Hugging Face's logo

guymorlan
/
levanti_diacritics2translit

Token Classification
Transformers
Safetensors
Arabic
canine
Model card Files
xet
Community
guymorlan commited on
Commit
d272bab
·
1 Parent(s): 4856584

add model

Browse files
Files changed (4) hide show
  1. config.json +47 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +44 -0
  4. tokenizer_config.json +46 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../results_final/google/canine-s_6_5e-05_0.0_True/checkpoint-852/",
3
+ "architectures": [
4
+ "CanineForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 57344,
8
+ "downsampling_rate": 4,
9
+ "eos_token_id": 57345,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "\u05b5",
15
+ "1": "\u05b9",
16
+ "2": "O",
17
+ "3": "\u05b7",
18
+ "4": "\u05b0",
19
+ "5": "\u05bb",
20
+ "6": "\u05b4"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "O": 2,
26
+ "\u05b0": 4,
27
+ "\u05b4": 6,
28
+ "\u05b5": 0,
29
+ "\u05b7": 3,
30
+ "\u05b9": 1,
31
+ "\u05bb": 5
32
+ },
33
+ "layer_norm_eps": 1e-12,
34
+ "local_transformer_stride": 128,
35
+ "max_position_embeddings": 16384,
36
+ "model_type": "canine",
37
+ "num_attention_heads": 12,
38
+ "num_hash_buckets": 16384,
39
+ "num_hash_functions": 8,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.38.1",
44
+ "type_vocab_size": 16,
45
+ "upsampling_kernel_size": 4,
46
+ "use_cache": true
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df75a5e3aa926a0dc0eb7a131ecd2e678c137780e441cfa62e031c4aa41d656b
3
+ size 528383308
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "\u0000",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "\u0000",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "57344": {
13
+ "content": "",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "57345": {
21
+ "content": "",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "57347": {
29
+ "content": "",
30
+ "lstrip": true,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "",
38
+ "clean_up_tokenization_spaces": true,
39
+ "cls_token": "",
40
+ "eos_token": "",
41
+ "mask_token": "",
42
+ "model_max_length": 2048,
43
+ "pad_token": "\u0000",
44
+ "sep_token": "",
45
+ "tokenizer_class": "CanineTokenizer"
46
+ }