Update README.md
Browse files
README.md
CHANGED
@@ -200,8 +200,6 @@ language:
|
|
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 |
tags:
|
203 |
-
- nllb
|
204 |
-
- nllb-moe
|
205 |
- translation
|
206 |
license: "cc-by-nc-4.0"
|
207 |
datasets:
|
@@ -248,13 +246,25 @@ for the list of all BCP-47 in the Flores 200 dataset.
|
|
248 |
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-moe-54b")
|
249 |
>>> model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-moe-54b")
|
250 |
|
251 |
-
>>>
|
252 |
-
|
|
|
|
|
|
|
|
|
|
|
253 |
|
254 |
>>> translated_tokens = model.generate(
|
255 |
-
... **inputs, forced_bos_token_id=tokenizer.lang_code_to_id["fra_Latn"]
|
256 |
... )
|
257 |
-
>>> tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
|
258 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
259 |
```
|
260 |
|
|
|
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 |
tags:
|
|
|
|
|
203 |
- translation
|
204 |
license: "cc-by-nc-4.0"
|
205 |
datasets:
|
|
|
246 |
>>> tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-moe-54b")
|
247 |
>>> model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-moe-54b")
|
248 |
|
249 |
+
>>> batched_input = ['We now have 4-month-old mice that are non-diabetic that used to be diabetic," he added.',
|
250 |
+
"Dr. Ehud Ur, professor of medicine at Dalhousie University in Halifax, Nova Scotia and chair of the clinical and scientific division of the Canadian Diabetes Association cautioned that the research is still in its early days."
|
251 |
+
"Like some other experts, he is skeptical about whether diabetes can be cured, noting that these findings have no relevance to people who already have Type 1 diabetes."
|
252 |
+
"On Monday, Sara Danius, permanent secretary of the Nobel Committee for Literature at the Swedish Academy, publicly announced during a radio program on Sveriges Radio in Sweden the committee, unable to reach Bob Dylan directly about winning the 2016 Nobel Prize in Literature, had abandoned its efforts to reach him.",
|
253 |
+
'Danius said, "Right now we are doing nothing. I have called and sent emails to his closest collaborator and received very friendly replies
|
254 |
+
]
|
255 |
+
>>> inputs = tokenizer(article, return_tensors="pt", padding = True)
|
256 |
|
257 |
>>> translated_tokens = model.generate(
|
258 |
+
... **inputs, forced_bos_token_id=tokenizer.lang_code_to_id["fra_Latn"]
|
259 |
... )
|
260 |
+
>>> tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
|
261 |
+
['"Nous avons maintenant des souris de 4 mois non diabétiques qui étaient diabétiques", a-t-il ajouté.',
|
262 |
+
"Le docteur Ehud Ur, professeur de médecine à l'université Dalhousie, à Halifax, en Nouvelle-Écosse, et président de la division clinique et scientifique de l'Association canadienne du diabète, prévient que la recherche n'en est qu'à ses débuts.",
|
263 |
+
"Comme d'autres spécialistes, il est sceptique quant à la guérison du diabète, notant que ces résultats ne sont pas pertinents pour les personnes atteintes de diabète de type 1.",
|
264 |
+
"Lundi, Sara Danius, secrétaire permanente du Comité Nobel de littérature à l'Académie suédoise, a annoncé publiquement lors d'une émission de radio sur Sveriges Radio en Suède que le comité, incapable de contacter Bob Dylan directement au sujet du prix Nobel de littérature 2016, avait abandonné ses efforts pour le joindre.",
|
265 |
+
"Danius a déclaré: \"Pour le moment, nous ne faisons rien. J'ai appelé et envoyé des courriels à son plus proche collaborateur et j'ai reçu des réponses très amicales. Pour l'instant, c'est certainement suffisant\".",
|
266 |
+
"Auparavant, le PDG de Ring, Jamie Siminoff, a fait remarquer que la société avait commencé lorsque sa sonnette n'était pas audible depuis son magasin dans son garage.",
|
267 |
+
"Il a construit une sonnette WiFi, il a dit.",
|
268 |
+
]
|
269 |
```
|
270 |
|