Fix tokenizer.

I was using the wrong class.

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "/tmp/tmp9i56bvpt",
+  "_name_or_path": "./artifacts/model-16iz9xkk-1590-0.8572:v0",
   "architectures": [
-    "ReadabilityPretrainedBertin"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 d e
 Ġ e
 Ġ de

tokenizer_config.json

@@ -1 +1 @@
-{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/tmp/tmp4ksox2ly", "tokenizer_class": "ReadabilityBertinTokenizer"}
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "./artifacts/model-16iz9xkk-1590-0.8572:v0", "tokenizer_class": "RobertaTokenizer"}