Adding ONNX file of this model

README.md

@@ -2,6 +2,7 @@
 tags:
 - trocr
 - image-to-text
+- onnx
 widget:
 - src: https://fki.tic.heia-fr.ch/static/img/a01-122-02.jpg
   example_title: Note 1

onnx/config.json

@@ -0,0 +1,58 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": true,
+    "attention_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "dropout": 0.1,
+    "init_std": 0.02,
+    "is_decoder": true,
+    "layernorm_embedding": true,
+    "max_position_embeddings": 512,
+    "model_type": "trocr",
+    "scale_embedding": true,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 64044
+  },
+  "encoder": {
+    "attention_probs_dropout_prob": 0.0,
+    "encoder_stride": 16,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 384,
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-12,
+    "model_type": "deit",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "pooler_act": "tanh",
+    "pooler_output_size": 384,
+    "qkv_bias": true,
+    "torch_dtype": "float32"
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05607490320b869d46b95572cba46538817fe71ec60f981fcb8e47a4b20bd7d
+size 158834142

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6921f06c9f6a477862cab9d6e13e4089782bcf024213f95c1096ae0727163f12
+size 159079076

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc26ea989ce6ec1f26d25d79c18344a5009b4daad7bb2daba6b456d0d6d634b
+size 154052951

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbd4029d62fd1aedde53bf4ce4a5da67cf3cead6822a587fdc5ae48a5d8806c
+size 87510770

onnx/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.51.3",
+  "use_cache": false
+}

onnx/preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DeiTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}