Pringled commited on
Commit
57905b1
·
verified ·
1 Parent(s): 45359ff

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -4,9 +4,9 @@
4
  "StaticModel"
5
  ],
6
  "tokenizer_name": "BAAI/bge-m3",
7
- "apply_pca": 256,
8
  "apply_zipf": null,
9
- "sif_coefficient": 1e-05,
10
  "hidden_dim": 256,
11
  "seq_length": 1000000,
12
  "normalize": true
 
4
  "StaticModel"
5
  ],
6
  "tokenizer_name": "BAAI/bge-m3",
7
+ "apply_pca": null,
8
  "apply_zipf": null,
9
+ "sif_coefficient": null,
10
  "hidden_dim": 256,
11
  "seq_length": 1000000,
12
  "normalize": true
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83eb52eb180d773fe409799701452896170e3b605756a6806335c5e354092e34
3
+ size 512365657
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:370e450e45668b38f46c2ac780839caab94d260fe9dc448e9872cb110f9c868d
3
- size 34630288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19f1909063da3cfe3bd83a782381f040dccea475f4816de11116444a73e1b6a1
3
+ size 18616131
tokenizer_config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "500353": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "500354": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "500355": {
36
+ "content": "<unk>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "500356": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "500357": {
52
+ "content": "<mask>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "bos_token": "<s>",
61
+ "clean_up_tokenization_spaces": false,
62
+ "cls_token": "<s>",
63
+ "eos_token": "</s>",
64
+ "extra_special_tokens": {},
65
+ "mask_token": "<mask>",
66
+ "model_max_length": 1000000000000000019884624838656,
67
+ "pad_token": "<pad>",
68
+ "sep_token": "</s>",
69
+ "tokenizer_class": "XLMRobertaTokenizerFast",
70
+ "unk_token": "<unk>"
71
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff