scroobiustrip commited on
Commit
07c3dd8
1 Parent(s): 43e8e12

Upload folder using huggingface_hub

Browse files
1_Pooling/config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
- "word_embedding_dimension": 384,
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
  }
 
1
  {
2
+ "word_embedding_dimension": 1024,
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
  }
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  pipeline_tag: sentence-similarity
3
  tags:
4
  - sentence-transformers
@@ -9,7 +10,7 @@ tags:
9
 
10
  # {MODEL_NAME}
11
 
12
- This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
13
 
14
  <!--- Describe your model here -->
15
 
@@ -46,20 +47,23 @@ The model was trained with the parameters:
46
 
47
  **DataLoader**:
48
 
49
- `torch.utils.data.dataloader.DataLoader` of length 3651 with parameters:
50
  ```
51
- {'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
52
  ```
53
 
54
  **Loss**:
55
 
56
- `sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
 
 
 
57
 
58
  Parameters of the fit()-Method:
59
  ```
60
  {
61
  "epochs": 1,
62
- "evaluation_steps": 1000,
63
  "evaluator": "NoneType",
64
  "max_grad_norm": 1,
65
  "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
@@ -68,7 +72,7 @@ Parameters of the fit()-Method:
68
  },
69
  "scheduler": "WarmupLinear",
70
  "steps_per_epoch": null,
71
- "warmup_steps": 366,
72
  "weight_decay": 0.01
73
  }
74
  ```
@@ -77,8 +81,8 @@ Parameters of the fit()-Method:
77
  ## Full Model Architecture
78
  ```
79
  SentenceTransformer(
80
- (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
81
- (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
82
  (2): Normalize()
83
  )
84
  ```
 
1
  ---
2
+ library_name: sentence-transformers
3
  pipeline_tag: sentence-similarity
4
  tags:
5
  - sentence-transformers
 
10
 
11
  # {MODEL_NAME}
12
 
13
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
 
15
  <!--- Describe your model here -->
16
 
 
47
 
48
  **DataLoader**:
49
 
50
+ `torch.utils.data.dataloader.DataLoader` of length 2918 with parameters:
51
  ```
52
+ {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
53
  ```
54
 
55
  **Loss**:
56
 
57
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
58
+ ```
59
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
60
+ ```
61
 
62
  Parameters of the fit()-Method:
63
  ```
64
  {
65
  "epochs": 1,
66
+ "evaluation_steps": 0,
67
  "evaluator": "NoneType",
68
  "max_grad_norm": 1,
69
  "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
 
72
  },
73
  "scheduler": "WarmupLinear",
74
  "steps_per_epoch": null,
75
+ "warmup_steps": 1000,
76
  "weight_decay": 0.01
77
  }
78
  ```
 
81
  ## Full Model Architecture
82
  ```
83
  SentenceTransformer(
84
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
85
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
86
  (2): Normalize()
87
  )
88
  ```
config.json CHANGED
@@ -1,25 +1,24 @@
1
  {
2
- "_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L12-v2/",
3
  "architectures": [
4
  "BertModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 384,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 1536,
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.35.2",
23
  "type_vocab_size": 2,
24
  "use_cache": true,
25
  "vocab_size": 30522
 
1
  {
2
+ "_name_or_path": "intfloat/e5-large-v2",
3
  "architectures": [
4
  "BertModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
  "pad_token_id": 0,
19
  "position_embedding_type": "absolute",
20
  "torch_dtype": "float32",
21
+ "transformers_version": "4.38.2",
22
  "type_vocab_size": 2,
23
  "use_cache": true,
24
  "vocab_size": 30522
config_sentence_transformers.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
  "__version__": {
3
- "sentence_transformers": "2.0.0",
4
- "transformers": "4.6.1",
5
- "pytorch": "1.8.1"
6
- }
 
 
7
  }
 
1
  {
2
  "__version__": {
3
+ "sentence_transformers": "2.6.1",
4
+ "transformers": "4.38.2",
5
+ "pytorch": "2.2.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aac28f7d9ff7af318f0acb119212d3e8c120b81eec4bf812ad9e8fc7ad4c8ec7
3
- size 133462128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e66b76709daa06fd805814c6f450dc4bed0fe803c3fcdd4aa1332bcbc50c84d
3
+ size 1340612432
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 128,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 512,
3
  "do_lower_case": false
4
  }
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -43,22 +43,13 @@
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
- "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
- "max_length": 128,
50
  "model_max_length": 512,
51
- "never_split": null,
52
- "pad_to_multiple_of": null,
53
  "pad_token": "[PAD]",
54
- "pad_token_type_id": 0,
55
- "padding_side": "right",
56
  "sep_token": "[SEP]",
57
- "stride": 0,
58
  "strip_accents": null,
59
  "tokenize_chinese_chars": true,
60
  "tokenizer_class": "BertTokenizer",
61
- "truncation_side": "right",
62
- "truncation_strategy": "longest_first",
63
  "unk_token": "[UNK]"
64
  }
 
43
  },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
 
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
 
48
  "model_max_length": 512,
 
 
49
  "pad_token": "[PAD]",
 
 
50
  "sep_token": "[SEP]",
 
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
  "tokenizer_class": "BertTokenizer",
 
 
54
  "unk_token": "[UNK]"
55
  }