Upload tokenizer_config.json

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
- "add_bos_token": false,
- "add_eos_token": false,
  "add_prefix_space": false,
  "added_tokens_decoder": {
  "0": {
@@ -12,223 +10,159 @@
  "special": true
  },
  "1": {
- "content": "<|padding|>",
+ "content": "<fim_prefix>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "50254": {
- "content": " ",
+ "2": {
+ "content": "<fim_middle>",
  "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50255": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50256": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50257": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50258": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50259": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50260": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50261": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
- "rstrip": false,
- "single_word": false,
- "special": false
- },
- "50262": {
- "content": " ",
- "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50263": {
- "content": " ",
+ "3": {
+ "content": "<fim_suffix>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50264": {
- "content": " ",
+ "4": {
+ "content": "<fim_pad>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50265": {
- "content": " ",
+ "5": {
+ "content": "<filename>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50266": {
- "content": " ",
+ "6": {
+ "content": "<gh_stars>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50267": {
- "content": " ",
+ "7": {
+ "content": "<issue_start>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50268": {
- "content": " ",
+ "8": {
+ "content": "<issue_comment>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50269": {
- "content": " ",
+ "9": {
+ "content": "<issue_closed>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50270": {
- "content": " ",
+ "10": {
+ "content": "<jupyter_start>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50271": {
- "content": " ",
+ "11": {
+ "content": "<jupyter_text>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50272": {
- "content": " ",
+ "12": {
+ "content": "<jupyter_code>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50273": {
- "content": " ",
+ "13": {
+ "content": "<jupyter_output>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50274": {
- "content": " ",
+ "14": {
+ "content": "<empty_output>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50275": {
- "content": " ",
+ "15": {
+ "content": "<commit_before>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50276": {
- "content": " ",
+ "16": {
+ "content": "<commit_msg>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50277": {
- "content": "<|pad|>",
+ "17": {
+ "content": "<commit_after>",
  "lstrip": false,
- "normalized": true,
+ "normalized": false,
  "rstrip": false,
  "single_word": false,
- "special": false
+ "special": true
  },
- "50278": {
- "content": "<|im_start|>",
+ "18": {
+ "content": "<reponame>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "50279": {
- "content": "<|im_end|>",
+ "49152": {
+ "content": "<|im_start|>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
  "single_word": false,
  "special": true
  },
- "50280": {
- "content": "[PAD]",
+ "49153": {
+ "content": "<|im_end|>",
  "lstrip": false,
  "normalized": false,
  "rstrip": false,
@@ -240,13 +174,14 @@
  "<|im_start|>",
  "<|im_end|>"
  ],
- "bos_token": "<|im_start|>",
+ "bos_token": "<|endoftext|>",
  "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": "<|im_end|>",
- "model_max_length": 1000000000000000019884624838656,
- "pad_token": "<|im_end|>",
- "tokenizer_class": "GPTNeoXTokenizer",
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 9223372036854775807,
+ "pad_token": "<|endoftext|>",
+ "padding_side": "left",
+ "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>",
  "vocab_size": 49152
 }