Commit
•
aeabcc1
1
Parent(s):
de1fce3
Update README.md
Browse files
README.md
CHANGED
@@ -5,14 +5,48 @@ tags:
|
|
5 |
- feature-extraction
|
6 |
- sentence-similarity
|
7 |
- transformers
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
|
11 |
-
#
|
|
|
|
|
|
|
12 |
|
13 |
-
|
14 |
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
## Usage (Sentence-Transformers)
|
18 |
|
@@ -67,60 +101,3 @@ sentence_embeddings = cls_pooling(model_output, encoded_input['attention_mask'])
|
|
67 |
print("Sentence embeddings:")
|
68 |
print(sentence_embeddings)
|
69 |
```
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
## Evaluation Results
|
74 |
-
|
75 |
-
<!--- Describe how your model was evaluated -->
|
76 |
-
|
77 |
-
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
78 |
-
|
79 |
-
|
80 |
-
## Training
|
81 |
-
The model was trained with the parameters:
|
82 |
-
|
83 |
-
**DataLoader**:
|
84 |
-
|
85 |
-
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 15699 with parameters:
|
86 |
-
```
|
87 |
-
{'batch_size': 4}
|
88 |
-
```
|
89 |
-
|
90 |
-
**Loss**:
|
91 |
-
|
92 |
-
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
|
93 |
-
```
|
94 |
-
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
95 |
-
```
|
96 |
-
|
97 |
-
Parameters of the fit()-Method:
|
98 |
-
```
|
99 |
-
{
|
100 |
-
"epochs": 1,
|
101 |
-
"evaluation_steps": 0,
|
102 |
-
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
|
103 |
-
"max_grad_norm": 1,
|
104 |
-
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
105 |
-
"optimizer_params": {
|
106 |
-
"lr": 2e-05
|
107 |
-
},
|
108 |
-
"scheduler": "WarmupLinear",
|
109 |
-
"steps_per_epoch": null,
|
110 |
-
"warmup_steps": 1569,
|
111 |
-
"weight_decay": 0.01
|
112 |
-
}
|
113 |
-
```
|
114 |
-
|
115 |
-
|
116 |
-
## Full Model Architecture
|
117 |
-
```
|
118 |
-
SentenceTransformer(
|
119 |
-
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
120 |
-
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
121 |
-
)
|
122 |
-
```
|
123 |
-
|
124 |
-
## Citing & Authors
|
125 |
-
|
126 |
-
<!--- Describe where people can find more information -->
|
|
|
5 |
- feature-extraction
|
6 |
- sentence-similarity
|
7 |
- transformers
|
8 |
+
license: cc-by-4.0
|
9 |
+
language: te
|
10 |
+
widget:
|
11 |
+
- source_sentence: "ఒక మహిళ ఉల్లిపాయను కత్తిస్తోంది"
|
12 |
+
sentences:
|
13 |
+
- "ఒక స్త్రీ ఉల్లిపాయలు కోస్తోంది"
|
14 |
+
- "ఒక స్త్రీ బంగాళాదుంపను తొక్కడం"
|
15 |
+
- "ఒక పిల్లి ఇంటి చుట్టూ నడుస్తోంది"
|
16 |
+
example_title: "Example 1"
|
17 |
+
|
18 |
+
- source_sentence: "పిల్లల బృందం జంపింగ్ పోటీని నిర్వహిస్తోంది"
|
19 |
+
sentences:
|
20 |
+
- "పిల్లల గుంపు సరదాగా గడుపుతోంది"
|
21 |
+
- "పిల్లలు పార్కులో ఆడుకోవడానికి ఇష్టపడతారు"
|
22 |
+
- "ముగ్గురు అబ్బాయిలు నడుస్తున్నారు"
|
23 |
+
example_title: "Example 2"
|
24 |
+
|
25 |
+
- source_sentence: "మీ రెండు ప్రశ్నలకు అవుననే సమాధానం వస్తుంది"
|
26 |
+
sentences:
|
27 |
+
- "రెండు ప్రశ్నలకు అవుననే సమాధానం వస్తోంది"
|
28 |
+
- "మేము మీ అన్ని ప్రశ్నలకు సమాధానమిచ్చాము"
|
29 |
+
- "నేను ఈ ప్రశ్నకు సమాధానం ఇస్తాను"
|
30 |
+
example_title: "Example 3"
|
31 |
---
|
32 |
|
33 |
+
# TeluguSBERT
|
34 |
+
|
35 |
+
This is a TeluguBERT model (l3cube-pune/telugu-bert) trained on the NLI dataset. <br>
|
36 |
+
Released as a part of project MahaNLP: https://github.com/l3cube-pune/MarathiNLP <br>
|
37 |
|
38 |
+
A better sentence similarity model (fine-tuned version of this model) is shared here: https://huggingface.co/l3cube-pune/telugu-sentence-similarity-sbert <br>
|
39 |
|
40 |
+
More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2211.11187)
|
41 |
+
|
42 |
+
```
|
43 |
+
@article{joshi2022l3cubemahasbert,
|
44 |
+
title={L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi},
|
45 |
+
author={Joshi, Ananya and Kajale, Aditi and Gadre, Janhavi and Deode, Samruddhi and Joshi, Raviraj},
|
46 |
+
journal={arXiv preprint arXiv:2211.11187},
|
47 |
+
year={2022}
|
48 |
+
}
|
49 |
+
```
|
50 |
|
51 |
## Usage (Sentence-Transformers)
|
52 |
|
|
|
101 |
print("Sentence embeddings:")
|
102 |
print(sentence_embeddings)
|
103 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|