Commit
•
7b44f7c
1
Parent(s):
1f18fec
Add SetFit model
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +7 -0
- README.md +49 -0
- config.json +29 -0
- config_sentence_transformers.json +7 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- pytorch_model.bin +3 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
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 |
+
}
|
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
pipeline_tag: text-classification
|
8 |
+
---
|
9 |
+
|
10 |
+
# fathyshalab/reklambox2-2-20
|
11 |
+
|
12 |
+
This is a [SetFit model](https://github.com/huggingface/setfit) that can be used for text classification. The model has been trained using an efficient few-shot learning technique that involves:
|
13 |
+
|
14 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
15 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
16 |
+
|
17 |
+
## Usage
|
18 |
+
|
19 |
+
To use this model for inference, first install the SetFit library:
|
20 |
+
|
21 |
+
```bash
|
22 |
+
python -m pip install setfit
|
23 |
+
```
|
24 |
+
|
25 |
+
You can then run inference as follows:
|
26 |
+
|
27 |
+
```python
|
28 |
+
from setfit import SetFitModel
|
29 |
+
|
30 |
+
# Download from Hub and run inference
|
31 |
+
model = SetFitModel.from_pretrained("fathyshalab/reklambox2-2-20")
|
32 |
+
# Run inference
|
33 |
+
preds = model(["i loved the spiderman movie!", "pineapple on pizza is the worst 🤮"])
|
34 |
+
```
|
35 |
+
|
36 |
+
## BibTeX entry and citation info
|
37 |
+
|
38 |
+
```bibtex
|
39 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
40 |
+
doi = {10.48550/ARXIV.2209.11055},
|
41 |
+
url = {https://arxiv.org/abs/2209.11055},
|
42 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
43 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
44 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
45 |
+
publisher = {arXiv},
|
46 |
+
year = {2022},
|
47 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
48 |
+
}
|
49 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/fathy/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-mpnet-base-v2/",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "xlm-roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.20.0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250002
|
29 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.0.0",
|
4 |
+
"transformers": "4.7.0",
|
5 |
+
"pytorch": "1.9.0+cu102"
|
6 |
+
}
|
7 |
+
}
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fabf34709125abec76c18e6d4ea062a4312e514ae0313a661b5f1924454a6c5
|
3 |
+
size 87063
|
modules.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
]
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51a3265fa256a25e6ddc8cd01edb8cbbcee443de9eeaccec908c36a7f426598e
|
3 |
+
size 1112245805
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 128,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
|
3 |
+
size 17082913
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "/home/fathy/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-mpnet-base-v2/",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|