Upload folder using huggingface_hub

config.json

@@ -20,7 +20,7 @@
   "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.29.2",
+  "transformers_version": "4.33.0.dev0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3610f3c12656f7ac725a5adf53a851979240d04070e32537d0de932efbe52af
+oid sha256:b89b8e23138941db4c4a2c72c119f1941f8f1f9f7ff0d813e784c6bc067d63bd
 size 1417727640

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6345d813165e8365070347ad1d483ed11e02bb0795ba6804f6cbf0f191195bb
+oid sha256:adfebe52baad33233222ff7b02c1e6621eb77136eac1e15b3cd0aa2e240ebf8e
 size 357203959

quantize_config.json

@@ -0,0 +1,36 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Pow",
+                "Cast",
+                "Div",
+                "CumSum",
+                "Not",
+                "MatMul",
+                "ConstantOfShape",
+                "Equal",
+                "Mul",
+                "Concat",
+                "Shape",
+                "ReduceMean",
+                "Sub",
+                "Sqrt",
+                "Softmax",
+                "Transpose",
+                "Unsqueeze",
+                "Gather",
+                "Expand",
+                "Reshape",
+                "Constant",
+                "Erf",
+                "Where",
+                "Add",
+                "Slice"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

tokenizer_config.json

@@ -6,10 +6,17 @@
   "eos_token": "</s>",
   "errors": "replace",
   "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "</s>",
+  "stride": 0,
   "tokenizer_class": "RobertaTokenizer",
   "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }