Upload 3 files

special_tokens_map.json

@@ -1,20 +1,27 @@
 {
   "bos_token": {
-    "content": "<|im_start|>",
+    "content": "[BOS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "[EOS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "[BOS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<|im_start|>",
+      "content": "[EOS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,15 @@
       "special": true
     },
     "2": {
-      "content": "<|im_end|>",
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,11 +33,13 @@
       "special": true
     }
   },
-  "bos_token": "<|im_start|>",
+  "bos_token": "[BOS]",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'system' %}\n{{ bos_token }}system\n{{ message['content'] }}\n{{ eos_token }}\n{% elif message['role'] == 'user' %}\n{{ bos_token }}user\n{{ message['content'] }}\n{{ eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ bos_token }}assistant\n{{ message['content'] }}\n{{ eos_token }}\n{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ bos_token }}assistant\n{% endif %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "[EOS]",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "tokenizer_class": "PreTrainedTokenizer"
 }