Upload 16 files

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "tarekziade/distilvit",
   "architectures": [
     "VisionEncoderDecoderModel"
   ],
@@ -178,6 +179,5 @@
   "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 sha256:4884fbf497eeb3b9548ff95cf37062f709d24a12568903decd06438b68f83cfa
+size 385863272

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d091bfbb6bcf0e5d0be5b2cb6d94d4f4409a9f406627e203103f15dcfccdf4fa
+size 387339536

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7ac7290a551abc1ef84fe9f5fbddc92f0b255a589479b890040ba4391c3bb6
+size 99755448

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be7fe9e2aa7cbd9ad7d264c7fb5c840588d95d34efb609a304e3d17e5eb73e0
+size 98063696

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f0b91b8725dfd83b4c56561cfb8af05c3c490ec7f01176dfc65282d29d32f6
+size 385862852

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d92e6d422d6fb0270176b92ba235ba32f401f9f8d313829a960b6d921e0456e
+size 98061103

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e151662b541653ab63ea653056c6902f90d001358c831c7c6b3f02f4123480e3
+size 343440610

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dfb73885aa98a91d6bd31c24ca7902acf0517f43ae99a8fe827ad50f007df8c
+size 87038150

quantize_config.json

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