I32">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="51">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="16" name="__module.vision_tower.vision_model.embeddings/aten::cat/Concat" type="Concat" version="opset1">
<data axis="1" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>1</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="55,embeddings.1">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="17" name="__module.vision_tower.vision_model.embeddings/aten::add/Multiply" type="Const" version="opset1">
<data element_type="f32" shape="1, 226, 32" offset="1716" size="28928" />
<output>
<port id="0" precision="FP32">
<dim>1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="18" name="__module.vision_tower.vision_model.embeddings/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>-1</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="58">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="19" name="__module.vision_tower.vision_model.pre_layrnorm/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="30644" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="20" name="__module.vision_tower.vision_model.pre_layrnorm/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="62,residual.1">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="21" name="__module.vision_tower.vision_model.encoder.layers.0.layer_norm1/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="30644" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="22" name="__module.vision_tower.vision_model.encoder.layers.0.layer_norm1/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="74,hidden_states.1">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="23" name="self.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 32" offset="30648" size="4096" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight">
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="24" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="84,query_states.1">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="25" name="Constant_13592" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="34744" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="26" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::view/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="92">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="27" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Constant" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="34776" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="28" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Transpose" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="93">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="29" name="self.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 32" offset="34792" size="4096" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight">
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="30" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="87,key_states.1">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="31" name="Constant_13593" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="34744" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="32" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::view/Reshape_1" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="95">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="33" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Constant_1" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="34776" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="34" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Transpose_1" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="96">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="35" name="self.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 32" offset="38888" size="4096" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight">
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="36" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="90,value_states.1">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="37" name="Constant_13594" type="Const" version="opset1">
<data element_type="i64" shape="4" offset="34744" size="32" />
<output>
<port id="0" precision="I64">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="38" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::view/Reshape_2" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="98">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="39" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Constant_2" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="34776" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="40" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Transpose_2" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="99">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="41" name="Constant_11010" type="Const" version="opset1">
<data element_type="f32" shape="" offset="42984" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="42" name="27" type="Const" version="opset1">
<data element_type="f32" shape="" offset="42988" size="4" />
<output>
<port id="0" precision="FP32" names="27" />
</output>
</layer>
<layer id="43" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::scaled_dot_product_attention/ScaledDotProductAttention" type="ScaledDotProductAttention" version="opset13">
<data causal="false" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
<port id="2" precision="FP32">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
<port id="3" precision="FP32" />
<port id="4" precision="FP32" />
</input>
<output>
<port id="5" precision="FP32" names="100,attn_output.1">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="44" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Constant_3" type="Const" version="opset1">
<data element_type="i32" shape="4" offset="34776" size="16" />
<output>
<port id="0" precision="I32">
<dim>4</dim>
</port>
</output>
</layer>
<layer id="45" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::transpose/Transpose_3" type="Transpose" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>4</dim>
<dim>226</dim>
<dim>8</dim>
</port>
<port id="1" precision="I32">
<dim>4</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="101,attn_output.3">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
</output>
</layer>
<layer id="46" name="Constant_13595" type="Const" version="opset1">
<data element_type="i64" shape="3" offset="42992" size="24" />
<output>
<port id="0" precision="I64">
<dim>3</dim>
</port>
</output>
</layer>
<layer id="47" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn/aten::reshape/Reshape" type="Reshape" version="opset1">
<data special_zero="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>4</dim>
<dim>8</dim>
</port>
<port id="1" precision="I64">
<dim>3</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="103">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="48" name="self.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 32" offset="43016" size="4096" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight">
<dim>32</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="49" name="__module.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="106,hidden_states.3">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="50" name="__module.vision_tower.vision_model.encoder.layers.0/aten::add/Add" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="107,residual.3">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="51" name="__module.vision_tower.vision_model.encoder.layers.0.layer_norm2/aten::layer_norm/Multiply" type="Const" version="opset1">
<data element_type="i32" shape="1" offset="30644" size="4" />
<output>
<port id="0" precision="I32">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="52" name="__module.vision_tower.vision_model.encoder.layers.0.layer_norm2/aten::layer_norm/MVN" type="MVN" version="opset6">
<data eps="9.9999997473787516e-06" normalize_variance="true" eps_mode="INSIDE_SQRT" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I32">
<dim>1</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="111">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="53" name="self.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight" type="Const" version="opset1">
<data element_type="f32" shape="37, 32" offset="47112" size="4736" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight">
<dim>37</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="54" name="__module.vision_tower.vision_model.encoder.layers.0.mlp.fc1/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>37</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="117,input.1">
<dim>-1</dim>
<dim>226</dim>
<dim>37</dim>
</port>
</output>
</layer>
<layer id="55" name="Constant_13523" type="Const" version="opset1">
<data element_type="f32" shape="" offset="51848" size="4" />
<output>
<port id="0" precision="FP32" />
</output>
</layer>
<layer id="56" name="__module.vision_tower.vision_model.encoder.layers.0.mlp.activation_fn/aten::mul/Multiply_1" type="Swish" version="opset4">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>37</dim>
</port>
<port id="1" precision="FP32" />
</input>
<output>
<port id="2" precision="FP32" names="120">
<dim>-1</dim>
<dim>226</dim>
<dim>37</dim>
</port>
</output>
</layer>
<layer id="57" name="self.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight" type="Const" version="opset1">
<data element_type="f32" shape="32, 37" offset="51852" size="4736" />
<output>
<port id="0" precision="FP32" names="self.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight">
<dim>32</dim>
<dim>37</dim>
</port>
</output>
</layer>
<layer id="58" name="__module.vision_tower.vision_model.encoder.layers.0.mlp.fc2/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>37</dim>
</port>
<port id="1" precision="FP32">
<dim>32</dim>
<dim>37</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="123,hidden_states.5">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="59" name="__module.vision_tower.vision_model.encoder.layers.0/aten::add/Add_1" type="Add" version="opset1">
<data auto_broadcast="numpy" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="124,185,9,residual.5">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="60" name="Constant_11629" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1672" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="61" name="Constant_11631" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="56588" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="62" name="Constant_11633" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1672" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="63" name="aten::slice/Reshape_1" type="Const" version="opset1">
<data element_type="i64" shape="1" offset="1672" size="8" />
<output>
<port id="0" precision="I64">
<dim>1</dim>
</port>
</output>
</layer>
<layer id="64" name="aten::slice/Slice_1" type="Slice" version="opset8">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>226</dim>
<dim>32</dim>
</port>
<port id="1" precision="I64">
<dim>1</dim>
</port>
<port id="2" precision="I64">
<dim>1</dim>
</port>
<port id="3" precision="I64">
<dim>1</dim>
</port>
<port id="4" precision="I64">
<dim>1</dim>
</port>
</input>
<output>
<port id="5" precision="FP32" names="14">
<dim>-1</dim>
<dim>225</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="65" name="self.multi_modal_projector.linear_1.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 32" offset="56596" size="2048" />
<output>
<port id="0" precision="FP32" names="self.multi_modal_projector.linear_1.weight">
<dim>16</dim>
<dim>32</dim>
</port>
</output>
</layer>
<layer id="66" name="__module.multi_modal_projector.linear_1/aten::linear/MatMul" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>225</dim>
<dim>32</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>32</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="195">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="67" name="__module.multi_modal_projector.act/aten::gelu/Gelu" type="Gelu" version="opset7">
<data approximation_mode="ERF" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="1" precision="FP32" names="196">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="68" name="self.multi_modal_projector.linear_2.weight" type="Const" version="opset1">
<data element_type="f32" shape="16, 16" offset="58644" size="1024" />
<output>
<port id="0" precision="FP32" names="self.multi_modal_projector.linear_2.weight">
<dim>16</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="69" name="__module.multi_modal_projector.linear_2/aten::linear/Add" type="MatMul" version="opset1">
<data transpose_a="false" transpose_b="true" />
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
<port id="1" precision="FP32">
<dim>16</dim>
<dim>16</dim>
</port>
</input>
<output>
<port id="2" precision="FP32" names="last_hidden_state">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
</output>
</layer>
<layer id="70" name="Result_11692" type="Result" version="opset1">
<input>
<port id="0" precision="FP32">
<dim>-1</dim>
<dim>225</dim>
<dim>16</dim>
</port>
</input>
</layer>
</layers>
<edges>
<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
<edge from-layer="1" from-port="0" to-layer="11" to-port="0" />
<edge from-layer="2" from-port="0" to-layer="3" to-port="1" />
<edge from-layer="3" from-port="2" to-layer="4" to-port="0" />
<edge from-layer="3" from-port="2" to-layer="13" to-port="0" />
<edge from-layer="4" from-port="1" to-layer="7" to-port="0" />
<edge from-layer="5" from-port="0" to-layer="7" to-port="1" />
<edge from-layer="6" from-port="0" to-layer="7" to-port="2" />
<edge from-layer="7" from-port="3" to-layer="10" to-port="0" />
<edge from-layer="8" from-port="0" to-layer="10" to-port="1" />
<edge from-layer="9" from-port="0" to-layer="10" to-port="2" />
<edge from-layer="10" from-port="3" to-layer="11" to-port="1" />
<edge from-layer="11" from-port="2" to-layer="16" to-port="0" />
<edge from-layer="12" from-port="0" to-layer="13" to-port="1" />
<edge from-layer="13" from-port="2" to-layer="15" to-port="0" />
<edge from-layer="14" from-port="0" to-layer="15" to-port="1" />
<edge from-layer="15" from-port="2" to-layer="16" to-port="1" />
<edge from-layer="16" from-port="2" to-layer="18" to-port="0" />
<edge from-layer="17" from-port="0" to-layer="18" to-port="1" />
<edge from-layer="18" from-port="2" to-layer="20" to-port="0" />
<edge from-layer="19" from-port="0" to-layer="20" to-port="1" />
<edge from-layer="20" from-port="2" to-layer="22" to-port="0" />
<edge from-layer="20" from-port="2" to-layer="50" to-port="0" />
<edge from-layer="21" from-port="0" to-layer="22" to-port="1" />
<edge from-layer="22" from-port="2" to-layer="24" to-port="0" />
<edge from-layer="22" from-port="2" to-layer="30" to-port="0" />
<edge from-layer="22" from-port="2" to-layer="36" to-port="0" />
<edge from-layer="23" from-port="0" to-layer="24" to-port="1" />
<edge from-layer="24" from-port="2" to-layer="26" to-port="0" />
<edge from-layer="25" from-port="0" to-layer="26" to-port="1" />
<edge from-layer="26" from-port="2" to-layer="28" to-port="0" />
<edge from-layer="27" from-port="0" to-layer="28" to-port="1" />
<edge from-layer="28" from-port="2" to-layer="43" to-port="0" />
<edge from-layer="29" from-port="0" to-layer="30" to-port="1" />
<edge from-layer="30" from-port="2" to-layer="32" to-port="0" />
<edge from-layer="31" from-port="0" to-layer="32" to-port="1" />
<edge from-layer="32" from-port="2" to-layer="34" to-port="0" />
<edge from-layer="33" from-port="0" to-layer="34" to-port="1" />
<edge from-layer="34" from-port="2" to-layer="43" to-port="1" />
<edge from-layer="35" from-port="0" to-layer="36" to-port="1" />
<edge from-layer="36" from-port="2" to-layer="38" to-port="0" />
<edge from-layer="37" from-port="0" to-layer="38" to-port="1" />
<edge from-layer="38" from-port="2" to-layer="40" to-port="0" />
<edge from-layer="39" from-port="0" to-layer="40" to-port="1" />
<edge from-layer="40" from-port="2" to-layer="43" to-port="2" />
<edge from-layer="41" from-port="0" to-layer="43" to-port="3" />
<edge from-layer="42" from-port="0" to-layer="43" to-port="4" />
<edge from-layer="43" from-port="5" to-layer="45" to-port="0" />
<edge from-layer="44" from-port="0" to-layer="45" to-port="1" />
<edge from-layer="45" from-port="2" to-layer="47" to-port="0" />
<edge from-layer="46" from-port="0" to-layer="47" to-port="1" />
<edge from-layer="47" from-port="2" to-layer="49" to-port="0" />
<edge from-layer="48" from-port="0" to-layer="49" to-port="1" />
<edge from-layer="49" from-port="2" to-layer="50" to-port="1" />
<edge from-layer="50" from-port="2" to-layer="52" to-port="0" />
<edge from-layer="50" from-port="2" to-layer="59" to-port="0" />
<edge from-layer="51" from-port="0" to-layer="52" to-port="1" />
<edge from-layer="52" from-port="2" to-layer="54" to-port="0" />
<edge from-layer="53" from-port="0" to-layer="54" to-port="1" />
<edge from-layer="54" from-port="2" to-layer="56" to-port="0" />
<edge from-layer="55" from-port="0" to-layer="56" to-port="1" />
<edge from-layer="56" from-port="2" to-layer="58" to-port="0" />
<edge from-layer="57" from-port="0" to-layer="58" to-port="1" />
<edge from-layer="58" from-port="2" to-layer="59" to-port="1" />
<edge from-layer="59" from-port="2" to-layer="64" to-port="0" />
<edge from-layer="60" from-port="0" to-layer="64" to-port="1" />
<edge from-layer="61" from-port="0" to-layer="64" to-port="2" />
<edge from-layer="62" from-port="0" to-layer="64" to-port="3" />
<edge from-layer="63" from-port="0" to-layer="64" to-port="4" />
<edge from-layer="64" from-port="5" to-layer="66" to-port="0" />
<edge from-layer="65" from-port="0" to-layer="66" to-port="1" />
<edge from-layer="66" from-port="2" to-layer="67" to-port="0" />
<edge from-layer="67" from-port="1" to-layer="69" to-port="0" />
<edge from-layer="68" from-port="0" to-layer="69" to-port="1" />
<edge from-layer="69" from-port="2" to-layer="70" to-port="0" />
</edges>
<rt_info>
<Runtime_version value="2024.5.0-17202-a7ccc5e0efc" />
<conversion_parameters>
<framework value="pytorch" />
<is_python_object value="True" />
</conversion_parameters>
<optimum>
<optimum_intel_version value="1.20.0.dev0+7cc52a7" />
<optimum_version value="1.23.2" />
<pytorch_version value="2.5.1" />
<transformers_version value="4.45.2" />
</optimum>
</rt_info>
</net>