Upload folder using huggingface_hub
Browse files- best_checkpoint/config.json +34 -0
- best_checkpoint/generation_config.json +9 -0
- best_checkpoint/model.safetensors +3 -0
- best_checkpoint/tokenizer.json +3 -0
- best_checkpoint/tokenizer_config.json +228 -0
- model.safetensors +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +2 -2
best_checkpoint/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 |
+
"dtype": "float32",
|
| 17 |
+
"encoder_attention_heads": 16,
|
| 18 |
+
"encoder_ffn_dim": 4096,
|
| 19 |
+
"encoder_layerdrop": 0,
|
| 20 |
+
"encoder_layers": 12,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"init_std": 0.02,
|
| 23 |
+
"is_encoder_decoder": true,
|
| 24 |
+
"label_smoothing_factor": 0.2,
|
| 25 |
+
"max_position_embeddings": 1024,
|
| 26 |
+
"model_type": "m2m_100",
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"scale_embedding": true,
|
| 29 |
+
"tie_word_embeddings": true,
|
| 30 |
+
"tokenizer_class": "NllbTokenizer",
|
| 31 |
+
"transformers_version": "5.4.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 256206
|
| 34 |
+
}
|
best_checkpoint/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": "5.4.0"
|
| 9 |
+
}
|
best_checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1bc05473c1ce32ed526d5f3a636356cc188bc55c3956468c2dbf8eb9ad7f48
|
| 3 |
+
size 2460354912
|
best_checkpoint/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f35b41a274f87f4736cc977d5bcdbf99031552e149328491019d1b13cd4f5f1
|
| 3 |
+
size 32240389
|
best_checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"extra_special_tokens": [
|
| 7 |
+
"ace_Arab",
|
| 8 |
+
"ace_Latn",
|
| 9 |
+
"acm_Arab",
|
| 10 |
+
"acq_Arab",
|
| 11 |
+
"aeb_Arab",
|
| 12 |
+
"afr_Latn",
|
| 13 |
+
"ajp_Arab",
|
| 14 |
+
"aka_Latn",
|
| 15 |
+
"amh_Ethi",
|
| 16 |
+
"apc_Arab",
|
| 17 |
+
"arb_Arab",
|
| 18 |
+
"ars_Arab",
|
| 19 |
+
"ary_Arab",
|
| 20 |
+
"arz_Arab",
|
| 21 |
+
"asm_Beng",
|
| 22 |
+
"ast_Latn",
|
| 23 |
+
"awa_Deva",
|
| 24 |
+
"ayr_Latn",
|
| 25 |
+
"azb_Arab",
|
| 26 |
+
"azj_Latn",
|
| 27 |
+
"bak_Cyrl",
|
| 28 |
+
"bam_Latn",
|
| 29 |
+
"ban_Latn",
|
| 30 |
+
"bel_Cyrl",
|
| 31 |
+
"bem_Latn",
|
| 32 |
+
"ben_Beng",
|
| 33 |
+
"bho_Deva",
|
| 34 |
+
"bjn_Arab",
|
| 35 |
+
"bjn_Latn",
|
| 36 |
+
"bod_Tibt",
|
| 37 |
+
"bos_Latn",
|
| 38 |
+
"bug_Latn",
|
| 39 |
+
"bul_Cyrl",
|
| 40 |
+
"cat_Latn",
|
| 41 |
+
"ceb_Latn",
|
| 42 |
+
"ces_Latn",
|
| 43 |
+
"cjk_Latn",
|
| 44 |
+
"ckb_Arab",
|
| 45 |
+
"crh_Latn",
|
| 46 |
+
"cym_Latn",
|
| 47 |
+
"dan_Latn",
|
| 48 |
+
"deu_Latn",
|
| 49 |
+
"dik_Latn",
|
| 50 |
+
"dyu_Latn",
|
| 51 |
+
"dzo_Tibt",
|
| 52 |
+
"ell_Grek",
|
| 53 |
+
"eng_Latn",
|
| 54 |
+
"epo_Latn",
|
| 55 |
+
"est_Latn",
|
| 56 |
+
"eus_Latn",
|
| 57 |
+
"ewe_Latn",
|
| 58 |
+
"fao_Latn",
|
| 59 |
+
"pes_Arab",
|
| 60 |
+
"fij_Latn",
|
| 61 |
+
"fin_Latn",
|
| 62 |
+
"fon_Latn",
|
| 63 |
+
"fra_Latn",
|
| 64 |
+
"fur_Latn",
|
| 65 |
+
"fuv_Latn",
|
| 66 |
+
"gla_Latn",
|
| 67 |
+
"gle_Latn",
|
| 68 |
+
"glg_Latn",
|
| 69 |
+
"grn_Latn",
|
| 70 |
+
"guj_Gujr",
|
| 71 |
+
"hat_Latn",
|
| 72 |
+
"hau_Latn",
|
| 73 |
+
"heb_Hebr",
|
| 74 |
+
"hin_Deva",
|
| 75 |
+
"hne_Deva",
|
| 76 |
+
"hrv_Latn",
|
| 77 |
+
"hun_Latn",
|
| 78 |
+
"hye_Armn",
|
| 79 |
+
"ibo_Latn",
|
| 80 |
+
"ilo_Latn",
|
| 81 |
+
"ind_Latn",
|
| 82 |
+
"isl_Latn",
|
| 83 |
+
"ita_Latn",
|
| 84 |
+
"jav_Latn",
|
| 85 |
+
"jpn_Jpan",
|
| 86 |
+
"kab_Latn",
|
| 87 |
+
"kac_Latn",
|
| 88 |
+
"kam_Latn",
|
| 89 |
+
"kan_Knda",
|
| 90 |
+
"kas_Arab",
|
| 91 |
+
"kas_Deva",
|
| 92 |
+
"kat_Geor",
|
| 93 |
+
"knc_Arab",
|
| 94 |
+
"knc_Latn",
|
| 95 |
+
"kaz_Cyrl",
|
| 96 |
+
"kbp_Latn",
|
| 97 |
+
"kea_Latn",
|
| 98 |
+
"khm_Khmr",
|
| 99 |
+
"kik_Latn",
|
| 100 |
+
"kin_Latn",
|
| 101 |
+
"kir_Cyrl",
|
| 102 |
+
"kmb_Latn",
|
| 103 |
+
"kon_Latn",
|
| 104 |
+
"kor_Hang",
|
| 105 |
+
"kmr_Latn",
|
| 106 |
+
"lao_Laoo",
|
| 107 |
+
"lvs_Latn",
|
| 108 |
+
"lij_Latn",
|
| 109 |
+
"lim_Latn",
|
| 110 |
+
"lin_Latn",
|
| 111 |
+
"lit_Latn",
|
| 112 |
+
"lmo_Latn",
|
| 113 |
+
"ltg_Latn",
|
| 114 |
+
"ltz_Latn",
|
| 115 |
+
"lua_Latn",
|
| 116 |
+
"lug_Latn",
|
| 117 |
+
"luo_Latn",
|
| 118 |
+
"lus_Latn",
|
| 119 |
+
"mag_Deva",
|
| 120 |
+
"mai_Deva",
|
| 121 |
+
"mal_Mlym",
|
| 122 |
+
"mar_Deva",
|
| 123 |
+
"min_Latn",
|
| 124 |
+
"mkd_Cyrl",
|
| 125 |
+
"plt_Latn",
|
| 126 |
+
"mlt_Latn",
|
| 127 |
+
"mni_Beng",
|
| 128 |
+
"khk_Cyrl",
|
| 129 |
+
"mos_Latn",
|
| 130 |
+
"mri_Latn",
|
| 131 |
+
"zsm_Latn",
|
| 132 |
+
"mya_Mymr",
|
| 133 |
+
"nld_Latn",
|
| 134 |
+
"nno_Latn",
|
| 135 |
+
"nob_Latn",
|
| 136 |
+
"npi_Deva",
|
| 137 |
+
"nso_Latn",
|
| 138 |
+
"nus_Latn",
|
| 139 |
+
"nya_Latn",
|
| 140 |
+
"oci_Latn",
|
| 141 |
+
"gaz_Latn",
|
| 142 |
+
"ory_Orya",
|
| 143 |
+
"pag_Latn",
|
| 144 |
+
"pan_Guru",
|
| 145 |
+
"pap_Latn",
|
| 146 |
+
"pol_Latn",
|
| 147 |
+
"por_Latn",
|
| 148 |
+
"prs_Arab",
|
| 149 |
+
"pbt_Arab",
|
| 150 |
+
"quy_Latn",
|
| 151 |
+
"ron_Latn",
|
| 152 |
+
"run_Latn",
|
| 153 |
+
"rus_Cyrl",
|
| 154 |
+
"sag_Latn",
|
| 155 |
+
"san_Deva",
|
| 156 |
+
"sat_Beng",
|
| 157 |
+
"scn_Latn",
|
| 158 |
+
"shn_Mymr",
|
| 159 |
+
"sin_Sinh",
|
| 160 |
+
"slk_Latn",
|
| 161 |
+
"slv_Latn",
|
| 162 |
+
"smo_Latn",
|
| 163 |
+
"sna_Latn",
|
| 164 |
+
"snd_Arab",
|
| 165 |
+
"som_Latn",
|
| 166 |
+
"sot_Latn",
|
| 167 |
+
"spa_Latn",
|
| 168 |
+
"als_Latn",
|
| 169 |
+
"srd_Latn",
|
| 170 |
+
"srp_Cyrl",
|
| 171 |
+
"ssw_Latn",
|
| 172 |
+
"sun_Latn",
|
| 173 |
+
"swe_Latn",
|
| 174 |
+
"swh_Latn",
|
| 175 |
+
"szl_Latn",
|
| 176 |
+
"tam_Taml",
|
| 177 |
+
"tat_Cyrl",
|
| 178 |
+
"tel_Telu",
|
| 179 |
+
"tgk_Cyrl",
|
| 180 |
+
"tgl_Latn",
|
| 181 |
+
"tha_Thai",
|
| 182 |
+
"tir_Ethi",
|
| 183 |
+
"taq_Latn",
|
| 184 |
+
"taq_Tfng",
|
| 185 |
+
"tpi_Latn",
|
| 186 |
+
"tsn_Latn",
|
| 187 |
+
"tso_Latn",
|
| 188 |
+
"tuk_Latn",
|
| 189 |
+
"tum_Latn",
|
| 190 |
+
"tur_Latn",
|
| 191 |
+
"twi_Latn",
|
| 192 |
+
"tzm_Tfng",
|
| 193 |
+
"uig_Arab",
|
| 194 |
+
"ukr_Cyrl",
|
| 195 |
+
"umb_Latn",
|
| 196 |
+
"urd_Arab",
|
| 197 |
+
"uzn_Latn",
|
| 198 |
+
"vec_Latn",
|
| 199 |
+
"vie_Latn",
|
| 200 |
+
"war_Latn",
|
| 201 |
+
"wol_Latn",
|
| 202 |
+
"xho_Latn",
|
| 203 |
+
"ydd_Hebr",
|
| 204 |
+
"yor_Latn",
|
| 205 |
+
"yue_Hant",
|
| 206 |
+
"zho_Hans",
|
| 207 |
+
"zho_Hant",
|
| 208 |
+
"zul_Latn"
|
| 209 |
+
],
|
| 210 |
+
"is_local": true,
|
| 211 |
+
"legacy_behaviour": false,
|
| 212 |
+
"mask_token": "<mask>",
|
| 213 |
+
"max_length": 128,
|
| 214 |
+
"model_max_length": 1024,
|
| 215 |
+
"pad_to_multiple_of": null,
|
| 216 |
+
"pad_token": "<pad>",
|
| 217 |
+
"pad_token_type_id": 0,
|
| 218 |
+
"padding_side": "right",
|
| 219 |
+
"sep_token": "</s>",
|
| 220 |
+
"sp_model_kwargs": {},
|
| 221 |
+
"src_lang": "run_Latn",
|
| 222 |
+
"stride": 0,
|
| 223 |
+
"tgt_lang": "run_Latn",
|
| 224 |
+
"tokenizer_class": "NllbTokenizer",
|
| 225 |
+
"truncation_side": "right",
|
| 226 |
+
"truncation_strategy": "longest_first",
|
| 227 |
+
"unk_token": "<unk>"
|
| 228 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2460354912
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1bc05473c1ce32ed526d5f3a636356cc188bc55c3956468c2dbf8eb9ad7f48
|
| 3 |
size 2460354912
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 32240389
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f35b41a274f87f4736cc977d5bcdbf99031552e149328491019d1b13cd4f5f1
|
| 3 |
size 32240389
|
tokenizer_config.json
CHANGED
|
@@ -218,9 +218,9 @@
|
|
| 218 |
"padding_side": "right",
|
| 219 |
"sep_token": "</s>",
|
| 220 |
"sp_model_kwargs": {},
|
| 221 |
-
"src_lang": "
|
| 222 |
"stride": 0,
|
| 223 |
-
"tgt_lang":
|
| 224 |
"tokenizer_class": "NllbTokenizer",
|
| 225 |
"truncation_side": "right",
|
| 226 |
"truncation_strategy": "longest_first",
|
|
|
|
| 218 |
"padding_side": "right",
|
| 219 |
"sep_token": "</s>",
|
| 220 |
"sp_model_kwargs": {},
|
| 221 |
+
"src_lang": "run_Latn",
|
| 222 |
"stride": 0,
|
| 223 |
+
"tgt_lang": "run_Latn",
|
| 224 |
"tokenizer_class": "NllbTokenizer",
|
| 225 |
"truncation_side": "right",
|
| 226 |
"truncation_strategy": "longest_first",
|