Upload folder using huggingface_hub

special_tokens_map.json

@@ -1,16 +1,29 @@
 {
   "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
+    {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
   ],
   "bos_token": "<|im_start|>",
   "eos_token": "<|im_end|>",
   "pad_token": "<|im_end|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,15 +1,14 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "32000": {
+    "1": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -17,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "32001": {
+    "2": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -27,6 +26,7 @@
     }
   },
   "additional_special_tokens": [
+    "<|endoftext|>",
     "<|im_start|>",
     "<|im_end|>"
   ],
@@ -35,8 +35,8 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|im_end|>",
-  "tokenizer_class": "GPT2Tokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "unk_token": "<|endoftext|>"
 }