add chat_template

special_tokens_map.json

@@ -1 +1,30 @@
-{}
+{
+    "bos_token": {
+        "content": "<|begin_of_text|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "eos_token": {
+        "content": "<|endoftext|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "pad_token": {
+        "content": "<|padding|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    },
+    "unk_token": {
+        "content": "<|unknown|>",
+        "lstrip": false,
+        "normalized": false,
+        "rstrip": false,
+        "single_word": false
+    }
+}

tokenizer_config.json

@@ -6593,7 +6593,12 @@
       "special": true
     }
   },
+  "bos_token": "<|begin_of_text|>",
+  "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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|padding|>",
+  "unk_token": "<|unknown|>",
   "clean_up_tokenization_spaces": true,
   "model_max_length": 1000000000000000019884624838656,
   "tokenizer_class": "PreTrainedTokenizerFast"
-}
+}