Update tokenizer_config.json

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+ "add_bos_token": false,
+ "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
  "0": {
@@ -10,150 +12,206 @@
  "special": true
  },
  "1": {
- "content": "<fim_prefix>",
+ "content": "<|padding|>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "2": {
- "content": "<fim_middle>",
+ "50254": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "3": {
- "content": "<fim_suffix>",
+ "50255": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "4": {
- "content": "<fim_pad>",
+ "50256": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "5": {
- "content": "<filename>",
+ "50257": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "6": {
- "content": "<gh_stars>",
+ "50258": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "7": {
- "content": "<issue_start>",
+ "50259": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "8": {
- "content": "<issue_comment>",
+ "50260": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "9": {
- "content": "<issue_closed>",
+ "50261": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "10": {
- "content": "<jupyter_start>",
+ "50262": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "11": {
- "content": "<jupyter_text>",
+ "50263": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "12": {
- "content": "<jupyter_code>",
+ "50264": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "13": {
- "content": "<jupyter_output>",
+ "50265": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "14": {
- "content": "<empty_output>",
+ "50266": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "15": {
- "content": "<commit_before>",
+ "50267": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "16": {
- "content": "<commit_msg>",
+ "50268": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "17": {
- "content": "<commit_after>",
+ "50269": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "18": {
- "content": "<reponame>",
+ "50270": {
+ "content": " ",
  "lstrip": false,
- "normalized": false,
+ "normalized": true,
  "rstrip": false,
  "single_word": false,
- "special": true
+ "special": false
  },
- "49152": {
+ "50271": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50272": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50273": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50274": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50275": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50276": {
+ "content": " ",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50277": {
+ "content": "<|pad|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "50278": {
  "content": "<|im_start|>",
  "lstrip": false,
  "normalized": false,
@@ -161,28 +219,35 @@
  "single_word": false,
  "special": true
  },
- "49153": {
+ "50279": {
  "content": "<|im_end|>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
+ },
+ "50280": {
+ "content": "[PAD]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
  }
  },
  "additional_special_tokens": [
  "<|im_start|>",
  "<|im_end|>"
  ],
- "bos_token": "<|endoftext|>",
+ "bos_token": "<|im_start|>",
  "chat_template": "{% 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": true,
- "eos_token": "<|endoftext|>",
- "model_max_length": 9223372036854775807,
- "pad_token": "<|endoftext|>",
- "padding_side": "left",
- "tokenizer_class": "GPT2Tokenizer",
- "unk_token": "<|endoftext|>",
+ "eos_token": "<|im_end|>",
+ "model_max_length": 1000000000000000019884624838656,
+ "pad_token": "<|im_end|>",
+ "tokenizer_class": "GPTNeoXTokenizer",
+ "unk_token": "<|endoftext|>"
  "vocab_size": 49152
 }