Training in progress, step 2400
Browse files- added_tokens.json +18 -15
- config.json +1 -1
- model.safetensors +2 -2
- special_tokens_map.json +20 -0
- tokenizer_config.json +164 -0
- training_args.bin +1 -1
- vocab.json +1 -1
added_tokens.json
CHANGED
@@ -1,17 +1,20 @@
|
|
1 |
{
|
2 |
-
"<1>":
|
3 |
-
"<2>":
|
4 |
-
"<3>":
|
5 |
-
"<
|
6 |
-
"<
|
7 |
-
"<
|
8 |
-
"<
|
9 |
-
"<
|
10 |
-
"<
|
11 |
-
"<
|
12 |
-
"<PFV>":
|
13 |
-
"<PL>":
|
14 |
-
"<
|
15 |
-
"<
|
16 |
-
"<
|
|
|
|
|
|
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"<1>": 50,
|
3 |
+
"<2>": 58,
|
4 |
+
"<3>": 63,
|
5 |
+
"<COND>": 57,
|
6 |
+
"<FUT>": 51,
|
7 |
+
"<IMP>": 52,
|
8 |
+
"<IND>": 61,
|
9 |
+
"<IPFV>": 56,
|
10 |
+
"<NFIN>": 53,
|
11 |
+
"<NOM>": 62,
|
12 |
+
"<PFV>": 59,
|
13 |
+
"<PL>": 54,
|
14 |
+
"<POS>": 60,
|
15 |
+
"<PRS>": 46,
|
16 |
+
"<PST>": 49,
|
17 |
+
"<SBJV>": 47,
|
18 |
+
"<SG>": 55,
|
19 |
+
"<V>": 48
|
20 |
}
|
config.json
CHANGED
@@ -25,5 +25,5 @@
|
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.35.2",
|
27 |
"use_cache": true,
|
28 |
-
"vocab_size":
|
29 |
}
|
|
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.35.2",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 64
|
29 |
}
|
model.safetensors
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 sha256:2ff60fba0e76fbe5fc73d46aec930d02037633ddfafe26efb9851a5fc51675c9
|
3 |
+
size 29459544
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,24 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<PRS>",
|
4 |
+
"<SBJV>",
|
5 |
+
"<V>",
|
6 |
+
"<PST>",
|
7 |
+
"<1>",
|
8 |
+
"<FUT>",
|
9 |
+
"<IMP>",
|
10 |
+
"<NFIN>",
|
11 |
+
"<PL>",
|
12 |
+
"<SG>",
|
13 |
+
"<IPFV>",
|
14 |
+
"<COND>",
|
15 |
+
"<2>",
|
16 |
+
"<PFV>",
|
17 |
+
"<POS>",
|
18 |
+
"<IND>",
|
19 |
+
"<NOM>",
|
20 |
+
"<3>"
|
21 |
+
],
|
22 |
"bos_token": {
|
23 |
"content": "<s>",
|
24 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -31,8 +31,172 @@
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
"bos_token": "<s>",
|
37 |
"clean_up_tokenization_spaces": true,
|
38 |
"eos_token": "</s>",
|
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
+
},
|
35 |
+
"46": {
|
36 |
+
"content": "<PRS>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"47": {
|
44 |
+
"content": "<SBJV>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"48": {
|
52 |
+
"content": "<V>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"49": {
|
60 |
+
"content": "<PST>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"50": {
|
68 |
+
"content": "<1>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"51": {
|
76 |
+
"content": "<FUT>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"52": {
|
84 |
+
"content": "<IMP>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"53": {
|
92 |
+
"content": "<NFIN>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"54": {
|
100 |
+
"content": "<PL>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"55": {
|
108 |
+
"content": "<SG>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"56": {
|
116 |
+
"content": "<IPFV>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"57": {
|
124 |
+
"content": "<COND>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"58": {
|
132 |
+
"content": "<2>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"59": {
|
140 |
+
"content": "<PFV>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"60": {
|
148 |
+
"content": "<POS>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"61": {
|
156 |
+
"content": "<IND>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"62": {
|
164 |
+
"content": "<NOM>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"63": {
|
172 |
+
"content": "<3>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
}
|
179 |
},
|
180 |
+
"additional_special_tokens": [
|
181 |
+
"<PRS>",
|
182 |
+
"<SBJV>",
|
183 |
+
"<V>",
|
184 |
+
"<PST>",
|
185 |
+
"<1>",
|
186 |
+
"<FUT>",
|
187 |
+
"<IMP>",
|
188 |
+
"<NFIN>",
|
189 |
+
"<PL>",
|
190 |
+
"<SG>",
|
191 |
+
"<IPFV>",
|
192 |
+
"<COND>",
|
193 |
+
"<2>",
|
194 |
+
"<PFV>",
|
195 |
+
"<POS>",
|
196 |
+
"<IND>",
|
197 |
+
"<NOM>",
|
198 |
+
"<3>"
|
199 |
+
],
|
200 |
"bos_token": "<s>",
|
201 |
"clean_up_tokenization_spaces": true,
|
202 |
"eos_token": "</s>",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d43744df5c002561af0767247b7ee3912b584b6b1941caa4d245f60f01e9ca4
|
3 |
size 4728
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"y": 0, "\u0153": 1, "d": 2, "s": 3, "i": 4, "\u00fb": 5, "\u00e2": 6, "x": 7, "'": 8, "\u00e9": 9, "\u00f4": 10, "m": 11, "e": 12, "g": 13, "\u00e7": 14, "N": 15, "j": 16, " ": 17, "v": 18, "a": 19, "u": 20, "\u00ee": 21, "h": 22, "c": 23, "f": 24, "l": 25, "w": 26, "k": 27, "o": 28, "n": 29, "\u00eb": 30, "\u00ef": 31, "\u00fc": 32, "b": 33, "\u1e63": 34, "\u00e8": 35, "-": 36, "z": 37, "r": 38, "q": 39, "t": 40, "p": 41}
|