Spaces:
Runtime error
Runtime error
track *pkl, add distillbert model, add wit dataset
Browse files- models/distilbert-base-wit/1_Pooling/config.json +7 -0
- models/distilbert-base-wit/2_Dense/config.json +1 -0
- models/distilbert-base-wit/2_Dense/pytorch_model.bin +3 -0
- models/distilbert-base-wit/README.md +109 -0
- models/distilbert-base-wit/config.json +24 -0
- models/distilbert-base-wit/config_sentence_transformers.json +7 -0
- models/distilbert-base-wit/modules.json +20 -0
- models/distilbert-base-wit/pytorch_model.bin +3 -0
- models/distilbert-base-wit/sentence_bert_config.json +4 -0
- models/distilbert-base-wit/special_tokens_map.json +1 -0
- models/distilbert-base-wit/tokenizer.json +0 -0
- models/distilbert-base-wit/tokenizer_config.json +1 -0
- models/distilbert-base-wit/vocab.txt +0 -0
- models/wit_dataset.pkl +3 -0
models/distilbert-base-wit/1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
models/distilbert-base-wit/2_Dense/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"in_features": 768, "out_features": 64, "bias": false, "activation_function": "torch.nn.modules.linear.Identity"}
|
models/distilbert-base-wit/2_Dense/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9489ee6242690d583b46ecf23515441811653c3d33eb70f41a4c329bd6a6dfe
|
3 |
+
size 197483
|
models/distilbert-base-wit/README.md
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
+
tags:
|
4 |
+
- sentence-transformers
|
5 |
+
- feature-extraction
|
6 |
+
- sentence-similarity
|
7 |
+
- transformers
|
8 |
+
---
|
9 |
+
|
10 |
+
**⚠️ This model is deprecated. Please don't use it as it produces sentence embeddings of low quality. You can find recommended sentence embedding models here: [SBERT.net - Pretrained Models](https://www.sbert.net/docs/pretrained_models.html)**
|
11 |
+
|
12 |
+
|
13 |
+
# sentence-transformers/distilbert-base-nli-stsb-mean-tokens
|
14 |
+
|
15 |
+
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
16 |
+
|
17 |
+
|
18 |
+
|
19 |
+
## Usage (Sentence-Transformers)
|
20 |
+
|
21 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
22 |
+
|
23 |
+
```
|
24 |
+
pip install -U sentence-transformers
|
25 |
+
```
|
26 |
+
|
27 |
+
Then you can use the model like this:
|
28 |
+
|
29 |
+
```python
|
30 |
+
from sentence_transformers import SentenceTransformer
|
31 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
32 |
+
|
33 |
+
model = SentenceTransformer('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
|
34 |
+
embeddings = model.encode(sentences)
|
35 |
+
print(embeddings)
|
36 |
+
```
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
## Usage (HuggingFace Transformers)
|
41 |
+
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.
|
42 |
+
|
43 |
+
```python
|
44 |
+
from transformers import AutoTokenizer, AutoModel
|
45 |
+
import torch
|
46 |
+
|
47 |
+
|
48 |
+
#Mean Pooling - Take attention mask into account for correct averaging
|
49 |
+
def mean_pooling(model_output, attention_mask):
|
50 |
+
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
|
51 |
+
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
|
52 |
+
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
|
53 |
+
|
54 |
+
|
55 |
+
# Sentences we want sentence embeddings for
|
56 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
57 |
+
|
58 |
+
# Load model from HuggingFace Hub
|
59 |
+
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
|
60 |
+
model = AutoModel.from_pretrained('sentence-transformers/distilbert-base-nli-stsb-mean-tokens')
|
61 |
+
|
62 |
+
# Tokenize sentences
|
63 |
+
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
64 |
+
|
65 |
+
# Compute token embeddings
|
66 |
+
with torch.no_grad():
|
67 |
+
model_output = model(**encoded_input)
|
68 |
+
|
69 |
+
# Perform pooling. In this case, max pooling.
|
70 |
+
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
|
71 |
+
|
72 |
+
print("Sentence embeddings:")
|
73 |
+
print(sentence_embeddings)
|
74 |
+
```
|
75 |
+
|
76 |
+
|
77 |
+
|
78 |
+
## Evaluation Results
|
79 |
+
|
80 |
+
|
81 |
+
|
82 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sentence-transformers/distilbert-base-nli-stsb-mean-tokens)
|
83 |
+
|
84 |
+
|
85 |
+
|
86 |
+
## Full Model Architecture
|
87 |
+
```
|
88 |
+
SentenceTransformer(
|
89 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
90 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
91 |
+
)
|
92 |
+
```
|
93 |
+
|
94 |
+
## Citing & Authors
|
95 |
+
|
96 |
+
This model was trained by [sentence-transformers](https://www.sbert.net/).
|
97 |
+
|
98 |
+
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
|
99 |
+
```bibtex
|
100 |
+
@inproceedings{reimers-2019-sentence-bert,
|
101 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
102 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
103 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
104 |
+
month = "11",
|
105 |
+
year = "2019",
|
106 |
+
publisher = "Association for Computational Linguistics",
|
107 |
+
url = "http://arxiv.org/abs/1908.10084",
|
108 |
+
}
|
109 |
+
```
|
models/distilbert-base-wit/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distilbert-base-nli-stsb-mean-tokens/",
|
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": "4.10.0.dev0",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
models/distilbert-base-wit/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 |
+
}
|
models/distilbert-base-wit/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": "dense",
|
17 |
+
"path": "2_Dense",
|
18 |
+
"type": "sentence_transformers.models.Dense"
|
19 |
+
}
|
20 |
+
]
|
models/distilbert-base-wit/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6a70fd2d5d714ee6ea6592ba217a39e3a9c43ee4fb7230043d56ffbd77f81a0
|
3 |
+
size 265488185
|
models/distilbert-base-wit/sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
models/distilbert-base-wit/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
models/distilbert-base-wit/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/distilbert-base-wit/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, "model_max_length": 512, "special_tokens_map_file": "output/training_nli_distilbert-base-uncased-2020-07-22_10-20-15/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distilbert-base-nli-stsb-mean-tokens/", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "DistilBertTokenizer"}
|
models/distilbert-base-wit/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/wit_dataset.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:755311f1f4739e93725b03d3de17dfd7827502834840ea15c6c69d55f6cc145b
|
3 |
+
size 796426374
|