Upload tokenizer

special_tokens_map.json

@@ -1,7 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<|none1|>"
-  ],
   "bos_token": {
     "content": "<|begin_of_text|>",
     "lstrip": false,
@@ -10,14 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -2047,30 +2047,16 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "145791": {
-      "content": "<|none1|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|none1|>"
-  ],
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\n' }}{% endif %}{% endfor %}",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|end_of_text|>",
-  "padding_side": "right",
-  "split_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast"
 }