Muennighoff commited on
Commit
3c4e8cb
1 Parent(s): 8587f19

Add SGPT-1.3B-mean-nli

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 2048,
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
+ }
README.md ADDED
@@ -0,0 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ - transformers
8
+ ---
9
+
10
+ # {MODEL_NAME}
11
+
12
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 2048 dimensional dense vector space and can be used for tasks like clustering or semantic search.
13
+
14
+ <!--- Describe your model here -->
15
+
16
+ ## Usage (Sentence-Transformers)
17
+
18
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
19
+
20
+ ```
21
+ pip install -U sentence-transformers
22
+ ```
23
+
24
+ Then you can use the model like this:
25
+
26
+ ```python
27
+ from sentence_transformers import SentenceTransformer
28
+ sentences = ["This is an example sentence", "Each sentence is converted"]
29
+
30
+ model = SentenceTransformer('{MODEL_NAME}')
31
+ embeddings = model.encode(sentences)
32
+ print(embeddings)
33
+ ```
34
+
35
+
36
+
37
+ ## Usage (HuggingFace Transformers)
38
+ Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
39
+
40
+ ```python
41
+ from transformers import AutoTokenizer, AutoModel
42
+ import torch
43
+
44
+
45
+ #Mean Pooling - Take attention mask into account for correct averaging
46
+ def mean_pooling(model_output, attention_mask):
47
+ token_embeddings = model_output[0] #First element of model_output contains all token embeddings
48
+ input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
49
+ return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
50
+
51
+
52
+ # Sentences we want sentence embeddings for
53
+ sentences = ['This is an example sentence', 'Each sentence is converted']
54
+
55
+ # Load model from HuggingFace Hub
56
+ tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
57
+ model = AutoModel.from_pretrained('{MODEL_NAME}')
58
+
59
+ # Tokenize sentences
60
+ encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
61
+
62
+ # Compute token embeddings
63
+ with torch.no_grad():
64
+ model_output = model(**encoded_input)
65
+
66
+ # Perform pooling. In this case, mean pooling.
67
+ sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
68
+
69
+ print("Sentence embeddings:")
70
+ print(sentence_embeddings)
71
+ ```
72
+
73
+
74
+
75
+ ## Evaluation Results
76
+
77
+ <!--- Describe how your model was evaluated -->
78
+
79
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
80
+
81
+
82
+ ## Training
83
+ The model was trained with the parameters:
84
+
85
+ **DataLoader**:
86
+
87
+ `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 93941 with parameters:
88
+ ```
89
+ {'batch_size': 6}
90
+ ```
91
+
92
+ **Loss**:
93
+
94
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
95
+ ```
96
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
97
+ ```
98
+
99
+ Parameters of the fit()-Method:
100
+ ```
101
+ {
102
+ "epochs": 1,
103
+ "evaluation_steps": 9394,
104
+ "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
105
+ "max_grad_norm": 1,
106
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
107
+ "optimizer_params": {
108
+ "lr": 1e-05
109
+ },
110
+ "scheduler": "WarmupLinear",
111
+ "steps_per_epoch": null,
112
+ "warmup_steps": 9395,
113
+ "weight_decay": 0.01
114
+ }
115
+ ```
116
+
117
+
118
+ ## Full Model Architecture
119
+ ```
120
+ SentenceTransformer(
121
+ (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel
122
+ (1): Pooling({'word_embedding_dimension': 2048, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
123
+ )
124
+ ```
125
+
126
+ ## Citing & Authors
127
+
128
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoModel"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "embed_dropout": 0,
45
+ "eos_token_id": 50256,
46
+ "gradient_checkpointing": false,
47
+ "hidden_size": 2048,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_type": "gpt_neo",
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
+ "resid_dropout": 0,
56
+ "summary_activation": null,
57
+ "summary_first_dropout": 0.1,
58
+ "summary_proj_to_labels": true,
59
+ "summary_type": "cls_index",
60
+ "summary_use_proj": true,
61
+ "task_specific_params": {
62
+ "text-generation": {
63
+ "do_sample": true,
64
+ "max_length": 50,
65
+ "temperature": 0.9
66
+ }
67
+ },
68
+ "tokenizer_class": "GPT2Tokenizer",
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.11.3",
71
+ "use_cache": true,
72
+ "vocab_size": 50257,
73
+ "window_size": 256
74
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.1.0",
4
+ "transformers": "4.11.3",
5
+ "pytorch": "1.10.1"
6
+ }
7
+ }
eval/similarity_evaluation_sts-dev_results.csv ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
3
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
4
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
5
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
6
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
7
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
8
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
9
+ 0,9394,0.8373182655863537,0.845196070823313,0.8271427498816395,0.8331617173225478,0.8319957080743787,0.8390395309874307,0.6893300589747797,0.7074110308965289
10
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
11
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
12
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
13
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
14
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
15
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
16
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
17
+ 0,18788,0.8460292442096218,0.8517575219706576,0.8174173008844023,0.8258517318508026,0.8168397305576491,0.8262308762405682,0.6970374368423717,0.7276170128124229
18
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
19
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
20
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
21
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
22
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
23
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
24
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
25
+ 0,28182,0.8423182362652242,0.8453058431410612,0.7919431838320004,0.8015495531579016,0.7940755774545485,0.8051602300268924,0.6917172406017684,0.7289138998284149
26
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
27
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
28
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
29
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
30
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
31
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
32
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
33
+ 0,37576,0.8350271261359457,0.8378360558126747,0.7752934357825343,0.7863975640536652,0.7772459231036742,0.7889837953758176,0.661212314434191,0.7149181303833082
34
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
35
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
36
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
37
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
38
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
39
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
40
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
41
+ 0,46970,0.8318315547470184,0.8346688073305782,0.7668707008207098,0.7786116067231977,0.7689640970529085,0.7810075389816382,0.6610508081146742,0.7167976227835687
42
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
43
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
44
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
45
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
46
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
47
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
48
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
49
+ 0,56364,0.8280527217316905,0.831118897407438,0.7638942889235072,0.7754947351547783,0.7673064315905456,0.7789253008898593,0.6604795200949729,0.7171098027143099
50
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
51
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
52
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
53
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
54
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
55
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
56
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
57
+ 0,65758,0.8266854501839274,0.8290434564733747,0.754227354046023,0.7662275821626152,0.7577722238557894,0.769852017048218,0.6442099295691925,0.7074707960623287
58
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
59
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
60
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
61
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
62
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
63
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
64
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
65
+ 0,75152,0.8274226239189728,0.8293274904772188,0.7528179270669322,0.7647594334625974,0.7566751001561818,0.7688974808022938,0.645064569352185,0.7087861457245139
66
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
67
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
68
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
69
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
70
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
71
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
72
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
73
+ 0,84546,0.8214606067797368,0.8235212747265149,0.7387120879725495,0.751939401041105,0.7431213209257714,0.756511437339819,0.630797948960558,0.6997602604920956
74
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
75
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
76
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
77
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
78
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
79
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
80
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
81
+ 0,93940,0.8197987240610421,0.8217049692026005,0.7377689011116928,0.7509787050911597,0.7421453743736961,0.7556724787930166,0.6265263193658941,0.696106030212265
82
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
83
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
84
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
85
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
86
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
87
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
88
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
89
+ 0,-1,0.8197928644030876,0.8216927147457449,0.7377774506651151,0.7510007851775719,0.7421530672082042,0.7557090197435007,0.6265183332131773,0.696126229514461
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6934444d1af597e35ad6de7c21f278c21036e5fae63adaf61b49bc312fe0c609
3
+ size 5363096833
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 75,
3
+ "do_lower_case": false
4
+ }
similarity_evaluation_sts-test_results.csv ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
3
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
4
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
5
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
6
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
7
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
8
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
9
+ -1,-1,0.8163652839944099,0.8184536075694563,0.7794147509073669,0.782091147640634,0.7790544940199657,0.7834707287382985,0.6441022388691878,0.6574417602773706
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-1.3B", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff