shahrukhx01 commited on
Commit
d5ec9d7
1 Parent(s): 9a7cef3
Files changed (5) hide show
  1. added_tokens.json +1 -1
  2. merges.txt +1 -1
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -1
  5. vocab.json +0 -0
added_tokens.json CHANGED
@@ -1 +1 @@
1
- {"<col0>": 50265, "<col1>": 50266, "<col2>": 50267, "<col3>": 50268, "<col4>": 50269, "<col5>": 50270, "<col6>": 50271, "<col7>": 50272, "<col8>": 50273, "<col9>": 50274, "<col10>": 50275, "<col11>": 50276, "<col12>": 50277, "<col13>": 50278, "<col14>": 50279, "<col15>": 50280, "<col16>": 50281, "<col17>": 50282, "<col18>": 50283, "<col19>": 50284, "<col20>": 50285, "<col21>": 50286, "<col22>": 50287, "<col23>": 50288, "<col24>": 50289, "<col25>": 50290, "<col26>": 50291, "<col27>": 50292, "<col28>": 50293, "<col29>": 50294, "<col30>": 50295, "<col31>": 50296, "<col32>": 50297, "<col33>": 50298, "<col34>": 50299, "<col35>": 50300, "<col36>": 50301, "<col37>": 50302, "<col38>": 50303, "<col39>": 50304, "<col40>": 50305, "<col41>": 50306, "<col42>": 50307, "<col43>": 50308, "<col44>": 50309, "<col45>": 50310, "<col46>": 50311, "<col47>": 50312, "<col48>": 50313, "<col49>": 50314}
1
+ {"<col31>": 50296, "<col15>": 50280, "<col18>": 50283, "<col5>": 50270, "<col12>": 50277, "<col43>": 50308, "<col20>": 50285, "<col36>": 50301, "<col16>": 50281, "<col13>": 50278, "<col38>": 50303, "<col9>": 50274, "<col22>": 50287, "<col7>": 50272, "<col1>": 50266, "<col49>": 50314, "<col0>": 50265, "<col17>": 50282, "<col47>": 50312, "<col33>": 50298, "<col2>": 50267, "<col30>": 50295, "<col6>": 50271, "<col45>": 50310, "<col46>": 50311, "<col42>": 50307, "<col11>": 50276, "<col23>": 50288, "<col14>": 50279, "<col3>": 50268, "<col21>": 50286, "<col8>": 50273, "<col39>": 50304, "<col29>": 50294, "<col32>": 50297, "<col4>": 50269, "<col26>": 50291, "<col25>": 50290, "<col24>": 50289, "<col41>": 50306, "<col40>": 50305, "<col48>": 50313, "<col35>": 50300, "<col37>": 50302, "<col27>": 50292, "<col28>": 50293, "<col10>": 50275, "<col19>": 50284, "<col34>": 50299, "<col44>": 50309}
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
1
+ #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "shahrukhx01/schema-aware-distilbart-cnn-12-6-text2sql", "tokenizer_file": "/Users/shahrukh/.cache/huggingface/transformers/04c4991cf0d39e038776a3f57634d2dd9fc72289dae48c51229014f0f7d032c1.0b0c42fc1dbbc023deffc35b933fb8ce65d28743308eee3cdab63f88c4596fc1"}
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./output/model_2"}
vocab.json CHANGED
The diff for this file is too large to render. See raw diff