adalbertojunior
commited on
Upload 7 files
Browse files- merges.txt +2 -126
- model.safetensors +1 -1
- special_tokens_map.json +3 -9
- tokenizer.json +0 -0
- tokenizer_config.json +3 -3
- vocab.json +0 -0
merges.txt
CHANGED
@@ -32107,7 +32107,6 @@ intui tivo</w>
|
|
32107 |
piet ro</w>
|
32108 |
ra lo</w>
|
32109 |
vi da
|
32110 |
-
à ¯
|
32111 |
ei de</w>
|
32112 |
com est
|
32113 |
ex óticas</w>
|
@@ -32117,6 +32116,7 @@ quei mando</w>
|
|
32117 |
cór tex</w>
|
32118 |
messen ger</w>
|
32119 |
ny lon</w>
|
|
|
32120 |
redu zi
|
32121 |
condu zia</w>
|
32122 |
bre a
|
@@ -39034,8 +39034,8 @@ exces sivos</w>
|
|
39034 |
multipli cam</w>
|
39035 |
enfei te</w>
|
39036 |
rotul agem</w>
|
39037 |
-
v v</w>
|
39038 |
v g</w>
|
|
|
39039 |
prim em</w>
|
39040 |
permi ssion
|
39041 |
psi como
|
@@ -48893,127 +48893,3 @@ conten da</w>
|
|
48893 |
kasper sky</w>
|
48894 |
u tentes</w>
|
48895 |
in pa</w>
|
48896 |
-
gu ang
|
48897 |
-
inter setorial</w>
|
48898 |
-
fei tura</w>
|
48899 |
-
che v</w>
|
48900 |
-
ini qui
|
48901 |
-
mor ta
|
48902 |
-
justi fiquem</w>
|
48903 |
-
super la
|
48904 |
-
có n</w>
|
48905 |
-
eta gem</w>
|
48906 |
-
bur gh</w>
|
48907 |
-
ast úcia</w>
|
48908 |
-
bul bo</w>
|
48909 |
-
gl y
|
48910 |
-
ze bu</w>
|
48911 |
-
exager adamente</w>
|
48912 |
-
enter al</w>
|
48913 |
-
londr ino</w>
|
48914 |
-
aná logos</w>
|
48915 |
-
irlan deses</w>
|
48916 |
-
objetiv am</w>
|
48917 |
-
arac ruz</w>
|
48918 |
-
antagon ismo</w>
|
48919 |
-
delu xe</w>
|
48920 |
-
u ab</w>
|
48921 |
-
vi gésima</w>
|
48922 |
-
ó fo
|
48923 |
-
sa ad</w>
|
48924 |
-
le p
|
48925 |
-
jo garem</w>
|
48926 |
-
popul oso</w>
|
48927 |
-
... :</w>
|
48928 |
-
bei rute</w>
|
48929 |
-
descre va</w>
|
48930 |
-
gem er</w>
|
48931 |
-
sop rar</w>
|
48932 |
-
arac y</w>
|
48933 |
-
gros jean</w>
|
48934 |
-
crustá ceos</w>
|
48935 |
-
tolent ino</w>
|
48936 |
-
re gen
|
48937 |
-
fes o</w>
|
48938 |
-
investi rá</w>
|
48939 |
-
ale k
|
48940 |
-
só is</w>
|
48941 |
-
hon estas</w>
|
48942 |
-
afe taram</w>
|
48943 |
-
sai bro</w>
|
48944 |
-
escu deria</w>
|
48945 |
-
confun didos</w>
|
48946 |
-
gla s
|
48947 |
-
mm mm</w>
|
48948 |
-
despe jar</w>
|
48949 |
-
corti có
|
48950 |
-
crian cinhas</w>
|
48951 |
-
bani mento</w>
|
48952 |
-
repudi ar</w>
|
48953 |
-
c zar</w>
|
48954 |
-
pi d</w>
|
48955 |
-
pon tinha</w>
|
48956 |
-
pol ónia</w>
|
48957 |
-
sobre põe</w>
|
48958 |
-
sh au
|
48959 |
-
desast rosas</w>
|
48960 |
-
acentu ou</w>
|
48961 |
-
examin e</w>
|
48962 |
-
° )</w>
|
48963 |
-
male ta</w>
|
48964 |
-
escalon amento</w>
|
48965 |
-
barna bé</w>
|
48966 |
-
ctn bio</w>
|
48967 |
-
ar busto</w>
|
48968 |
-
in sensibilidade</w>
|
48969 |
-
re tes</w>
|
48970 |
-
ti rados</w>
|
48971 |
-
se ju
|
48972 |
-
ex ul
|
48973 |
-
des atenção</w>
|
48974 |
-
ru ssel</w>
|
48975 |
-
ba tidos</w>
|
48976 |
-
ce us</w>
|
48977 |
-
bu gre</w>
|
48978 |
-
deci r</w>
|
48979 |
-
orden adas</w>
|
48980 |
-
dro p
|
48981 |
-
prefer imos</w>
|
48982 |
-
conhec esse</w>
|
48983 |
-
igual a</w>
|
48984 |
-
shi va</w>
|
48985 |
-
esca darias</w>
|
48986 |
-
despre zando</w>
|
48987 |
-
itiner ários</w>
|
48988 |
-
carcer agem</w>
|
48989 |
-
polin ização</w>
|
48990 |
-
tendenci osa</w>
|
48991 |
-
pomp eia</w>
|
48992 |
-
camil le</w>
|
48993 |
-
sangüÃŃ nea</w>
|
48994 |
-
diale to</w>
|
48995 |
-
vi tinho</w>
|
48996 |
-
gu id
|
48997 |
-
lo gs</w>
|
48998 |
-
her bá
|
48999 |
-
inteli gÃŃvel</w>
|
49000 |
-
igual zinho</w>
|
49001 |
-
diant eiras</w>
|
49002 |
-
afo gados</w>
|
49003 |
-
bian co</w>
|
49004 |
-
ey es</w>
|
49005 |
-
panturri lha</w>
|
49006 |
-
s cru
|
49007 |
-
ri ck
|
49008 |
-
ca ts</w>
|
49009 |
-
gi b
|
49010 |
-
pes cados</w>
|
49011 |
-
dis mos</w>
|
49012 |
-
mes quitas</w>
|
49013 |
-
esti losa</w>
|
49014 |
-
cal i</w>
|
49015 |
-
conser tos</w>
|
49016 |
-
exibi rá</w>
|
49017 |
-
semi condutores</w>
|
49018 |
-
vu itton</w>
|
49019 |
-
won der</w>
|
|
|
32107 |
piet ro</w>
|
32108 |
ra lo</w>
|
32109 |
vi da
|
|
|
32110 |
ei de</w>
|
32111 |
com est
|
32112 |
ex óticas</w>
|
|
|
32116 |
cór tex</w>
|
32117 |
messen ger</w>
|
32118 |
ny lon</w>
|
32119 |
+
à ¯
|
32120 |
redu zi
|
32121 |
condu zia</w>
|
32122 |
bre a
|
|
|
39034 |
multipli cam</w>
|
39035 |
enfei te</w>
|
39036 |
rotul agem</w>
|
|
|
39037 |
v g</w>
|
39038 |
+
v v</w>
|
39039 |
prim em</w>
|
39040 |
permi ssion
|
39041 |
psi como
|
|
|
48893 |
kasper sky</w>
|
48894 |
u tentes</w>
|
48895 |
in pa</w>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1710537716
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28fcc6e28da3bda5d6898c65e8348ddd75b382dd315b9a31717a980da428271e
|
3 |
size 1710537716
|
special_tokens_map.json
CHANGED
@@ -9,21 +9,15 @@
|
|
9 |
"eos_token": {
|
10 |
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": {
|
17 |
-
"content": "<|endoftext|>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
|
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
26 |
-
"normalized":
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
}
|
|
|
9 |
"eos_token": {
|
10 |
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
+
"normalized": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
"content": "<|startoftext|>",
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
@@ -9,10 +9,10 @@
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
"content": "<|endoftext|>",
|
14 |
"lstrip": false,
|
15 |
-
"normalized":
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
"content": "<|startoftext|>",
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"49407": {
|
13 |
"content": "<|endoftext|>",
|
14 |
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|