Training update v1.2 - 3/13 datasets completed

special_tokens_map.json

@@ -1,34 +1,4 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|human|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|context|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -6,16 +6,7 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": {
-    "strategy": {
-      "Fixed": 256
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50256,
-    "pad_type_id": 0,
-    "pad_token": "<|endoftext|>"
-  },
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,
@@ -25,42 +16,6 @@
       "rstrip": false,
       "normalized": true,
       "special": true
-    },
-    {
-      "id": 50257,
-      "content": "<|human|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50258,
-      "content": "<|assistant|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50259,
-      "content": "<|system|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 50260,
-      "content": "<|context|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -9,46 +9,8 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "50257": {
-      "content": "<|human|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50258": {
-      "content": "<|assistant|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50259": {
-      "content": "<|system|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50260": {
-      "content": "<|context|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|human|>",
-    "<|assistant|>",
-    "<|system|>",
-    "<|context|>"
-  ],
   "bos_token": "<|endoftext|>",
   "chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
   "clean_up_tokenization_spaces": true,