update configs (batch 1/1)
This commit is contained in:
495
tokenizer_config.json
Normal file
495
tokenizer_config.json
Normal file
@@ -0,0 +1,495 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"200000": {
|
||||
"content": "]!p~[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200001": {
|
||||
"content": "<fim_prefix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200002": {
|
||||
"content": "<fim_middle>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200003": {
|
||||
"content": "<fim_suffix>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200004": {
|
||||
"content": "<fim_pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200005": {
|
||||
"content": "<reponame>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200006": {
|
||||
"content": "<filename>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200007": {
|
||||
"content": "<gh_stars>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200008": {
|
||||
"content": "<issue_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200009": {
|
||||
"content": "<issue_comment>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200010": {
|
||||
"content": "<issue_closed>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200011": {
|
||||
"content": "<jupyter_start>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200012": {
|
||||
"content": "<jupyter_text>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200013": {
|
||||
"content": "<jupyter_code>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200014": {
|
||||
"content": "<jupyter_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200015": {
|
||||
"content": "<empty_output>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200016": {
|
||||
"content": "<commit_before>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200017": {
|
||||
"content": "<commit_msg>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200018": {
|
||||
"content": "<commit_after>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200019": {
|
||||
"content": "]~b]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200020": {
|
||||
"content": "[e~[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200021": {
|
||||
"content": "]!d~[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200022": {
|
||||
"content": "<function_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200023": {
|
||||
"content": "<code_interpreter>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200024": {
|
||||
"content": "]<]speech[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200025": {
|
||||
"content": "]<]image[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200026": {
|
||||
"content": "]<]video[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200027": {
|
||||
"content": "]<]start of speech[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200028": {
|
||||
"content": "]<]end of speech[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200029": {
|
||||
"content": "]<]start of image[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200030": {
|
||||
"content": "]<]end of image[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200031": {
|
||||
"content": "]<]start of video[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200032": {
|
||||
"content": "]<]end of video[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200033": {
|
||||
"content": "]<]vision pad[>[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200034": {
|
||||
"content": "]~!b[",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200035": {
|
||||
"content": "<jupyter_error>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200036": {
|
||||
"content": "<add_file>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200037": {
|
||||
"content": "<delete_file>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200038": {
|
||||
"content": "<rename_file>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200039": {
|
||||
"content": "<edit_file>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200040": {
|
||||
"content": "<commit_message>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200041": {
|
||||
"content": "<empty_source_file>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200042": {
|
||||
"content": "<repo_struct>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"200043": {
|
||||
"content": "<code_context>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200044": {
|
||||
"content": "<file_content>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200045": {
|
||||
"content": "<source_files>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200046": {
|
||||
"content": "<pr_start>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200047": {
|
||||
"content": "<review_comment>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200048": {
|
||||
"content": "<filepath>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200049": {
|
||||
"content": "<file_sep>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": true
|
||||
},
|
||||
"200050": {
|
||||
"content": "<think>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"200051": {
|
||||
"content": "</think>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"200052": {
|
||||
"content": "<minimax:tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
},
|
||||
"200053": {
|
||||
"content": "</minimax:tool_call>",
|
||||
"single_word": false,
|
||||
"lstrip": false,
|
||||
"rstrip": false,
|
||||
"normalized": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<code_interpreter>",
|
||||
"<commit_after>",
|
||||
"<commit_before>",
|
||||
"<commit_msg>",
|
||||
"<empty_output>",
|
||||
"<filename>",
|
||||
"<fim_middle>",
|
||||
"<fim_pad>",
|
||||
"<fim_prefix>",
|
||||
"<fim_suffix>",
|
||||
"<function_call>",
|
||||
"<gh_stars>",
|
||||
"]<]speech[>[",
|
||||
"]<]image[>[",
|
||||
"]<]video[>[",
|
||||
"]<]start of speech[>[",
|
||||
"]<]end of speech[>[",
|
||||
"]<]start of image[>[",
|
||||
"]<]end of image[>[",
|
||||
"]<]start of video[>[",
|
||||
"]<]end of video[>[",
|
||||
"]<]vision pad[>[",
|
||||
"]~!b[",
|
||||
"<issue_closed>",
|
||||
"<issue_comment>",
|
||||
"<issue_start>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<reponame>",
|
||||
"[e~[",
|
||||
"]!d~[",
|
||||
"]!p~[",
|
||||
"]~b]",
|
||||
"<jupyter_error>",
|
||||
"<add_file>",
|
||||
"<delete_file>",
|
||||
"<rename_file>",
|
||||
"<edit_file>",
|
||||
"<commit_message>",
|
||||
"<empty_source_file>",
|
||||
"<repo_struct>",
|
||||
"<code_context>",
|
||||
"<file_content>",
|
||||
"<source_files>",
|
||||
"<pr_start>",
|
||||
"<review_comment>",
|
||||
"<filepath>",
|
||||
"<file_sep>"
|
||||
],
|
||||
"add_prefix_space": false,
|
||||
"bos_token": "]~!b[",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "[e~[",
|
||||
"model_max_length": 40960000,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "]!d~["
|
||||
}
|
||||
Reference in New Issue
Block a user