enas commited on
Commit
1ee0033
·
verified ·
1 Parent(s): 9fcfddd

Upload 19 files

Browse files
Files changed (19) hide show
  1. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/README-checkpoint.md +0 -0
  2. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/modules-checkpoint.json +20 -0
  3. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/sentence_bert_config-checkpoint.json +4 -0
  4. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/special_tokens_map-checkpoint.json +51 -0
  5. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
  6. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/tokenizer_config-checkpoint.json +73 -0
  7. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/vocab-checkpoint.txt +0 -0
  8. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /1_Pooling/.ipynb_checkpoints/config-checkpoint.json +10 -0
  9. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /1_Pooling/config.json +10 -0
  10. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /README.md +0 -0
  11. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /config.json +24 -0
  12. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /config_sentence_transformers.json +10 -0
  13. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /model.safetensors +3 -0
  14. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /modules.json +20 -0
  15. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /sentence_bert_config.json +4 -0
  16. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /special_tokens_map.json +51 -0
  17. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /tokenizer.json +0 -0
  18. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /tokenizer_config.json +73 -0
  19. 5_Self-Supervised Contrastive (SimCSE) (SS-C) /vocab.txt +0 -0
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/README-checkpoint.md ADDED
The diff for this file is too large to render. See raw diff
 
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/modules-checkpoint.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/sentence_bert_config-checkpoint.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 384,
3
+ "do_lower_case": false
4
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/special_tokens_map-checkpoint.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
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": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "max_length": 128,
60
+ "model_max_length": 384,
61
+ "pad_to_multiple_of": null,
62
+ "pad_token": "<pad>",
63
+ "pad_token_type_id": 0,
64
+ "padding_side": "right",
65
+ "sep_token": "</s>",
66
+ "stride": 0,
67
+ "strip_accents": null,
68
+ "tokenize_chinese_chars": true,
69
+ "tokenizer_class": "MPNetTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /.ipynb_checkpoints/vocab-checkpoint.txt ADDED
The diff for this file is too large to render. See raw diff
 
5_Self-Supervised Contrastive (SimCSE) (SS-C) /1_Pooling/.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /README.md ADDED
The diff for this file is too large to render. See raw diff
 
5_Self-Supervised Contrastive (SimCSE) (SS-C) /config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.49.0",
23
+ "vocab_size": 30527
24
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.49.0",
5
+ "pytorch": "2.6.0+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72931f6fda4d8354a9ddbea5ba05a94827554c21f072144c733813e15efed2e0
3
+ size 437967672
5_Self-Supervised Contrastive (SimCSE) (SS-C) /modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
5_Self-Supervised Contrastive (SimCSE) (SS-C) /sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 384,
3
+ "do_lower_case": false
4
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
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": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
5_Self-Supervised Contrastive (SimCSE) (SS-C) /tokenizer_config.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": false,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "extra_special_tokens": {},
58
+ "mask_token": "<mask>",
59
+ "max_length": 128,
60
+ "model_max_length": 384,
61
+ "pad_to_multiple_of": null,
62
+ "pad_token": "<pad>",
63
+ "pad_token_type_id": 0,
64
+ "padding_side": "right",
65
+ "sep_token": "</s>",
66
+ "stride": 0,
67
+ "strip_accents": null,
68
+ "tokenize_chinese_chars": true,
69
+ "tokenizer_class": "MPNetTokenizer",
70
+ "truncation_side": "right",
71
+ "truncation_strategy": "longest_first",
72
+ "unk_token": "[UNK]"
73
+ }
5_Self-Supervised Contrastive (SimCSE) (SS-C) /vocab.txt ADDED
The diff for this file is too large to render. See raw diff