Upload tokenizer

README.md

@@ -1,15 +1,15 @@
 ---
+base_model:
+- MBZUAI/LaMini-GPT-774M
 library_name: transformers
+license: apache-2.0
+model_name: ChatGPT-2.V2
 tags:
 - conversational-ai
 - fine-tuning
 - gpt2
 - causal-lm
 - chatbots
-license: apache-2.0
-model_name: ChatGPT-2.V2
-base_model:
-- MBZUAI/LaMini-GPT-774M
 ---
 
 # ChatGPT-2.V2 Model Card

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|im_start|>",
+    "<|im_end|>"
   ],
   "bos_token": {
     "content": "<|endoftext|>",
@@ -29,7 +17,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -47,6 +47,6 @@
   "model_max_length": 512,
   "pad_token": "<|endoftext|>",
   "padding_side": "right",
-  "tokenizer_class": "GPT2Tokenizer",
+  "tokenizer_class": "CustomGPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }