working

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "pszemraj_nougat-small-onnx",
+  "_name_or_path": "onnx-nougat-small-opset17",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -184,6 +184,6 @@
   "is_encoder_decoder": true,
   "model_type": "vision-encoder-decoder",
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.2"
+  "transformers_version": "4.38.1",
+  "use_cache": true
 }

decoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9027a5e08a9ef8cb2ebdf04f14ef8b9241fc6715c63d156615c1980363974dfc
-size 174355235
+oid sha256:a8e53e78f218278375c6e39f3bdd3c40d19ca6790a2015c670998fc275840ff7
+size 174345955

decoder_with_past_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b668105a2f2d5facef05a793d80d35528d65333cd3cdf5337f6b57b94db7fc9
-size 165841896
+oid sha256:07fcc7dba6cf8cc6c7c10601017a36ae314f87c79389b8141fb1f56f7f0e1b49
+size 165825900

encoder_model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146f59fc8b8e5d66cf6b90504136af85cf35216a7bb56189fdc1e0fa9cd1b6da
-size 81972840
+oid sha256:6bec906871770afe111f0f3474bd5cb143cfd7f659c242431ee5431be580684d
+size 82052587

ort_config.json

@@ -2,7 +2,7 @@
   "one_external_file": true,
   "opset": null,
   "optimization": {},
-  "optimum_version": "1.17.1",
+  "optimum_version": "1.18.0.dev0",
   "quantization": {
     "activations_dtype": "QUInt8",
     "activations_symmetric": false,
@@ -30,6 +30,6 @@
     "weights_dtype": "QInt8",
     "weights_symmetric": true
   },
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.38.1",
   "use_external_data_format": false
 }