Upload with huggingface_hub
Browse files- 1_Pooling/config.json +7 -0
- 2_Dense/config.json +1 -0
- 2_Dense/pytorch_model.bin +3 -0
- README.md +89 -1
- config.json +2 -2
- pytorch_model.bin +2 -2
- tokenizer_config.json +1 -1
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 |
+
}
|
2_Dense/config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"in_features": 768, "out_features": 512, "bias": true, "activation_function": "torch.nn.modules.activation.Tanh"}
|
2_Dense/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fede9032f7e4183ec18aac747b21d4e8ca0a1bbe3e7cfbf208f7f9acbc8e08c
|
3 |
+
size 1575975
|
README.md
CHANGED
@@ -1,3 +1,91 @@
|
|
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 512 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 64769 with parameters:
|
50 |
+
```
|
51 |
+
{'batch_size': 80, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
52 |
+
```
|
53 |
+
|
54 |
+
**Loss**:
|
55 |
+
|
56 |
+
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
57 |
+
```
|
58 |
+
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
59 |
+
```
|
60 |
+
|
61 |
+
Parameters of the fit()-Method:
|
62 |
+
```
|
63 |
+
{
|
64 |
+
"epochs": 20,
|
65 |
+
"evaluation_steps": 0,
|
66 |
+
"evaluator": "NoneType",
|
67 |
+
"max_grad_norm": 1,
|
68 |
+
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
69 |
+
"optimizer_params": {
|
70 |
+
"lr": 2e-05
|
71 |
+
},
|
72 |
+
"scheduler": "WarmupLinear",
|
73 |
+
"steps_per_epoch": null,
|
74 |
+
"warmup_steps": 129538,
|
75 |
+
"weight_decay": 0.01
|
76 |
+
}
|
77 |
+
```
|
78 |
+
|
79 |
+
|
80 |
+
## Full Model Architecture
|
81 |
+
```
|
82 |
+
SentenceTransformer(
|
83 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel
|
84 |
+
(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})
|
85 |
+
(2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
|
86 |
+
)
|
87 |
+
```
|
88 |
+
|
89 |
+
## Citing & Authors
|
90 |
+
|
91 |
+
<!--- Describe where people can find more information -->
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertModel"
|
@@ -21,6 +21,6 @@
|
|
21 |
"sinusoidal_pos_embds": false,
|
22 |
"tie_weights_": true,
|
23 |
"torch_dtype": "float32",
|
24 |
-
"transformers_version": "4.
|
25 |
"vocab_size": 119547
|
26 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v2/",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertModel"
|
|
|
21 |
"sinusoidal_pos_embds": false,
|
22 |
"tie_weights_": true,
|
23 |
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.23.1",
|
25 |
"vocab_size": 119547
|
26 |
}
|
pytorch_model.bin
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 sha256:104232b098726da9f703da7d7c3154112b57373a6ac3f52dff454e0bdc37ecdf
|
3 |
+
size 538968313
|
tokenizer_config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"full_tokenizer_file": null,
|
6 |
"mask_token": "[MASK]",
|
7 |
"max_len": 512,
|
8 |
-
"name_or_path": "
|
9 |
"never_split": null,
|
10 |
"pad_token": "[PAD]",
|
11 |
"sep_token": "[SEP]",
|
|
|
5 |
"full_tokenizer_file": null,
|
6 |
"mask_token": "[MASK]",
|
7 |
"max_len": 512,
|
8 |
+
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_distiluse-base-multilingual-cased-v2/",
|
9 |
"never_split": null,
|
10 |
"pad_token": "[PAD]",
|
11 |
"sep_token": "[SEP]",
|