Hugging Face's logo

chef2121
/
DSA4213

Safetensors
Model card Files
xet
Community
chef2121 commited on
Commit
600ee4e
·
1 Parent(s): cc6e319

ok

Browse files
Files changed (15) hide show
  1. .gitattributes +0 -35
  2. article_longformer.zip +0 -3
  3. article_longformer/config.json +0 -57
  4. article_longformer/merges.txt +0 -0
  5. article_longformer/model.safetensors +0 -3
  6. article_longformer/special_tokens_map.json +0 -51
  7. article_longformer/tokenizer_config.json +0 -57
  8. article_longformer/vocab.json +0 -0
  9. config.json +0 -57
  10. main.py +0 -14
  11. merges.txt +0 -0
  12. model.safetensors +0 -3
  13. special_tokens_map.json +0 -51
  14. tokenizer_config.json +0 -57
  15. vocab.json +0 -0
.gitattributes DELETED
@@ -1,35 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
article_longformer.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:508839b95060d30128cad0a38b352c6d344135e033396799028a09cb7d067c3a
3
- size 356773517
 
 
 
 
article_longformer/config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "architectures": [
3
- "LongformerForSequenceClassification"
4
- ],
5
- "attention_mode": "longformer",
6
- "attention_probs_dropout_prob": 0.1,
7
- "attention_window": [
8
- 512,
9
- 512,
10
- 512,
11
- 512,
12
- 512,
13
- 512,
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512
20
- ],
21
- "bos_token_id": 0,
22
- "dtype": "float32",
23
- "eos_token_id": 2,
24
- "gradient_checkpointing": false,
25
- "hidden_act": "gelu",
26
- "hidden_dropout_prob": 0.1,
27
- "hidden_size": 768,
28
- "id2label": {
29
- "0": "left",
30
- "1": "lean left",
31
- "2": "center",
32
- "3": "lean right",
33
- "4": "right"
34
- },
35
- "ignore_attention_mask": false,
36
- "initializer_range": 0.02,
37
- "intermediate_size": 3072,
38
- "label2id": {
39
- "center": 2,
40
- "lean left": 1,
41
- "lean right": 3,
42
- "left": 0,
43
- "right": 4
44
- },
45
- "layer_norm_eps": 1e-05,
46
- "max_position_embeddings": 4098,
47
- "model_type": "longformer",
48
- "num_attention_heads": 12,
49
- "num_hidden_layers": 12,
50
- "onnx_export": false,
51
- "pad_token_id": 1,
52
- "problem_type": "single_label_classification",
53
- "sep_token_id": 2,
54
- "transformers_version": "4.57.1",
55
- "type_vocab_size": 1,
56
- "vocab_size": 50265
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
article_longformer/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
article_longformer/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8417148427672a3452e533b1ec4c14bf8d28c08cac5f58a034f0532913f79cb7
3
- size 599432328
 
 
 
 
article_longformer/special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
article_longformer/tokenizer_config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "LongformerTokenizer",
56
- "unk_token": "<unk>"
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
article_longformer/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "architectures": [
3
- "LongformerForSequenceClassification"
4
- ],
5
- "attention_mode": "longformer",
6
- "attention_probs_dropout_prob": 0.1,
7
- "attention_window": [
8
- 512,
9
- 512,
10
- 512,
11
- 512,
12
- 512,
13
- 512,
14
- 512,
15
- 512,
16
- 512,
17
- 512,
18
- 512,
19
- 512
20
- ],
21
- "bos_token_id": 0,
22
- "dtype": "float32",
23
- "eos_token_id": 2,
24
- "gradient_checkpointing": false,
25
- "hidden_act": "gelu",
26
- "hidden_dropout_prob": 0.1,
27
- "hidden_size": 768,
28
- "id2label": {
29
- "0": "left",
30
- "1": "lean left",
31
- "2": "center",
32
- "3": "lean right",
33
- "4": "right"
34
- },
35
- "ignore_attention_mask": false,
36
- "initializer_range": 0.02,
37
- "intermediate_size": 3072,
38
- "label2id": {
39
- "center": 2,
40
- "lean left": 1,
41
- "lean right": 3,
42
- "left": 0,
43
- "right": 4
44
- },
45
- "layer_norm_eps": 1e-05,
46
- "max_position_embeddings": 4098,
47
- "model_type": "longformer",
48
- "num_attention_heads": 12,
49
- "num_hidden_layers": 12,
50
- "onnx_export": false,
51
- "pad_token_id": 1,
52
- "problem_type": "single_label_classification",
53
- "sep_token_id": 2,
54
- "transformers_version": "4.57.1",
55
- "type_vocab_size": 1,
56
- "vocab_size": 50265
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
main.py DELETED
@@ -1,14 +0,0 @@
1
-
2
- from transformers import AutoModelForSequenceClassification, AutoTokenizer
3
-
4
- # Load your model
5
- model = AutoModelForSequenceClassification.from_pretrained("./article_longformer")
6
- tokenizer = AutoTokenizer.from_pretrained("./article_longformer")
7
-
8
- # Login and push
9
- from huggingface_hub import notebook_login
10
- notebook_login() # Enter your HF token
11
-
12
- model.push_to_hub("chef2121/DSA4213")
13
- tokenizer.push_to_hub("chef2121/DSA4213")
14
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8417148427672a3452e533b1ec4c14bf8d28c08cac5f58a034f0532913f79cb7
3
- size 599432328
 
 
 
 
special_tokens_map.json DELETED
@@ -1,51 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json DELETED
@@ -1,57 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<s>",
6
- "lstrip": false,
7
- "normalized": true,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<pad>",
14
- "lstrip": false,
15
- "normalized": true,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": true,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- }
44
- },
45
- "bos_token": "<s>",
46
- "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
- "eos_token": "</s>",
49
- "errors": "replace",
50
- "extra_special_tokens": {},
51
- "mask_token": "<mask>",
52
- "model_max_length": 1000000000000000019884624838656,
53
- "pad_token": "<pad>",
54
- "sep_token": "</s>",
55
- "tokenizer_class": "LongformerTokenizer",
56
- "unk_token": "<unk>"
57
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vocab.json DELETED
The diff for this file is too large to render. See raw diff