Upload tokenizer

README.md

@@ -1,7 +1,7 @@
 ---
-license: apache-2.0
-language:
-- en
 datasets:
 - Locutusque/UltraTextbooks
----
+language:
+- en
+license: apache-2.0
+---

special_tokens_map.json

@@ -1,4 +1,8 @@
 {
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
   "bos_token": {
     "content": "<|bos|>",
     "lstrip": false,
@@ -13,7 +17,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

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>",
@@ -67,14 +68,18 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
   "bos_token": "<|bos|>",
+  "chat_template": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}{%- else -%}{{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'<|im_start|>assistant\n'-}}{%- endif -%}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": true,
   "max_length": 1536,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "stride": 0,