pdf

tokenizer_config.json

@@ -1,13 +1,46 @@
-
-  {
-    "pat_str": "'s|'t|'re|'ve|'m|'ll|'d| ?[\\p{L}]+| ?[\\p{N}]+| ?[^\\s\\p{L}\\p{N}]+|\\s+(?!\\S)|\\s+",
-
-    "tokenizer_class": "OBITokenizer",
-    "auto_map": {
-        "AutoTokenizer": [
-          "tokenizeConfig.OBITokenizer",
-          null
-        ]
-      },
-    "vocab_size": 600
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "token2.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
 }