init commit
Browse files- added_tokens.json +1 -0
- config.json +37 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{":vtok0:": 128112, ":vtok1:": 128113, ":vtok2:": 128114, ":vtok3:": 128115, ":vtok4:": 128116, ":vtok5:": 128117, ":vtok6:": 128118, ":vtok7:": 128119, ":vtok8:": 128120, ":vtok9:": 128121, ":vtok10:": 128122, ":vtok11:": 128123, ":vtok12:": 128124, ":vtok13:": 128125, ":vtok14:": 128126, ":vtok15:": 128127, ":vtok16:": 128128, ":vtok17:": 128129, ":vtok18:": 128130, ":vtok19:": 128131, ":vtok20:": 128132, ":vtok21:": 128133, ":vtok22:": 128134, ":vtok23:": 128135, ":vtok24:": 128136, ":vtok25:": 128137, ":vtok26:": 128138, ":vtok27:": 128139, ":vtok28:": 128140, ":vtok29:": 128141, ":vtok30:": 128142, ":vtok31:": 128143, ":vtok32:": 128144, ":vtok33:": 128145, ":vtok34:": 128146, ":vtok35:": 128147, ":vtok36:": 128148, ":vtok37:": 128149, ":vtok38:": 128150, ":vtok39:": 128151, ":vtok40:": 128152, ":vtok41:": 128153, ":vtok42:": 128154, ":vtok43:": 128155, ":vtok44:": 128156, ":vtok45:": 128157, ":vtok46:": 128158, ":vtok47:": 128159, ":vtok48:": 128160, ":vtok49:": 128161, ":vtok50:": 128162, ":vtok51:": 128163, ":vtok52:": 128164, ":vtok53:": 128165, ":vtok54:": 128166, ":vtok55:": 128167, ":vtok56:": 128168, ":vtok57:": 128169, ":vtok58:": 128170, ":vtok59:": 128171, ":vtok60:": 128172, ":vtok61:": 128173, ":vtok62:": 128174, ":vtok63:": 128175, ":vtok64:": 128176, ":vtok65:": 128177, ":vtok66:": 128178, ":vtok67:": 128179, ":vtok68:": 128180, ":vtok69:": 128181, ":vtok70:": 128182, ":vtok71:": 128183, ":vtok72:": 128184, ":vtok73:": 128185, ":vtok74:": 128186, ":vtok75:": 128187, ":vtok76:": 128188, ":vtok77:": 128189, ":vtok78:": 128190, ":vtok79:": 128191, ":vtok80:": 128192, ":vtok81:": 128193, ":vtok82:": 128194, ":vtok83:": 128195, ":vtok84:": 128196, ":vtok85:": 128197, ":vtok86:": 128198, ":vtok87:": 128199, ":vtok88:": 128200, ":vtok89:": 128201, ":vtok90:": 128202, ":vtok91:": 128203, ":vtok92:": 128204, ":vtok93:": 128205, ":vtok94:": 128206, ":vtok95:": 128207, ":vtok96:": 128208, ":vtok97:": 128209, ":vtok98:": 128210, ":vtok99:": 128211, ":vtok100:": 128212, ":vtok101:": 128213, ":vtok102:": 128214, ":vtok103:": 128215, ":vtok104:": 128216, ":vtok105:": 128217, ":vtok106:": 128218, ":vtok107:": 128219, ":vtok108:": 128220, ":vtok109:": 128221, ":vtok110:": 128222, ":vtok111:": 128223, ":vtok112:": 128224, ":vtok113:": 128225, ":vtok114:": 128226, ":vtok115:": 128227, ":vtok116:": 128228, ":vtok117:": 128229, ":vtok118:": 128230, ":vtok119:": 128231, ":vtok120:": 128232, ":vtok121:": 128233, ":vtok122:": 128234, ":vtok123:": 128235, ":vtok124:": 128236, ":vtok125:": 128237, ":vtok126:": 128238, ":vtok127:": 128239, ":vtok128:": 128240, ":vtok129:": 128241, ":vtok130:": 128242, ":vtok131:": 128243, ":vtok132:": 128244, ":vtok133:": 128245, ":vtok134:": 128246, ":vtok135:": 128247, ":vtok136:": 128248, ":vtok137:": 128249, ":vtok138:": 128250, ":vtok139:": 128251, ":vtok140:": 128252, ":vtok141:": 128253, ":vtok142:": 128254, ":vtok143:": 128255, ":vtok144:": 128256, ":vtok145:": 128257, ":vtok146:": 128258, ":vtok147:": 128259, ":vtok148:": 128260, ":vtok149:": 128261, ":vtok150:": 128262, ":vtok151:": 128263, ":vtok152:": 128264, ":vtok153:": 128265, ":vtok154:": 128266, ":vtok155:": 128267, ":vtok156:": 128268, ":vtok157:": 128269, ":vtok158:": 128270, ":vtok159:": 128271, ":vtok160:": 128272, ":vtok161:": 128273, ":vtok162:": 128274, ":vtok163:": 128275, ":vtok164:": 128276, ":vtok165:": 128277, ":vtok166:": 128278, ":vtok167:": 128279, ":vtok168:": 128280, ":vtok169:": 128281, ":vtok170:": 128282, ":vtok171:": 128283, ":vtok172:": 128284, ":vtok173:": 128285, ":vtok174:": 128286, ":vtok175:": 128287, ":vtok176:": 128288, ":vtok177:": 128289, ":vtok178:": 128290, ":vtok179:": 128291, ":vtok180:": 128292, ":vtok181:": 128293, ":vtok182:": 128294, ":vtok183:": 128295, ":vtok184:": 128296, ":vtok185:": 128297, ":vtok186:": 128298, ":vtok187:": 128299, ":vtok188:": 128300, ":vtok189:": 128301, ":vtok190:": 128302, ":vtok191:": 128303, ":vtok192:": 128304, ":vtok193:": 128305, ":vtok194:": 128306, ":vtok195:": 128307, ":vtok196:": 128308, ":vtok197:": 128309, ":vtok198:": 128310, ":vtok199:": 128311, ":vtok200:": 128312}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/m2m100_418M",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"M2M100Model"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.05,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"early_stopping": true,
|
18 |
+
"encoder_attention_heads": 16,
|
19 |
+
"encoder_ffn_dim": 4096,
|
20 |
+
"encoder_layerdrop": 0.05,
|
21 |
+
"encoder_layers": 12,
|
22 |
+
"eos_token_id": 2,
|
23 |
+
"gradient_checkpointing": false,
|
24 |
+
"init_std": 0.02,
|
25 |
+
"is_encoder_decoder": true,
|
26 |
+
"max_length": 200,
|
27 |
+
"max_position_embeddings": 1024,
|
28 |
+
"model_type": "m2m_100",
|
29 |
+
"num_beams": 1,
|
30 |
+
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"scale_embedding": true,
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.12.3",
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 128313
|
37 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46760d7b6b3f311f4eb04e8672b59fc4e7dbe4f2c95cb1b5cdd32ffc1d3b6449
|
3 |
+
size 1945043306
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
|
3 |
+
size 2423393
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "facebook/m2m100_418M", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|