初始化项目，由ModelHub XC社区提供模型

Model: NeTSlab/gpt2_parfind_en_zh_equal
Source: Original Platform

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenizer.EnhancedParadigmTokenizerWrapper",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "boundaries_discovery": true,
+  "boundary_discovery_mode": "space_free_only",
+  "boundary_min_sequence_length": 2,
+  "boundary_shorter_first": true,
+  "boundary_space_marker": "_",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "fallback_mode": "none",
+  "model_max_length": 1000000000000000019884624838656,
+  "null_suffix_token": "ε",
+  "null_suffixes_as_tokens": false,
+  "pad_token": "<pad>",
+  "paradigm_specific_roots": false,
+  "paradigm_specific_suffixes": false,
+  "paradigm_token_format": "{token}_p{paradigm_idx}",
+  "segment_cache_size": 200000,
+  "space_free_bootstrap_languages": [
+    "zho"
+  ],
+  "tokenizer_class": "EnhancedParadigmTokenizerWrapper",
+  "unk_token": "<unk>",
+  "use_word_boundaries": false,
+  "word_boundary_token": "▁"
+}