Hugging Face's logo

ngocdang83
/
HachimiMT-30-zh-vi

Translation
Transformers
Safetensors
Chinese
Vietnamese
marian
text2text-generation
zh-vi
chinese-vietnamese
marianmt
machine-translation
Model card Files
xet
 Community
ngocdang83 commited on
Commit
5e527cf
·
verified ·
1 Parent(s): 84a2e9c

Add CTranslate2 INT8 runtime

Browse files
Files changed (9) hide show
  1. ct2-int8_float32/config.json +10 -0
  2. ct2-int8_float32/generation_config.json +9 -0
  3. ct2-int8_float32/model.bin +3 -0
  4. ct2-int8_float32/shared_vocabulary.json +0 -0
  5. ct2-int8_float32/source.spm +3 -0
  6. ct2-int8_float32/special_tokens_map.json +6 -0
  7. ct2-int8_float32/target.spm +3 -0
  8. ct2-int8_float32/tokenizer_config.json +48 -0
  9. ct2-int8_float32/vocab.json +0 -0
ct2-int8_float32/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": "<pad>",
6
+ "eos_token": "</s>",
7
+ "layer_norm_epsilon": null,
8
+ "multi_query_attention": false,
9
+ "unk_token": "<unk>"
10
+ }
ct2-int8_float32/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.56.0"
9
+ }
ct2-int8_float32/model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978e306ddc1b16de6a072a172328a5577eb60601f473083a7e26a677d6ecb10a
3
+ size 32999195
ct2-int8_float32/shared_vocabulary.json ADDED
The diff for this file is too large to render. See raw diff
 
ct2-int8_float32/source.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c748c239774106a9b4dd521ae66ba1cf55fe9778d21ceea843ba0cbf7e59e9c
3
+ size 612230
ct2-int8_float32/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
ct2-int8_float32/target.spm ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c748c239774106a9b4dd521ae66ba1cf55fe9778d21ceea843ba0cbf7e59e9c
3
+ size 612230
ct2-int8_float32/tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<s>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "extra_special_tokens": {},
40
+ "model_max_length": 512,
41
+ "pad_token": "<pad>",
42
+ "separate_vocabs": false,
43
+ "source_lang": null,
44
+ "sp_model_kwargs": {},
45
+ "target_lang": null,
46
+ "tokenizer_class": "MarianTokenizer",
47
+ "unk_token": "<unk>"
48
+ }
ct2-int8_float32/vocab.json ADDED
The diff for this file is too large to render. See raw diff