Upload tokenizer

chat_template.jinja

@@ -0,0 +1,16 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+<|im_start|>user
+{{ message['content'] }}<|im_end|>
+{% elif message['role'] == 'system' %}
+<|im_start|>system
+{{ message['content'] }}<|im_end|>
+{% elif message['role'] == 'assistant' %}
+<|im_start|>assistant
+{% generation %}{{ message['content'] }}<|im_end|>{% endgeneration %}
+{% endif %}
+{% endfor %}
+{% if  add_generation_prompt %}
+<|im_start|>assistant
+
+{% endif %}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}