ggaonlp commited on
Commit
4b8b256
·
verified ·
1 Parent(s): 4b90d1d

Upload 12 files

Browse files
0_DataParallel/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/msmarco-distilbert-base-tas-b",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertModel"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "qa_dropout": 0.1,
18
+ "seq_classif_dropout": 0.2,
19
+ "sinusoidal_pos_embds": false,
20
+ "tie_weights_": true,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.18.0",
23
+ "vocab_size": 30522
24
+ }
0_DataParallel/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de28048b1acc51e4989e59428dac3d9b6687061dde110a6e6dfaf3a16f4caf6d
3
+ size 265483513
0_DataParallel/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 128,
3
+ "do_lower_case": false
4
+ }
0_DataParallel/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
0_DataParallel/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
0_DataParallel/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "model_max_length": 128, "name_or_path": "sentence-transformers/msmarco-distilbert-base-tas-b", "special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/ba1a276969ccad7ea2344196e7b8561b36292db74bff940ee316dadc05d005d3.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_class": "DistilBertTokenizer"}
0_DataParallel/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
1_DataParallel/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false
7
+ }
README.md CHANGED
@@ -1,3 +1,91 @@
1
- ---
2
- license: cc-by-nc-4.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+
8
+ ---
9
+
10
+ # {MODEL_NAME}
11
+
12
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a None 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
+ ## Evaluation Results
38
+
39
+ <!--- Describe how your model was evaluated -->
40
+
41
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
42
+
43
+
44
+ ## Training
45
+ The model was trained with the parameters:
46
+
47
+ **DataLoader**:
48
+
49
+ `torch.utils.data.dataloader.DataLoader` of length 1127 with parameters:
50
+ ```
51
+ {'batch_size': 440, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
52
+ ```
53
+
54
+ **Loss**:
55
+
56
+ `losses.reward_ranking.LossWRanking`
57
+
58
+ Parameters of the fit()-Method:
59
+ ```
60
+ {
61
+ "epochs": 2,
62
+ "evaluation_steps": 140,
63
+ "evaluator": "utils.train_retriever.OurInformationRetrievalEvaluator",
64
+ "max_grad_norm": 1,
65
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
66
+ "optimizer_params": {
67
+ "lr": 1e-06
68
+ },
69
+ "scheduler": "ConstantLR",
70
+ "steps_per_epoch": null,
71
+ "warmup_steps": 0,
72
+ "weight_decay": 0.01
73
+ }
74
+ ```
75
+
76
+
77
+ ## Full Model Architecture
78
+ ```
79
+ SentenceTransformerWandb(
80
+ (0): DataParallel(
81
+ (module): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
82
+ )
83
+ (1): DataParallel(
84
+ (module): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
85
+ )
86
+ )
87
+ ```
88
+
89
+ ## Citing & Authors
90
+
91
+ <!--- Describe where people can find more information -->
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ }
7
+ }
model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e4a16d7cd0ad5211ea3226731a6f371fe0826e6c5af262f9f5e137262d6991
3
+ size 265987255
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "0_DataParallel",
6
+ "type": "torch.nn.parallel.data_parallel"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_DataParallel",
12
+ "type": "torch.nn.parallel.data_parallel"
13
+ }
14
+ ]