Huggs108Bj commited on
Commit
858be73
1 Parent(s): 131db6f

Upload 9 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,253 @@
1
  ---
2
- license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - ace
4
+ - acm
5
+ - acq
6
+ - aeb
7
+ - af
8
+ - ajp
9
+ - ak
10
+ - als
11
+ - am
12
+ - apc
13
+ - ar
14
+ - ars
15
+ - ary
16
+ - arz
17
+ - as
18
+ - ast
19
+ - awa
20
+ - ayr
21
+ - azb
22
+ - azj
23
+ - ba
24
+ - bm
25
+ - ban
26
+ - be
27
+ - bem
28
+ - bn
29
+ - bho
30
+ - bjn
31
+ - bo
32
+ - bs
33
+ - bug
34
+ - bg
35
+ - ca
36
+ - ceb
37
+ - cs
38
+ - cjk
39
+ - ckb
40
+ - crh
41
+ - cy
42
+ - da
43
+ - de
44
+ - dik
45
+ - dyu
46
+ - dz
47
+ - el
48
+ - en
49
+ - eo
50
+ - et
51
+ - eu
52
+ - ee
53
+ - fo
54
+ - fj
55
+ - fi
56
+ - fon
57
+ - fr
58
+ - fur
59
+ - fuv
60
+ - gaz
61
+ - gd
62
+ - ga
63
+ - gl
64
+ - gn
65
+ - gu
66
+ - ht
67
+ - ha
68
+ - he
69
+ - hi
70
+ - hne
71
+ - hr
72
+ - hu
73
+ - hy
74
+ - ig
75
+ - ilo
76
+ - id
77
+ - is
78
+ - it
79
+ - jv
80
+ - ja
81
+ - kab
82
+ - kac
83
+ - kam
84
+ - kn
85
+ - ks
86
+ - ka
87
+ - kk
88
+ - kbp
89
+ - kea
90
+ - khk
91
+ - km
92
+ - ki
93
+ - rw
94
+ - ky
95
+ - kmb
96
+ - kmr
97
+ - knc
98
+ - kg
99
+ - ko
100
+ - lo
101
+ - lij
102
+ - li
103
+ - ln
104
+ - lt
105
+ - lmo
106
+ - ltg
107
+ - lb
108
+ - lua
109
+ - lg
110
+ - luo
111
+ - lus
112
+ - lvs
113
+ - mag
114
+ - mai
115
+ - ml
116
+ - mar
117
+ - min
118
+ - mk
119
+ - mt
120
+ - mni
121
+ - mos
122
+ - mi
123
+ - my
124
+ - nl
125
+ - nn
126
+ - nb
127
+ - npi
128
+ - nso
129
+ - nus
130
+ - ny
131
+ - oc
132
+ - ory
133
+ - pag
134
+ - pa
135
+ - pap
136
+ - pbt
137
+ - pes
138
+ - plt
139
+ - pl
140
+ - pt
141
+ - prs
142
+ - quy
143
+ - ro
144
+ - rn
145
+ - ru
146
+ - sg
147
+ - sa
148
+ - sat
149
+ - scn
150
+ - shn
151
+ - si
152
+ - sk
153
+ - sl
154
+ - sm
155
+ - sn
156
+ - sd
157
+ - so
158
+ - st
159
+ - es
160
+ - sc
161
+ - sr
162
+ - ss
163
+ - su
164
+ - sv
165
+ - swh
166
+ - szl
167
+ - ta
168
+ - taq
169
+ - tt
170
+ - te
171
+ - tg
172
+ - tl
173
+ - th
174
+ - ti
175
+ - tpi
176
+ - tn
177
+ - ts
178
+ - tk
179
+ - tum
180
+ - tr
181
+ - tw
182
+ - tzm
183
+ - ug
184
+ - uk
185
+ - umb
186
+ - ur
187
+ - uzn
188
+ - vec
189
+ - vi
190
+ - war
191
+ - wo
192
+ - xh
193
+ - ydd
194
+ - yo
195
+ - yue
196
+ - zh
197
+ - zsm
198
+ - zu
199
+
200
+ language_details: "ace_Arab, ace_Latn, acm_Arab, acq_Arab, aeb_Arab, afr_Latn, ajp_Arab, aka_Latn, amh_Ethi, apc_Arab, arb_Arab, ars_Arab, ary_Arab, arz_Arab, asm_Beng, ast_Latn, awa_Deva, ayr_Latn, azb_Arab, azj_Latn, bak_Cyrl, bam_Latn, ban_Latn,bel_Cyrl, bem_Latn, ben_Beng, bho_Deva, bjn_Arab, bjn_Latn, bod_Tibt, bos_Latn, bug_Latn, bul_Cyrl, cat_Latn, ceb_Latn, ces_Latn, cjk_Latn, ckb_Arab, crh_Latn, cym_Latn, dan_Latn, deu_Latn, dik_Latn, dyu_Latn, dzo_Tibt, ell_Grek, eng_Latn, epo_Latn, est_Latn, eus_Latn, ewe_Latn, fao_Latn, pes_Arab, fij_Latn, fin_Latn, fon_Latn, fra_Latn, fur_Latn, fuv_Latn, gla_Latn, gle_Latn, glg_Latn, grn_Latn, guj_Gujr, hat_Latn, hau_Latn, heb_Hebr, hin_Deva, hne_Deva, hrv_Latn, hun_Latn, hye_Armn, ibo_Latn, ilo_Latn, ind_Latn, isl_Latn, ita_Latn, jav_Latn, jpn_Jpan, kab_Latn, kac_Latn, kam_Latn, kan_Knda, kas_Arab, kas_Deva, kat_Geor, knc_Arab, knc_Latn, kaz_Cyrl, kbp_Latn, kea_Latn, khm_Khmr, kik_Latn, kin_Latn, kir_Cyrl, kmb_Latn, kon_Latn, kor_Hang, kmr_Latn, lao_Laoo, lvs_Latn, lij_Latn, lim_Latn, lin_Latn, lit_Latn, lmo_Latn, ltg_Latn, ltz_Latn, lua_Latn, lug_Latn, luo_Latn, lus_Latn, mag_Deva, mai_Deva, mal_Mlym, mar_Deva, min_Latn, mkd_Cyrl, plt_Latn, mlt_Latn, mni_Beng, khk_Cyrl, mos_Latn, mri_Latn, zsm_Latn, mya_Mymr, nld_Latn, nno_Latn, nob_Latn, npi_Deva, nso_Latn, nus_Latn, nya_Latn, oci_Latn, gaz_Latn, ory_Orya, pag_Latn, pan_Guru, pap_Latn, pol_Latn, por_Latn, prs_Arab, pbt_Arab, quy_Latn, ron_Latn, run_Latn, rus_Cyrl, sag_Latn, san_Deva, sat_Beng, scn_Latn, shn_Mymr, sin_Sinh, slk_Latn, slv_Latn, smo_Latn, sna_Latn, snd_Arab, som_Latn, sot_Latn, spa_Latn, als_Latn, srd_Latn, srp_Cyrl, ssw_Latn, sun_Latn, swe_Latn, swh_Latn, szl_Latn, tam_Taml, tat_Cyrl, tel_Telu, tgk_Cyrl, tgl_Latn, tha_Thai, tir_Ethi, taq_Latn, taq_Tfng, tpi_Latn, tsn_Latn, tso_Latn, tuk_Latn, tum_Latn, tur_Latn, twi_Latn, tzm_Tfng, uig_Arab, ukr_Cyrl, umb_Latn, urd_Arab, uzn_Latn, vec_Latn, vie_Latn, war_Latn, wol_Latn, xho_Latn, ydd_Hebr, yor_Latn, yue_Hant, zho_Hans, zho_Hant, zul_Latn"
201
+
202
+ pipeline_tag: translation
203
+ tags:
204
+ - nllb
205
+ license: "cc-by-nc-4.0"
206
+ datasets:
207
+ - flores-200
208
+ metrics:
209
+ - bleu
210
+ - spbleu
211
+ - chrf++
212
+ inference: false
213
  ---
214
+
215
+ # NLLB-200
216
+
217
+ This is the model card of NLLB-200's distilled 600M variant.
218
+
219
+ Here are the [metrics](https://tinyurl.com/nllb200densedst600mmetrics) for that particular checkpoint.
220
+
221
+ - Information about training algorithms, parameters, fairness constraints or other applied approaches, and features. The exact training algorithm, data and the strategies to handle data imbalances for high and low resource languages that were used to train NLLB-200 is described in the paper.
222
+ - Paper or other resource for more information NLLB Team et al, No Language Left Behind: Scaling Human-Centered Machine Translation, Arxiv, 2022
223
+ - License: CC-BY-NC
224
+ - Where to send questions or comments about the model: https://github.com/facebookresearch/fairseq/issues
225
+
226
+
227
+
228
+ ## Intended Use
229
+ - Primary intended uses: NLLB-200 is a machine translation model primarily intended for research in machine translation, - especially for low-resource languages. It allows for single sentence translation among 200 languages. Information on how to - use the model can be found in Fairseq code repository along with the training code and references to evaluation and training data.
230
+ - Primary intended users: Primary users are researchers and machine translation research community.
231
+ - Out-of-scope use cases: NLLB-200 is a research model and is not released for production deployment. NLLB-200 is trained on general domain text data and is not intended to be used with domain specific texts, such as medical domain or legal domain. The model is not intended to be used for document translation. The model was trained with input lengths not exceeding 512 tokens, therefore translating longer sequences might result in quality degradation. NLLB-200 translations can not be used as certified translations.
232
+
233
+ ## Metrics
234
+ • Model performance measures: NLLB-200 model was evaluated using BLEU, spBLEU, and chrF++ metrics widely adopted by machine translation community. Additionally, we performed human evaluation with the XSTS protocol and measured the toxicity of the generated translations.
235
+
236
+
237
+ ## Evaluation Data
238
+ - Datasets: Flores-200 dataset is described in Section 4
239
+ - Motivation: We used Flores-200 as it provides full evaluation coverage of the languages in NLLB-200
240
+ - Preprocessing: Sentence-split raw text data was preprocessed using SentencePiece. The
241
+ SentencePiece model is released along with NLLB-200.
242
+
243
+ ## Training Data
244
+ • We used parallel multilingual data from a variety of sources to train the model. We provide detailed report on data selection and construction process in Section 5 in the paper. We also used monolingual data constructed from Common Crawl. We provide more details in Section 5.2.
245
+
246
+ ## Ethical Considerations
247
+ • In this work, we took a reflexive approach in technological development to ensure that we prioritize human users and minimize risks that could be transferred to them. While we reflect on our ethical considerations throughout the article, here are some additional points to highlight. For one, many languages chosen for this study are low-resource languages, with a heavy emphasis on African languages. While quality translation could improve education and information access in many in these communities, such an access could also make groups with lower levels of digital literacy more vulnerable to misinformation or online scams. The latter scenarios could arise if bad actors misappropriate our work for nefarious activities, which we conceive as an example of unintended use. Regarding data acquisition, the training data used for model development were mined from various publicly available sources on the web. Although we invested heavily in data cleaning, personally identifiable information may not be entirely eliminated. Finally, although we did our best to optimize for translation quality, mistranslations produced by the model could remain. Although the odds are low, this could have adverse impact on those who rely on these translations to make important decisions (particularly when related to health and safety).
248
+
249
+ ## Caveats and Recommendations
250
+ • Our model has been tested on the Wikimedia domain with limited investigation on other domains supported in NLLB-MD. In addition, the supported languages may have variations that our model is not capturing. Users should make appropriate assessments.
251
+
252
+ ## Carbon Footprint Details
253
+ • The carbon dioxide (CO2e) estimate is reported in Section 8.8.
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0,
19
+ "encoder_layers": 12,
20
+ "eos_token_id": 2,
21
+ "init_std": 0.02,
22
+ "is_encoder_decoder": true,
23
+ "max_position_embeddings": 1024,
24
+ "model_type": "m2m_100",
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 1,
27
+ "scale_embedding": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.21.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 256206,
32
+ "tokenizer_class": "NllbTokenizer",
33
+ "max_length": 200
34
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 200,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.27.0.dev0"
9
+ }
gitattributes.txt ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ftz filter=lfs diff=lfs merge=lfs -text
6
+ *.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.h5 filter=lfs diff=lfs merge=lfs -text
8
+ *.joblib filter=lfs diff=lfs merge=lfs -text
9
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
10
+ *.model filter=lfs diff=lfs merge=lfs -text
11
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
12
+ *.onnx filter=lfs diff=lfs merge=lfs -text
13
+ *.ot filter=lfs diff=lfs merge=lfs -text
14
+ *.parquet filter=lfs diff=lfs merge=lfs -text
15
+ *.pb filter=lfs diff=lfs merge=lfs -text
16
+ *.pt filter=lfs diff=lfs merge=lfs -text
17
+ *.pth filter=lfs diff=lfs merge=lfs -text
18
+ *.rar filter=lfs diff=lfs merge=lfs -text
19
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
20
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
21
+ *.tflite filter=lfs diff=lfs merge=lfs -text
22
+ *.tgz filter=lfs diff=lfs merge=lfs -text
23
+ *.wasm filter=lfs diff=lfs merge=lfs -text
24
+ *.xz filter=lfs diff=lfs merge=lfs -text
25
+ *.zip filter=lfs diff=lfs merge=lfs -text
26
+ *.zstandard filter=lfs diff=lfs merge=lfs -text
27
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ sentencepiece.bpe.model filter=lfs diff=lfs merge=lfs -text
29
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c266c2cfd19758b6d09c1fc31ecdf1e485509035f6b51dfe84f1ada83eefcc42
3
+ size 2460457927
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json ADDED
@@ -0,0 +1,219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
210
+ "content": "<mask>",
211
+ "lstrip": true,
212
+ "normalized": true,
213
+ "rstrip": false,
214
+ "single_word": false
215
+ },
216
+ "pad_token": "<pad>",
217
+ "sep_token": "</s>",
218
+ "unk_token": "<unk>"
219
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
3
+ size 17331176
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": {
7
+ "__type": "AddedToken",
8
+ "content": "<mask>",
9
+ "lstrip": true,
10
+ "normalized": true,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "model_max_length": 1024,
15
+ "name_or_path": "facebook/nllb-200-distilled-600M",
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "sp_model_kwargs": {},
19
+ "special_tokens_map_file": null,
20
+ "src_lang": null,
21
+ "tgt_lang": null,
22
+ "tokenizer_class": "NllbTokenizer",
23
+ "unk_token": "<unk>"
24
+ }