Upload README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ tags:
|
|
| 8 |
|
| 9 |
---
|
| 10 |
|
| 11 |
-
#
|
| 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 |
|
|
@@ -26,12 +26,9 @@ Then you can use the model like this:
|
|
| 26 |
|
| 27 |
```python
|
| 28 |
from sentence_transformers import SentenceTransformer
|
| 29 |
-
sentences = ["
|
| 30 |
-
"Menara Eifel terletak di Paris, Perancis",
|
| 31 |
-
"Pizza adalah makanan khas Italia",
|
| 32 |
-
"Saya kuliah di Carneige Mellon University"]
|
| 33 |
|
| 34 |
-
model = SentenceTransformer('
|
| 35 |
embeddings = model.encode(sentences)
|
| 36 |
print(embeddings)
|
| 37 |
```
|
|
@@ -54,15 +51,11 @@ def mean_pooling(model_output, attention_mask):
|
|
| 54 |
|
| 55 |
|
| 56 |
# Sentences we want sentence embeddings for
|
| 57 |
-
sentences = [
|
| 58 |
-
"Menara Eifel terletak di Paris, Perancis",
|
| 59 |
-
"Pizza adalah makanan khas Italia",
|
| 60 |
-
"Saya kuliah di Carneige Melon University"]
|
| 61 |
-
|
| 62 |
|
| 63 |
# Load model from HuggingFace Hub
|
| 64 |
-
tokenizer = AutoTokenizer.from_pretrained('
|
| 65 |
-
model = AutoModel.from_pretrained('
|
| 66 |
|
| 67 |
# Tokenize sentences
|
| 68 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
|
@@ -92,7 +85,7 @@ The model was trained with the parameters:
|
|
| 92 |
|
| 93 |
**DataLoader**:
|
| 94 |
|
| 95 |
-
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length
|
| 96 |
```
|
| 97 |
{'batch_size': 16}
|
| 98 |
```
|
|
@@ -107,7 +100,7 @@ The model was trained with the parameters:
|
|
| 107 |
Parameters of the fit()-Method:
|
| 108 |
```
|
| 109 |
{
|
| 110 |
-
"epochs":
|
| 111 |
"evaluation_steps": 0,
|
| 112 |
"evaluator": "NoneType",
|
| 113 |
"max_grad_norm": 1,
|
|
@@ -117,7 +110,7 @@ Parameters of the fit()-Method:
|
|
| 117 |
},
|
| 118 |
"scheduler": "WarmupLinear",
|
| 119 |
"steps_per_epoch": null,
|
| 120 |
-
"warmup_steps":
|
| 121 |
"weight_decay": 0.01
|
| 122 |
}
|
| 123 |
```
|
|
|
|
| 8 |
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# {MODEL_NAME}
|
| 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 |
|
|
|
|
| 26 |
|
| 27 |
```python
|
| 28 |
from sentence_transformers import SentenceTransformer
|
| 29 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
| 32 |
embeddings = model.encode(sentences)
|
| 33 |
print(embeddings)
|
| 34 |
```
|
|
|
|
| 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('{MODEL_NAME}')
|
| 58 |
+
model = AutoModel.from_pretrained('{MODEL_NAME}')
|
| 59 |
|
| 60 |
# Tokenize sentences
|
| 61 |
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
|
|
|
|
| 85 |
|
| 86 |
**DataLoader**:
|
| 87 |
|
| 88 |
+
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 19861 with parameters:
|
| 89 |
```
|
| 90 |
{'batch_size': 16}
|
| 91 |
```
|
|
|
|
| 100 |
Parameters of the fit()-Method:
|
| 101 |
```
|
| 102 |
{
|
| 103 |
+
"epochs": 5,
|
| 104 |
"evaluation_steps": 0,
|
| 105 |
"evaluator": "NoneType",
|
| 106 |
"max_grad_norm": 1,
|
|
|
|
| 110 |
},
|
| 111 |
"scheduler": "WarmupLinear",
|
| 112 |
"steps_per_epoch": null,
|
| 113 |
+
"warmup_steps": 9930,
|
| 114 |
"weight_decay": 0.01
|
| 115 |
}
|
| 116 |
```
|