sergioburdisso
commited on
Commit
•
b15e034
1
Parent(s):
1486f0b
Push model to huggingface
Browse files- 1_Pooling/config.json +1 -1
- README.md +18 -48
- config.json +4 -4
- config_sentence_transformers.json +3 -3
- model.safetensors +2 -2
- modules.json +0 -6
- sentence_bert_config.json +1 -1
- tokenizer.json +2 -4
- tokenizer_config.json +1 -3
1_Pooling/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"word_embedding_dimension":
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
|
|
1 |
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
"pooling_mode_cls_token": false,
|
4 |
"pooling_mode_mean_tokens": true,
|
5 |
"pooling_mode_max_tokens": false,
|
README.md
CHANGED
@@ -1,26 +1,16 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
license: mit
|
4 |
-
library_name: sentence-transformers
|
5 |
tags:
|
6 |
- sentence-transformers
|
|
|
7 |
- sentence-similarity
|
8 |
-
-
|
9 |
-
- dialog-flow
|
10 |
-
datasets:
|
11 |
-
- Salesforce/dialogstudio
|
12 |
-
pipeline_tag: sentence-similarity
|
13 |
-
base_model:
|
14 |
-
- aws-ai/dse-bert-base
|
15 |
-
---
|
16 |
|
|
|
17 |
|
18 |
-
#
|
19 |
-
|
20 |
-
This a variation of the **D2F$_{single}$** model introduced in the paper ["Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction"](https://publications.idiap.ch/attachments/papers/2024/Burdisso_EMNLP2024_2024.pdf) published in the EMNLP 2024 main conference.
|
21 |
-
This version uses DSE-base as the backbone model which yields to an increase in performance as compared to the vanilla version using BERT-base as the backbone (results reported in Appendix C).
|
22 |
|
23 |
-
|
24 |
|
25 |
<!--- Describe your model here -->
|
26 |
|
@@ -36,7 +26,7 @@ Then you can use the model like this:
|
|
36 |
|
37 |
```python
|
38 |
from sentence_transformers import SentenceTransformer
|
39 |
-
sentences = ["
|
40 |
|
41 |
model = SentenceTransformer('sergioburdisso/dialog2flow-single-dse-base')
|
42 |
embeddings = model.encode(sentences)
|
@@ -61,7 +51,7 @@ def mean_pooling(model_output, attention_mask):
|
|
61 |
|
62 |
|
63 |
# Sentences we want sentence embeddings for
|
64 |
-
sentences = ['
|
65 |
|
66 |
# Load model from HuggingFace Hub
|
67 |
tokenizer = AutoTokenizer.from_pretrained('sergioburdisso/dialog2flow-single-dse-base')
|
@@ -81,23 +71,21 @@ print("Sentence embeddings:")
|
|
81 |
print(sentence_embeddings)
|
82 |
```
|
83 |
|
84 |
-
## Training
|
85 |
-
The model was trained with the parameters:
|
86 |
|
87 |
-
**DataLoader**:
|
88 |
|
89 |
-
|
90 |
-
```
|
91 |
-
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
92 |
-
```
|
93 |
|
94 |
-
|
95 |
|
96 |
-
|
|
|
|
|
|
|
|
|
97 |
|
98 |
**DataLoader**:
|
99 |
|
100 |
-
`torch.utils.data.dataloader.DataLoader` of length
|
101 |
```
|
102 |
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
103 |
```
|
@@ -110,7 +98,7 @@ Parameters of the fit()-Method:
|
|
110 |
```
|
111 |
{
|
112 |
"epochs": 15,
|
113 |
-
"evaluation_steps":
|
114 |
"evaluator": [
|
115 |
"spretrainer.evaluation.FewShotClassificationEvaluator.FewShotClassificationEvaluator"
|
116 |
],
|
@@ -136,22 +124,4 @@ SentenceTransformer(
|
|
136 |
|
137 |
## Citing & Authors
|
138 |
|
139 |
-
|
140 |
-
```bibtex
|
141 |
-
@inproceedings{burdisso-etal-2024-dialog2flow,
|
142 |
-
title = "Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction",
|
143 |
-
author = "Burdisso, Sergio and
|
144 |
-
Madikeri, Srikanth and
|
145 |
-
Motlicek, Petr",
|
146 |
-
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
|
147 |
-
month = nov,
|
148 |
-
year = "2024",
|
149 |
-
address = "Miami",
|
150 |
-
publisher = "Association for Computational Linguistics",
|
151 |
-
}
|
152 |
-
```
|
153 |
-
|
154 |
-
## License
|
155 |
-
|
156 |
-
Copyright (c) 2024 [Idiap Research Institute](https://www.idiap.ch/).
|
157 |
-
MIT License.
|
|
|
1 |
---
|
2 |
+
pipeline_tag: sentence-similarity
|
|
|
|
|
3 |
tags:
|
4 |
- sentence-transformers
|
5 |
+
- feature-extraction
|
6 |
- sentence-similarity
|
7 |
+
- transformers
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
+
---
|
10 |
|
11 |
+
# sergioburdisso/dialog2flow-single-dse-base
|
|
|
|
|
|
|
12 |
|
13 |
+
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.
|
14 |
|
15 |
<!--- Describe your model here -->
|
16 |
|
|
|
26 |
|
27 |
```python
|
28 |
from sentence_transformers import SentenceTransformer
|
29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
30 |
|
31 |
model = SentenceTransformer('sergioburdisso/dialog2flow-single-dse-base')
|
32 |
embeddings = model.encode(sentences)
|
|
|
51 |
|
52 |
|
53 |
# Sentences we want sentence embeddings for
|
54 |
+
sentences = ['This is an example sentence', 'Each sentence is converted']
|
55 |
|
56 |
# Load model from HuggingFace Hub
|
57 |
tokenizer = AutoTokenizer.from_pretrained('sergioburdisso/dialog2flow-single-dse-base')
|
|
|
71 |
print(sentence_embeddings)
|
72 |
```
|
73 |
|
|
|
|
|
74 |
|
|
|
75 |
|
76 |
+
## Evaluation Results
|
|
|
|
|
|
|
77 |
|
78 |
+
<!--- Describe how your model was evaluated -->
|
79 |
|
80 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=sergioburdisso/dialog2flow-single-dse-base)
|
81 |
+
|
82 |
+
|
83 |
+
## Training
|
84 |
+
The model was trained with the parameters:
|
85 |
|
86 |
**DataLoader**:
|
87 |
|
88 |
+
`torch.utils.data.dataloader.DataLoader` of length 24615 with parameters:
|
89 |
```
|
90 |
{'batch_size': 64, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
91 |
```
|
|
|
98 |
```
|
99 |
{
|
100 |
"epochs": 15,
|
101 |
+
"evaluation_steps": 246,
|
102 |
"evaluator": [
|
103 |
"spretrainer.evaluation.FewShotClassificationEvaluator.FewShotClassificationEvaluator"
|
104 |
],
|
|
|
124 |
|
125 |
## Citing & Authors
|
126 |
|
127 |
+
<!--- Describe where people can find more information -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
@@ -8,14 +8,14 @@
|
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"initializer_range": 0.02,
|
13 |
-
"intermediate_size":
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
"max_position_embeddings": 512,
|
16 |
"model_type": "bert",
|
17 |
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers":
|
19 |
"pad_token_id": 0,
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/idiap/temp/sburdisso/repos/jsalt/keya-dialog/outputs/tod_all/dse-bert-base/soft-labels/label_multi-qa-mpnet-base-dot-v1_t0.35/msl64_pm-mean/ch-on_t0.05/lr3e-06_bs64_e15/best_model_metric_0",
|
3 |
"architectures": [
|
4 |
"BertModel"
|
5 |
],
|
|
|
8 |
"gradient_checkpointing": false,
|
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-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",
|
config_sentence_transformers.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
-
"sentence_transformers": "2.
|
4 |
-
"transformers": "4.
|
5 |
-
"pytorch": "
|
6 |
}
|
7 |
}
|
|
|
1 |
{
|
2 |
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.30.2",
|
5 |
+
"pytorch": "2.0.1"
|
6 |
}
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6ab50d69e51a41345e8595dbd36fe0c4706e89472b59b675b9656ce2620382c
|
3 |
+
size 437951328
|
modules.json
CHANGED
@@ -10,11 +10,5 @@
|
|
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 |
]
|
|
|
10 |
"name": "1",
|
11 |
"path": "1_Pooling",
|
12 |
"type": "sentence_transformers.models.Pooling"
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
}
|
14 |
]
|
sentence_bert_config.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"max_seq_length":
|
3 |
"do_lower_case": false
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"max_seq_length": 64,
|
3 |
"do_lower_case": false
|
4 |
}
|
tokenizer.json
CHANGED
@@ -2,14 +2,12 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
-
"strategy":
|
11 |
-
"Fixed": 128
|
12 |
-
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
15 |
"pad_id": 0,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 64,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
+
"strategy": "BatchLongest",
|
|
|
|
|
11 |
"direction": "Right",
|
12 |
"pad_to_multiple_of": null,
|
13 |
"pad_id": 0,
|
tokenizer_config.json
CHANGED
@@ -43,12 +43,10 @@
|
|
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":
|
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,
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
|
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"max_length": 64,
|
49 |
"model_max_length": 512,
|
|
|
50 |
"pad_to_multiple_of": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"pad_token_type_id": 0,
|