codewithdark commited on
Commit
707cb91
·
verified ·
1 Parent(s): e1075c1

Upload folder using huggingface_hub

Browse files
checkpoints/model_checkpoint_epoch_1.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450e628c29ef5fbfe6175670bae2ee4e373ecc970373b759ac6f4016789884d9
3
+ size 653029198
checkpoints/model_checkpoint_epoch_2.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:934143f987ccf0dc8fecd3daacaae36e5ff1f75ef555cbd970d79a964a790e9c
3
+ size 653029198
checkpoints/model_checkpoint_epoch_3.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0e59a53351dece9172c720610d6552d75405a0cfdf0c8ec4164eb74f88e7c56
3
+ size 653029198
checkpoints/model_checkpoint_epoch_4.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76f085063c50d85918a977935992a4d18c901609fd59d90af540e73febd37f90
3
+ size 653029198
checkpoints/model_checkpoint_epoch_5.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d954fca595fd12dff375b7f4d80e7a24ff0187b73a6744c2fdbba84f649cce
3
+ size 653029198
checkpoints/tokenizer/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoints/tokenizer/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoints/tokenizer/tokenizer/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ArabicGPTModel"
4
+ ],
5
+ "dropout": 0.1,
6
+ "embed_dim": 512,
7
+ "ff_dim": 2048,
8
+ "max_seq_len": 256,
9
+ "model_type": "arabic-gpt",
10
+ "num_heads": 8,
11
+ "num_layers": 12,
12
+ "torch_dtype": "float32",
13
+ "transformers_version": "4.51.3",
14
+ "vocab_size": 32000
15
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c467b8b9d6c54e34f8acf1651d30c6660da2f025b8bedef3768b0c54b8af001
3
+ size 217609658