Upload tokenizer

README.md

@@ -1,38 +1,37 @@
 ---
 language:
-  - en
+- en
 license: mit
 tags:
-  - finance
+- finance
 pipeline_tag: text-generation
 widget:
-  - example_title: Easy
-    text: >
-      <|user|>
-      
-      How do call options benefit the buyer?
-      
-      <|assistant|>
-
-      
-  - example_title: Medium
-    text: >
-      <|user|>
-      
-      Why might a trader choose to quickly exit a losing position, even if they still believe in the original trade idea?
-      
-      <|assistant|>
-
-      
-  - example_title: Hard
-    text: >
-      <|user|>
-      
-      In the context of Harry Markowitz's Portfolio Selection theory, what does an 'efficient' portfolio refer to?
-      
-      <|assistant|>
-
-      
+- example_title: Easy
+  text: '<|user|>
+
+    How do call options benefit the buyer?
+
+    <|assistant|>
+
+    '
+- example_title: Medium
+  text: '<|user|>
+
+    Why might a trader choose to quickly exit a losing position, even if they still
+    believe in the original trade idea?
+
+    <|assistant|>
+
+    '
+- example_title: Hard
+  text: '<|user|>
+
+    In the context of Harry Markowitz''s Portfolio Selection theory, what does an
+    ''efficient'' portfolio refer to?
+
+    <|assistant|>
+
+    '
 inference:
   parameters:
     temperature: 0.2

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

special_tokens_map.json

@@ -13,6 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -29,25 +29,33 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32000,
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    {
+      "id": 32001,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -134,6 +142,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,17 +26,36 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": false,
+  "use_fast": true
 }