Abelex commited on
Commit
fc24471
·
verified ·
1 Parent(s): 980a13d

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. config.json +2 -2
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +2 -2
  4. tokenizer_config.json +3 -44
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "model_type": "bert",
3
  "architecture": "HybridSentenceChuLo",
4
- "chunk_size": 256,
5
  "max_chunks": 8,
6
  "num_labels": 8,
7
  "label2id": {
@@ -24,6 +24,6 @@
24
  "6": "sport",
25
  "7": "technology"
26
  },
27
- "pretrained_model": "Davlan/afro-xlmr-large",
28
  "top_k_sentences": 12
29
  }
 
1
  {
2
  "model_type": "bert",
3
  "architecture": "HybridSentenceChuLo",
4
+ "chunk_size": 512,
5
  "max_chunks": 8,
6
  "num_labels": 8,
7
  "label2id": {
 
24
  "6": "sport",
25
  "7": "technology"
26
  },
27
+ "pretrained_model": "Davlan/afro-xlmr-base",
28
  "top_k_sentences": 12
29
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a0609a33b54fa1ac22552412daa6579d9f151d031a746de697ecb05507274fc
3
- size 2247121467
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3ef9ccab8b56d8fe25dff4974479599e705aa4910fe1f6a11d43c79a8c6113
3
+ size 1119389563
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
3
- size 17082734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0cb7277b7f6efc61e33bc5daf6f17142babb0bb68b2d5dd600c96471a90c62e
3
+ size 16766134
tokenizer_config.json CHANGED
@@ -1,51 +1,10 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
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
- "250001": {
36
- "content": "<mask>",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
  "bos_token": "<s>",
45
- "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
- "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
  "model_max_length": 512,
51
  "pad_token": "<pad>",
 
1
  {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "bos_token": "<s>",
 
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
+ "is_local": false,
8
  "mask_token": "<mask>",
9
  "model_max_length": 512,
10
  "pad_token": "<pad>",