Add ONNX export for CPU inference (no GPU required)

model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f331acf700f8f29c6ba42939c6ba842694b5a5e02a5f3e9592e971c7d08d934
-size 929547
+oid sha256:8bc44e4d2a3e8f2117a5754ee081634630fa549bf4fce5a28c424636978fe064
+size 331055014

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -1,24 +1,24 @@
-{
-  "add_prefix_space": false,
-  "backend": "tokenizers",
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "is_local": false,
-  "mask_token": "<mask>",
-  "max_length": 512,
-  "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>"
-}
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "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>"
+}