Commit
•
f65aba2
1
Parent(s):
cb36cd8
Upload 12 files
Browse files- 1_Pooling/config.json +9 -0
- README.md +86 -1
- config.json +25 -0
- config_sentence_transformers.json +7 -0
- model_head.pkl +3 -0
- modules.json +20 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- vocab.txt +0 -0
1_Pooling/config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
README.md
CHANGED
@@ -1,3 +1,88 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
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 1024 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 133200 with parameters:
|
50 |
+
```
|
51 |
+
{'batch_size': 8, '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": 2,
|
62 |
+
"evaluation_steps": 0,
|
63 |
+
"evaluator": "NoneType",
|
64 |
+
"max_grad_norm": 1,
|
65 |
+
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
66 |
+
"optimizer_params": {
|
67 |
+
"lr": 2e-05
|
68 |
+
},
|
69 |
+
"scheduler": "WarmupLinear",
|
70 |
+
"steps_per_epoch": 266400,
|
71 |
+
"warmup_steps": 26640,
|
72 |
+
"weight_decay": 0.01
|
73 |
+
}
|
74 |
+
```
|
75 |
+
|
76 |
+
|
77 |
+
## Full Model Architecture
|
78 |
+
```
|
79 |
+
SentenceTransformer(
|
80 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
81 |
+
(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})
|
82 |
+
(2): Normalize()
|
83 |
+
)
|
84 |
+
```
|
85 |
+
|
86 |
+
## Citing & Authors
|
87 |
+
|
88 |
+
<!--- Describe where people can find more information -->
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/knut/.cache/torch/sentence_transformers/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": "4.29.2",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.29.2",
|
5 |
+
"pytorch": "1.13.1+cu117"
|
6 |
+
}
|
7 |
+
}
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e47afc249145dc4e5b9f603b4f27ecfbfb9bcb4305781c92a750608c31a2f6e3
|
3 |
+
size 9013223
|
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": "2",
|
17 |
+
"path": "2_Normalize",
|
18 |
+
"type": "sentence_transformers.models.Normalize"
|
19 |
+
}
|
20 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3443e6dbdd1de4cbf2913233c549234105e280687472133020bb7305b57aa9
|
3 |
+
size 1340703853
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|