danielhanchen
commited on
Commit
•
c794dac
1
Parent(s):
ff28d1e
Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +256 -0
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
|
3 |
+
size 17525357
|
tokenizer_config.json
CHANGED
@@ -1737,6 +1737,262 @@
|
|
1737 |
"rstrip": false,
|
1738 |
"single_word": false,
|
1739 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1740 |
}
|
1741 |
},
|
1742 |
"additional_special_tokens": [
|
|
|
1737 |
"rstrip": false,
|
1738 |
"single_word": false,
|
1739 |
"special": false
|
1740 |
+
},
|
1741 |
+
"255968": {
|
1742 |
+
"content": "[toxicity=0]",
|
1743 |
+
"lstrip": false,
|
1744 |
+
"normalized": false,
|
1745 |
+
"rstrip": false,
|
1746 |
+
"single_word": false,
|
1747 |
+
"special": false
|
1748 |
+
},
|
1749 |
+
"255969": {
|
1750 |
+
"content": "\t\t",
|
1751 |
+
"lstrip": false,
|
1752 |
+
"normalized": false,
|
1753 |
+
"rstrip": false,
|
1754 |
+
"single_word": false,
|
1755 |
+
"special": false
|
1756 |
+
},
|
1757 |
+
"255970": {
|
1758 |
+
"content": "\t\t\t",
|
1759 |
+
"lstrip": false,
|
1760 |
+
"normalized": false,
|
1761 |
+
"rstrip": false,
|
1762 |
+
"single_word": false,
|
1763 |
+
"special": false
|
1764 |
+
},
|
1765 |
+
"255971": {
|
1766 |
+
"content": "\t\t\t\t",
|
1767 |
+
"lstrip": false,
|
1768 |
+
"normalized": false,
|
1769 |
+
"rstrip": false,
|
1770 |
+
"single_word": false,
|
1771 |
+
"special": false
|
1772 |
+
},
|
1773 |
+
"255972": {
|
1774 |
+
"content": "\t\t\t\t\t",
|
1775 |
+
"lstrip": false,
|
1776 |
+
"normalized": false,
|
1777 |
+
"rstrip": false,
|
1778 |
+
"single_word": false,
|
1779 |
+
"special": false
|
1780 |
+
},
|
1781 |
+
"255973": {
|
1782 |
+
"content": "\t\t\t\t\t\t",
|
1783 |
+
"lstrip": false,
|
1784 |
+
"normalized": false,
|
1785 |
+
"rstrip": false,
|
1786 |
+
"single_word": false,
|
1787 |
+
"special": false
|
1788 |
+
},
|
1789 |
+
"255974": {
|
1790 |
+
"content": "\t\t\t\t\t\t\t",
|
1791 |
+
"lstrip": false,
|
1792 |
+
"normalized": false,
|
1793 |
+
"rstrip": false,
|
1794 |
+
"single_word": false,
|
1795 |
+
"special": false
|
1796 |
+
},
|
1797 |
+
"255975": {
|
1798 |
+
"content": "\t\t\t\t\t\t\t\t",
|
1799 |
+
"lstrip": false,
|
1800 |
+
"normalized": false,
|
1801 |
+
"rstrip": false,
|
1802 |
+
"single_word": false,
|
1803 |
+
"special": false
|
1804 |
+
},
|
1805 |
+
"255976": {
|
1806 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
1807 |
+
"lstrip": false,
|
1808 |
+
"normalized": false,
|
1809 |
+
"rstrip": false,
|
1810 |
+
"single_word": false,
|
1811 |
+
"special": false
|
1812 |
+
},
|
1813 |
+
"255977": {
|
1814 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
1815 |
+
"lstrip": false,
|
1816 |
+
"normalized": false,
|
1817 |
+
"rstrip": false,
|
1818 |
+
"single_word": false,
|
1819 |
+
"special": false
|
1820 |
+
},
|
1821 |
+
"255978": {
|
1822 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
1823 |
+
"lstrip": false,
|
1824 |
+
"normalized": false,
|
1825 |
+
"rstrip": false,
|
1826 |
+
"single_word": false,
|
1827 |
+
"special": false
|
1828 |
+
},
|
1829 |
+
"255979": {
|
1830 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
1831 |
+
"lstrip": false,
|
1832 |
+
"normalized": false,
|
1833 |
+
"rstrip": false,
|
1834 |
+
"single_word": false,
|
1835 |
+
"special": false
|
1836 |
+
},
|
1837 |
+
"255980": {
|
1838 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1839 |
+
"lstrip": false,
|
1840 |
+
"normalized": false,
|
1841 |
+
"rstrip": false,
|
1842 |
+
"single_word": false,
|
1843 |
+
"special": false
|
1844 |
+
},
|
1845 |
+
"255981": {
|
1846 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1847 |
+
"lstrip": false,
|
1848 |
+
"normalized": false,
|
1849 |
+
"rstrip": false,
|
1850 |
+
"single_word": false,
|
1851 |
+
"special": false
|
1852 |
+
},
|
1853 |
+
"255982": {
|
1854 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1855 |
+
"lstrip": false,
|
1856 |
+
"normalized": false,
|
1857 |
+
"rstrip": false,
|
1858 |
+
"single_word": false,
|
1859 |
+
"special": false
|
1860 |
+
},
|
1861 |
+
"255983": {
|
1862 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1863 |
+
"lstrip": false,
|
1864 |
+
"normalized": false,
|
1865 |
+
"rstrip": false,
|
1866 |
+
"single_word": false,
|
1867 |
+
"special": false
|
1868 |
+
},
|
1869 |
+
"255984": {
|
1870 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1871 |
+
"lstrip": false,
|
1872 |
+
"normalized": false,
|
1873 |
+
"rstrip": false,
|
1874 |
+
"single_word": false,
|
1875 |
+
"special": false
|
1876 |
+
},
|
1877 |
+
"255985": {
|
1878 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1879 |
+
"lstrip": false,
|
1880 |
+
"normalized": false,
|
1881 |
+
"rstrip": false,
|
1882 |
+
"single_word": false,
|
1883 |
+
"special": false
|
1884 |
+
},
|
1885 |
+
"255986": {
|
1886 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1887 |
+
"lstrip": false,
|
1888 |
+
"normalized": false,
|
1889 |
+
"rstrip": false,
|
1890 |
+
"single_word": false,
|
1891 |
+
"special": false
|
1892 |
+
},
|
1893 |
+
"255987": {
|
1894 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1895 |
+
"lstrip": false,
|
1896 |
+
"normalized": false,
|
1897 |
+
"rstrip": false,
|
1898 |
+
"single_word": false,
|
1899 |
+
"special": false
|
1900 |
+
},
|
1901 |
+
"255988": {
|
1902 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1903 |
+
"lstrip": false,
|
1904 |
+
"normalized": false,
|
1905 |
+
"rstrip": false,
|
1906 |
+
"single_word": false,
|
1907 |
+
"special": false
|
1908 |
+
},
|
1909 |
+
"255989": {
|
1910 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1911 |
+
"lstrip": false,
|
1912 |
+
"normalized": false,
|
1913 |
+
"rstrip": false,
|
1914 |
+
"single_word": false,
|
1915 |
+
"special": false
|
1916 |
+
},
|
1917 |
+
"255990": {
|
1918 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1919 |
+
"lstrip": false,
|
1920 |
+
"normalized": false,
|
1921 |
+
"rstrip": false,
|
1922 |
+
"single_word": false,
|
1923 |
+
"special": false
|
1924 |
+
},
|
1925 |
+
"255991": {
|
1926 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1927 |
+
"lstrip": false,
|
1928 |
+
"normalized": false,
|
1929 |
+
"rstrip": false,
|
1930 |
+
"single_word": false,
|
1931 |
+
"special": false
|
1932 |
+
},
|
1933 |
+
"255992": {
|
1934 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1935 |
+
"lstrip": false,
|
1936 |
+
"normalized": false,
|
1937 |
+
"rstrip": false,
|
1938 |
+
"single_word": false,
|
1939 |
+
"special": false
|
1940 |
+
},
|
1941 |
+
"255993": {
|
1942 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1943 |
+
"lstrip": false,
|
1944 |
+
"normalized": false,
|
1945 |
+
"rstrip": false,
|
1946 |
+
"single_word": false,
|
1947 |
+
"special": false
|
1948 |
+
},
|
1949 |
+
"255994": {
|
1950 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1951 |
+
"lstrip": false,
|
1952 |
+
"normalized": false,
|
1953 |
+
"rstrip": false,
|
1954 |
+
"single_word": false,
|
1955 |
+
"special": false
|
1956 |
+
},
|
1957 |
+
"255995": {
|
1958 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1959 |
+
"lstrip": false,
|
1960 |
+
"normalized": false,
|
1961 |
+
"rstrip": false,
|
1962 |
+
"single_word": false,
|
1963 |
+
"special": false
|
1964 |
+
},
|
1965 |
+
"255996": {
|
1966 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1967 |
+
"lstrip": false,
|
1968 |
+
"normalized": false,
|
1969 |
+
"rstrip": false,
|
1970 |
+
"single_word": false,
|
1971 |
+
"special": false
|
1972 |
+
},
|
1973 |
+
"255997": {
|
1974 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1975 |
+
"lstrip": false,
|
1976 |
+
"normalized": false,
|
1977 |
+
"rstrip": false,
|
1978 |
+
"single_word": false,
|
1979 |
+
"special": false
|
1980 |
+
},
|
1981 |
+
"255998": {
|
1982 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
1983 |
+
"lstrip": false,
|
1984 |
+
"normalized": false,
|
1985 |
+
"rstrip": false,
|
1986 |
+
"single_word": false,
|
1987 |
+
"special": false
|
1988 |
+
},
|
1989 |
+
"255999": {
|
1990 |
+
"content": "<unused99>",
|
1991 |
+
"lstrip": false,
|
1992 |
+
"normalized": false,
|
1993 |
+
"rstrip": false,
|
1994 |
+
"single_word": false,
|
1995 |
+
"special": false
|
1996 |
}
|
1997 |
},
|
1998 |
"additional_special_tokens": [
|