deepseek-coder-6.7b-enhance / tokenizer_config.json
instinctguo's picture
Upload 9 files
57e73d4 verified
Raw
History Blame Contribute Delete
8.54 kB
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"32000": {
"content": "õ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32001": {
"content": "÷",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32002": {
"content": "Á",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32003": {
"content": "ý",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32004": {
"content": "À",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32005": {
"content": "ÿ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32006": {
"content": "ø",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32007": {
"content": "ú",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32008": {
"content": "þ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32009": {
"content": "ü",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32010": {
"content": "ù",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32011": {
"content": "ö",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32012": {
"content": "û",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32013": {
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32014": {
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32015": {
"content": "<|fim▁hole|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32016": {
"content": "<|fim▁begin|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32017": {
"content": "<|fim▁end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32018": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32019": {
"content": "<|User|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32020": {
"content": "<|Assistant|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32021": {
"content": "<|EOT|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32022": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32023": {
"content": "<neighbor>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32024": {
"content": "<codecontent>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32025": {
"content": "<codesketch>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32026": {
"content": "<filesketch>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32027": {
"content": "<codeblock>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32028": {
"content": "<filename>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32029": {
"content": "<repodesc>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32030": {
"content": "<reponame>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32031": {
"content": "<gh_stars>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32032": {
"content": "<issue_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32033": {
"content": "<issue_comment>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32034": {
"content": "<issue_closed>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32035": {
"content": "<jupyter_start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32036": {
"content": "<jupyter_text>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32037": {
"content": "<jupyter_code>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32038": {
"content": "<jupyter_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32039": {
"content": "<empty_output>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32040": {
"content": "<commit_before>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32041": {
"content": "<commit_msg>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32042": {
"content": "<commit_after>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<repodesc>",
"<reponame>",
"<filesketch>",
"<codesketch>",
"<filename>",
"<neighbor>",
"<codeblock>",
"<|fim▁begin|>",
"<|fim▁hole|>",
"<|fim▁end|>",
"<codecontent>",
"<|endoftext|>",
"<gh_stars>",
"<issue_start>",
"<issue_comment>",
"<issue_closed>",
"<jupyter_start>",
"<jupyter_text>",
"<jupyter_code>",
"<jupyter_output>",
"<empty_output>",
"<commit_before>",
"<commit_msg>",
"<commit_after>",
"<pad>"
],
"bos_token": "<|begin▁of▁sentence|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": true,
"model_max_length": 16384,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": null,
"use_default_system_prompt": true
}