Upload tokenizer

README.md

@@ -1,11 +1,11 @@
 ---
+library_name: transformers
 pipeline_tag: text-generation
 inference: true
 widget:
-- text: 'Hello!'
+- text: Hello!
   example_title: Hello world
   group: Python
-library_name: transformers
 ---
 
 This model is randomly initialized, using the config from [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) but with smaller size. 

tokenizer.json

@@ -26,9 +26,9 @@
       "content": "</s>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
-      "special": true
+      "special": false
     },
     {
       "id": 32000,
@@ -44,7 +44,7 @@
       "content": "<|assistant|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -53,7 +53,7 @@
       "content": "<|placeholder1|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -62,7 +62,7 @@
       "content": "<|placeholder2|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -71,7 +71,7 @@
       "content": "<|placeholder3|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -80,7 +80,7 @@
       "content": "<|placeholder4|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -89,7 +89,7 @@
       "content": "<|system|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -98,7 +98,7 @@
       "content": "<|end|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -107,7 +107,7 @@
       "content": "<|placeholder5|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -116,7 +116,7 @@
       "content": "<|placeholder6|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     },
@@ -125,7 +125,7 @@
       "content": "<|user|>",
       "single_word": false,
       "lstrip": false,
-      "rstrip": false,
+      "rstrip": true,
       "normalized": false,
       "special": true
     }

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -22,9 +23,9 @@
       "content": "</s>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "32000": {
       "content": "<|endoftext|>",
@@ -38,7 +39,7 @@
       "content": "<|assistant|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -46,7 +47,7 @@
       "content": "<|placeholder1|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -54,7 +55,7 @@
       "content": "<|placeholder2|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -62,7 +63,7 @@
       "content": "<|placeholder3|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -70,7 +71,7 @@
       "content": "<|placeholder4|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -78,7 +79,7 @@
       "content": "<|system|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -86,7 +87,7 @@
       "content": "<|end|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -94,7 +95,7 @@
       "content": "<|placeholder5|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -102,7 +103,7 @@
       "content": "<|placeholder6|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     },
@@ -110,13 +111,13 @@
       "content": "<|user|>",
       "lstrip": false,
       "normalized": false,
-      "rstrip": false,
+      "rstrip": true,
       "single_word": false,
       "special": true
     }
   },
   "bos_token": "<s>",
-  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|system|>' + '\n' + message['content'] + '<|end|>' + '\n'}}{% elif (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif message['role'] == 'assistant' %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,