Upload 16 files

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "tarekziade/deit-tiny-distilgpt2",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -2173,6 +2174,5 @@
   "model_type": "vision-encoder-decoder",
   "pad_token_id": 50256,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.36.2"
 }

generation_config.json

@@ -1,5 +1,5 @@
 {
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.36.2"
 }

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95230cea497effc8eb407b0e190bc39e9799b40048b63d6ac16ec846b0eb9be7
+size 386451960

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf356550b2794843a8cbc5e279b36676d025b63b95a483542c79d6256925ac8
+size 387928537

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd9c0ea213be12610b06cb3304c20bdd60cd8f0b2ec06c695d2dd9b72ee126c
+size 99900479

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f6daab7f2de1096ba6af627903c9b022ccfb846fbdf55a334974e5e204eb18
+size 98207533

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63e1745e472b6121f01bffbbebc0e59e7149635a8e262aa7420dbe2bb1bfc50
+size 386456075

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0153902ef06d3afe269072efb68b87562cb39062f1816af5bcb2a4f63653c79
+size 98213050

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7f4928b69e0b198701b2924a8233be2da9cdb9c1cd548a33070103e8e67a56
+size 22346734

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0440b5a907b9d65f5a87340ff19e0f79945c3c0b216a638b99f2cb6bf27e2f48
+size 6150834

quantize_config.json

@@ -0,0 +1,125 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_with_past_model": {
+            "op_types": [
+                "Sqrt",
+                "Tanh",
+                "Slice",
+                "Pow",
+                "Div",
+                "Range",
+                "ConstantOfShape",
+                "Split",
+                "Unsqueeze",
+                "Sub",
+                "Add",
+                "Softmax",
+                "Where",
+                "Shape",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Gemm",
+                "Cast",
+                "Reshape",
+                "Mul",
+                "Gather",
+                "Squeeze",
+                "Constant",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model": {
+            "op_types": [
+                "Sqrt",
+                "Tanh",
+                "Slice",
+                "Pow",
+                "Div",
+                "Range",
+                "ConstantOfShape",
+                "Split",
+                "Unsqueeze",
+                "Sub",
+                "Add",
+                "Softmax",
+                "Where",
+                "Shape",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Gemm",
+                "Cast",
+                "Reshape",
+                "Mul",
+                "Gather",
+                "Squeeze",
+                "Constant",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Sqrt",
+                "Slice",
+                "Pow",
+                "Div",
+                "ConstantOfShape",
+                "Unsqueeze",
+                "Conv",
+                "Sub",
+                "Erf",
+                "Add",
+                "Softmax",
+                "Where",
+                "Expand",
+                "Shape",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Equal",
+                "Reshape",
+                "Mul",
+                "Gather",
+                "Constant",
+                "MatMul"
+            ],
+            "weight_type": "QUInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Sqrt",
+                "Tanh",
+                "Slice",
+                "If",
+                "Pow",
+                "Div",
+                "Range",
+                "ConstantOfShape",
+                "Split",
+                "Unsqueeze",
+                "Sub",
+                "Add",
+                "Softmax",
+                "Where",
+                "Shape",
+                "ReduceMean",
+                "Concat",
+                "Transpose",
+                "Gemm",
+                "Cast",
+                "Reshape",
+                "Mul",
+                "Gather",
+                "Squeeze",
+                "Constant",
+                "MatMul"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }