scriptedvn commited on
Commit
15d4f11
·
verified ·
1 Parent(s): efb53bd

m2m100_418m: CTranslate2 int8 (MIT, facebook/m2m100_418M @55c2e61)

Browse files
m2m100_418m/ct2_int8/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_source_bos": false,
3
+ "add_source_eos": false,
4
+ "bos_token": "<s>",
5
+ "decoder_start_token": "</s>",
6
+ "eos_token": "</s>",
7
+ "layer_norm_epsilon": null,
8
+ "multi_query_attention": false,
9
+ "unk_token": "<unk>"
10
+ }
m2m100_418m/ct2_int8/model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:590e9c7e229e84de8affe7b15487660a286d3d76e44a4ca10e33099b198d9a76
3
+ size 490667752
m2m100_418m/ct2_int8/runtime_manifest.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": 1,
3
+ "created": "2026-11-13T01:18:48.842629+00:00",
4
+ "model_bin_size": 490667752,
5
+ "files": [
6
+ "config.json",
7
+ "model.bin",
8
+ "shared_vocabulary.json"
9
+ ],
10
+ "source_dir": "facebook_m2m100_418m",
11
+ "model_bin_sha256": "590e9c7e229e84de8affe7b15487660a286d3d76e44a4ca10e33099b198d9a76"
12
+ }
m2m100_418m/ct2_int8/shared_vocabulary.json ADDED
The diff for this file is too large to render. See raw diff
 
m2m100_418m/model/LICENSE ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ MIT License
2
+
3
+ Copyright (c) Facebook, Inc. and its affiliates.
4
+
5
+ Permission is hereby granted, free of charge, to any person obtaining a copy
6
+ of this software and associated documentation files (the "Software"), to deal
7
+ in the Software without restriction, including without limitation the rights
8
+ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9
+ copies of the Software, and to permit persons to whom the Software is
10
+ furnished to do so, subject to the following conditions:
11
+
12
+ The above copyright notice and this permission notice shall be included in all
13
+ copies or substantial portions of the Software.
14
+
15
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18
+ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20
+ OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21
+ SOFTWARE.
m2m100_418m/model/README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - multilingual
4
+ - af
5
+ - am
6
+ - ar
7
+ - ast
8
+ - az
9
+ - ba
10
+ - be
11
+ - bg
12
+ - bn
13
+ - br
14
+ - bs
15
+ - ca
16
+ - ceb
17
+ - cs
18
+ - cy
19
+ - da
20
+ - de
21
+ - el
22
+ - en
23
+ - es
24
+ - et
25
+ - fa
26
+ - ff
27
+ - fi
28
+ - fr
29
+ - fy
30
+ - ga
31
+ - gd
32
+ - gl
33
+ - gu
34
+ - ha
35
+ - he
36
+ - hi
37
+ - hr
38
+ - ht
39
+ - hu
40
+ - hy
41
+ - id
42
+ - ig
43
+ - ilo
44
+ - is
45
+ - it
46
+ - ja
47
+ - jv
48
+ - ka
49
+ - kk
50
+ - km
51
+ - kn
52
+ - ko
53
+ - lb
54
+ - lg
55
+ - ln
56
+ - lo
57
+ - lt
58
+ - lv
59
+ - mg
60
+ - mk
61
+ - ml
62
+ - mn
63
+ - mr
64
+ - ms
65
+ - my
66
+ - ne
67
+ - nl
68
+ - no
69
+ - ns
70
+ - oc
71
+ - or
72
+ - pa
73
+ - pl
74
+ - ps
75
+ - pt
76
+ - ro
77
+ - ru
78
+ - sd
79
+ - si
80
+ - sk
81
+ - sl
82
+ - so
83
+ - sq
84
+ - sr
85
+ - ss
86
+ - su
87
+ - sv
88
+ - sw
89
+ - ta
90
+ - th
91
+ - tl
92
+ - tn
93
+ - tr
94
+ - uk
95
+ - ur
96
+ - uz
97
+ - vi
98
+ - wo
99
+ - xh
100
+ - yi
101
+ - yo
102
+ - zh
103
+ - zu
104
+ license: mit
105
+ ---
106
+
107
+ # M2M100 418M
108
+
109
+ M2M100 is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation.
110
+ It was introduced in this [paper](https://arxiv.org/abs/2010.11125) and first released in [this](https://github.com/pytorch/fairseq/tree/master/examples/m2m_100) repository.
111
+
112
+ The model that can directly translate between the 9,900 directions of 100 languages.
113
+ To translate into a target language, the target language id is forced as the first generated token.
114
+ To force the target language id as the first generated token, pass the `forced_bos_token_id` parameter to the `generate` method.
115
+
116
+ *Note: `M2M100Tokenizer` depends on `sentencepiece`, so make sure to install it before running the example.*
117
+
118
+ To install `sentencepiece` run `pip install sentencepiece`
119
+
120
+
121
+ ```python
122
+ from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer
123
+
124
+ hi_text = "जीवन एक चॉकलेट बॉक्स की तरह है।"
125
+ chinese_text = "生活就像一盒巧克力。"
126
+
127
+ model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
128
+ tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")
129
+
130
+ # translate Hindi to French
131
+ tokenizer.src_lang = "hi"
132
+ encoded_hi = tokenizer(hi_text, return_tensors="pt")
133
+ generated_tokens = model.generate(**encoded_hi, forced_bos_token_id=tokenizer.get_lang_id("fr"))
134
+ tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
135
+ # => "La vie est comme une boîte de chocolat."
136
+
137
+ # translate Chinese to English
138
+ tokenizer.src_lang = "zh"
139
+ encoded_zh = tokenizer(chinese_text, return_tensors="pt")
140
+ generated_tokens = model.generate(**encoded_zh, forced_bos_token_id=tokenizer.get_lang_id("en"))
141
+ tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
142
+ # => "Life is like a box of chocolate."
143
+ ```
144
+
145
+
146
+ See the [model hub](https://huggingface.co/models?filter=m2m_100) to look for more fine-tuned versions.
147
+
148
+
149
+ ## Languages covered
150
+ Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English (en), Spanish (es), Estonian (et), Persian (fa), Fulah (ff), Finnish (fi), French (fr), Western Frisian (fy), Irish (ga), Gaelic; Scottish Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Croatian (hr), Haitian; Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Igbo (ig), Iloko (ilo), Icelandic (is), Italian (it), Japanese (ja), Javanese (jv), Georgian (ka), Kazakh (kk), Central Khmer (km), Kannada (kn), Korean (ko), Luxembourgish; Letzeburgesch (lb), Ganda (lg), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Burmese (my), Nepali (ne), Dutch; Flemish (nl), Norwegian (no), Northern Sotho (ns), Occitan (post 1500) (oc), Oriya (or), Panjabi; Punjabi (pa), Polish (pl), Pushto; Pashto (ps), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Sindhi (sd), Sinhala; Sinhalese (si), Slovak (sk), Slovenian (sl), Somali (so), Albanian (sq), Serbian (sr), Swati (ss), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Thai (th), Tagalog (tl), Tswana (tn), Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Xhosa (xh), Yiddish (yi), Yoruba (yo), Chinese (zh), Zulu (zu)
151
+
152
+
153
+ ## BibTeX entry and citation info
154
+ ```
155
+ @misc{fan2020englishcentric,
156
+ title={Beyond English-Centric Multilingual Machine Translation},
157
+ author={Angela Fan and Shruti Bhosale and Holger Schwenk and Zhiyi Ma and Ahmed El-Kishky and Siddharth Goyal and Mandeep Baines and Onur Celebi and Guillaume Wenzek and Vishrav Chaudhary and Naman Goyal and Tom Birch and Vitaliy Liptchinsky and Sergey Edunov and Edouard Grave and Michael Auli and Armand Joulin},
158
+ year={2020},
159
+ eprint={2010.11125},
160
+ archivePrefix={arXiv},
161
+ primaryClass={cs.CL}
162
+ }
163
+ ```
m2m100_418m/model/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "hf_models/m2m100_418M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
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": 5,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "scale_embedding": true,
33
+ "transformers_version": "4.4.0.dev0",
34
+ "use_cache": true,
35
+ "vocab_size": 128112
36
+ }
m2m100_418m/model/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "max_length": 200,
8
+ "num_beams": 5,
9
+ "pad_token_id": 1,
10
+ "transformers_version": "4.27.0.dev0"
11
+ }
m2m100_418m/model/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
m2m100_418m/model/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__"]}
m2m100_418m/model/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>", "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "m2m_100_1.2B_v2/", "model_max_length": 1024}
m2m100_418m/model/vocab.json ADDED
The diff for this file is too large to render. See raw diff