hf-transformers-bot commited on
Commit
3159843
1 Parent(s): 2a7f87d

Update tiny models for NllbMoeForConditionalGeneration

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +2 -2
  3. pytorch_model.bin +2 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +2 -204
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -25,7 +25,7 @@
25
  "init_std": 0.02,
26
  "is_encoder_decoder": true,
27
  "max_position_embeddings": 20,
28
- "model_type": "nllb_moe",
29
  "moe_eval_capacity_token_fraction": 1.0,
30
  "moe_token_dropout": 0.2,
31
  "normalize_router_prob_before_dropping": false,
@@ -44,5 +44,5 @@
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.28.0.dev0",
46
  "use_cache": true,
47
- "vocab_size": 1199
48
  }
 
25
  "init_std": 0.02,
26
  "is_encoder_decoder": true,
27
  "max_position_embeddings": 20,
28
+ "model_type": "nllb-moe",
29
  "moe_eval_capacity_token_fraction": 1.0,
30
  "moe_token_dropout": 0.2,
31
  "normalize_router_prob_before_dropping": false,
 
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.28.0.dev0",
46
  "use_cache": true,
47
+ "vocab_size": 256204
48
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:828580e1f2a31f711e5ec7a3e9b20450d3144fb090b5416622baf9369957df4b
3
- size 234113
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11fd8b578c73ba258b38cd48c53b99ea6d331aed2def1ae6e49e6234200d4ae0
3
+ size 16554497
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,209 +1,7 @@
1
  {
2
- "additional_special_tokens": [
3
- "ace_Arab",
4
- "ace_Latn",
5
- "acm_Arab",
6
- "acq_Arab",
7
- "aeb_Arab",
8
- "afr_Latn",
9
- "ajp_Arab",
10
- "aka_Latn",
11
- "amh_Ethi",
12
- "apc_Arab",
13
- "arb_Arab",
14
- "ars_Arab",
15
- "ary_Arab",
16
- "arz_Arab",
17
- "asm_Beng",
18
- "ast_Latn",
19
- "awa_Deva",
20
- "ayr_Latn",
21
- "azb_Arab",
22
- "azj_Latn",
23
- "bak_Cyrl",
24
- "bam_Latn",
25
- "ban_Latn",
26
- "bel_Cyrl",
27
- "bem_Latn",
28
- "ben_Beng",
29
- "bho_Deva",
30
- "bjn_Arab",
31
- "bjn_Latn",
32
- "bod_Tibt",
33
- "bos_Latn",
34
- "bug_Latn",
35
- "bul_Cyrl",
36
- "cat_Latn",
37
- "ceb_Latn",
38
- "ces_Latn",
39
- "cjk_Latn",
40
- "ckb_Arab",
41
- "crh_Latn",
42
- "cym_Latn",
43
- "dan_Latn",
44
- "deu_Latn",
45
- "dik_Latn",
46
- "dyu_Latn",
47
- "dzo_Tibt",
48
- "ell_Grek",
49
- "eng_Latn",
50
- "epo_Latn",
51
- "est_Latn",
52
- "eus_Latn",
53
- "ewe_Latn",
54
- "fao_Latn",
55
- "pes_Arab",
56
- "fij_Latn",
57
- "fin_Latn",
58
- "fon_Latn",
59
- "fra_Latn",
60
- "fur_Latn",
61
- "fuv_Latn",
62
- "gla_Latn",
63
- "gle_Latn",
64
- "glg_Latn",
65
- "grn_Latn",
66
- "guj_Gujr",
67
- "hat_Latn",
68
- "hau_Latn",
69
- "heb_Hebr",
70
- "hin_Deva",
71
- "hne_Deva",
72
- "hrv_Latn",
73
- "hun_Latn",
74
- "hye_Armn",
75
- "ibo_Latn",
76
- "ilo_Latn",
77
- "ind_Latn",
78
- "isl_Latn",
79
- "ita_Latn",
80
- "jav_Latn",
81
- "jpn_Jpan",
82
- "kab_Latn",
83
- "kac_Latn",
84
- "kam_Latn",
85
- "kan_Knda",
86
- "kas_Arab",
87
- "kas_Deva",
88
- "kat_Geor",
89
- "knc_Arab",
90
- "knc_Latn",
91
- "kaz_Cyrl",
92
- "kbp_Latn",
93
- "kea_Latn",
94
- "khm_Khmr",
95
- "kik_Latn",
96
- "kin_Latn",
97
- "kir_Cyrl",
98
- "kmb_Latn",
99
- "kon_Latn",
100
- "kor_Hang",
101
- "kmr_Latn",
102
- "lao_Laoo",
103
- "lvs_Latn",
104
- "lij_Latn",
105
- "lim_Latn",
106
- "lin_Latn",
107
- "lit_Latn",
108
- "lmo_Latn",
109
- "ltg_Latn",
110
- "ltz_Latn",
111
- "lua_Latn",
112
- "lug_Latn",
113
- "luo_Latn",
114
- "lus_Latn",
115
- "mag_Deva",
116
- "mai_Deva",
117
- "mal_Mlym",
118
- "mar_Deva",
119
- "min_Latn",
120
- "mkd_Cyrl",
121
- "plt_Latn",
122
- "mlt_Latn",
123
- "mni_Beng",
124
- "khk_Cyrl",
125
- "mos_Latn",
126
- "mri_Latn",
127
- "zsm_Latn",
128
- "mya_Mymr",
129
- "nld_Latn",
130
- "nno_Latn",
131
- "nob_Latn",
132
- "npi_Deva",
133
- "nso_Latn",
134
- "nus_Latn",
135
- "nya_Latn",
136
- "oci_Latn",
137
- "gaz_Latn",
138
- "ory_Orya",
139
- "pag_Latn",
140
- "pan_Guru",
141
- "pap_Latn",
142
- "pol_Latn",
143
- "por_Latn",
144
- "prs_Arab",
145
- "pbt_Arab",
146
- "quy_Latn",
147
- "ron_Latn",
148
- "run_Latn",
149
- "rus_Cyrl",
150
- "sag_Latn",
151
- "san_Deva",
152
- "sat_Beng",
153
- "scn_Latn",
154
- "shn_Mymr",
155
- "sin_Sinh",
156
- "slk_Latn",
157
- "slv_Latn",
158
- "smo_Latn",
159
- "sna_Latn",
160
- "snd_Arab",
161
- "som_Latn",
162
- "sot_Latn",
163
- "spa_Latn",
164
- "als_Latn",
165
- "srd_Latn",
166
- "srp_Cyrl",
167
- "ssw_Latn",
168
- "sun_Latn",
169
- "swe_Latn",
170
- "swh_Latn",
171
- "szl_Latn",
172
- "tam_Taml",
173
- "tat_Cyrl",
174
- "tel_Telu",
175
- "tgk_Cyrl",
176
- "tgl_Latn",
177
- "tha_Thai",
178
- "tir_Ethi",
179
- "taq_Latn",
180
- "taq_Tfng",
181
- "tpi_Latn",
182
- "tsn_Latn",
183
- "tso_Latn",
184
- "tuk_Latn",
185
- "tum_Latn",
186
- "tur_Latn",
187
- "twi_Latn",
188
- "tzm_Tfng",
189
- "uig_Arab",
190
- "ukr_Cyrl",
191
- "umb_Latn",
192
- "urd_Arab",
193
- "uzn_Latn",
194
- "vec_Latn",
195
- "vie_Latn",
196
- "war_Latn",
197
- "wol_Latn",
198
- "xho_Latn",
199
- "ydd_Hebr",
200
- "yor_Latn",
201
- "yue_Hant",
202
- "zho_Hans",
203
- "zho_Hant",
204
- "zul_Latn"
205
- ],
206
  "bos_token": "<s>",
 
207
  "cls_token": "<s>",
208
  "eos_token": "</s>",
209
  "mask_token": {
 
1
  {
2
+ "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "mask_token": {